% Embodied AI Radar - curated papers (1344 entries), built from arXiv metadata (CC0). % https://embodied-ai-radar.com/ @misc{brohan2022rt, title = {{RT-1: Robotics Transformer for Real-World Control at Scale}}, author = {Anthony Brohan and Noah Brown and Justice Carbajal and Yevgen Chebotar and Joseph Dabis and Chelsea Finn and Keerthana Gopalakrishnan and Karol Hausman and Alex Herzog and Jasmine Hsu and Julian Ibarz and Brian Ichter and Alex Irpan and Tomas Jackson and Sally Jesmonth and Nikhil J Joshi and Ryan Julian and Dmitry Kalashnikov and Yuheng Kuang and Isabel Leal and Kuang-Huei Lee and Sergey Levine and Yao Lu and Utsav Malla and Deeksha Manjunath and Igor Mordatch and Ofir Nachum and Carolina Parada and Jodilyn Peralta and Emily Perez and Karl Pertsch and Jornell Quiambao and Kanishka Rao and Michael Ryoo and Grecia Salazar and Pannag Sanketi and Kevin Sayed and Jaspiar Singh and Sumedh Sontakke and Austin Stone and Clayton Tan and Huong Tran and Vincent Vanhoucke and Steve Vega and Quan Vuong and Fei Xia and Ted Xiao and Peng Xu and Sichun Xu and Tianhe Yu and others}, year = {2022}, eprint = {2212.06817}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2212.06817}, } @misc{brohan2023rt, title = {{RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control}}, author = {Anthony Brohan and Noah Brown and Justice Carbajal and Yevgen Chebotar and Xi Chen and Krzysztof Choromanski and Tianli Ding and Danny Driess and Avinava Dubey and Chelsea Finn and Pete Florence and Chuyuan Fu and Montse Gonzalez Arenas and Keerthana Gopalakrishnan and Kehang Han and Karol Hausman and Alexander Herzog and Jasmine Hsu and Brian Ichter and Alex Irpan and Nikhil Joshi and Ryan Julian and Dmitry Kalashnikov and Yuheng Kuang and Isabel Leal and Lisa Lee and Tsang-Wei Edward Lee and Sergey Levine and Yao Lu and Henryk Michalewski and Igor Mordatch and Karl Pertsch and Kanishka Rao and Krista Reymann and Michael Ryoo and Grecia Salazar and Pannag Sanketi and Pierre Sermanet and Jaspiar Singh and Anikait Singh and Radu Soricut and Huong Tran and Vincent Vanhoucke and Quan Vuong and Ayzaan Wahid and Stefan Welker and Paul Wohlhart and Jialin Wu and Fei Xia and Ted Xiao and others}, year = {2023}, eprint = {2307.15818}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2307.15818}, } @misc{team2024octo, title = {{Octo: An Open-Source Generalist Robot Policy}}, author = {Octo Model Team and Dibya Ghosh and Homer Walke and Karl Pertsch and Kevin Black and Oier Mees and Sudeep Dasari and Joey Hejna and Tobias Kreiman and Charles Xu and Jianlan Luo and You Liang Tan and Lawrence Yunliang Chen and Pannag Sanketi and Quan Vuong and Ted Xiao and Dorsa Sadigh and Chelsea Finn and Sergey Levine}, year = {2024}, eprint = {2405.12213}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2405.12213}, } @misc{kim2024openvla, title = {{OpenVLA: An Open-Source Vision-Language-Action Model}}, author = {Moo Jin Kim and Karl Pertsch and Siddharth Karamcheti and Ted Xiao and Ashwin Balakrishna and Suraj Nair and Rafael Rafailov and Ethan Foster and Grace Lam and Pannag Sanketi and Quan Vuong and Thomas Kollar and Benjamin Burchfiel and Russ Tedrake and Dorsa Sadigh and Sergey Levine and Percy Liang and Chelsea Finn}, year = {2024}, eprint = {2406.09246}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.09246}, } @misc{kim2025fine, title = {{Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success}}, author = {Moo Jin Kim and Chelsea Finn and Percy Liang}, year = {2025}, eprint = {2502.19645}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.19645}, } @misc{black2024vision, title = {{$π_0$: A Vision-Language-Action Flow Model for General Robot Control}}, author = {Kevin Black and Noah Brown and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Lucy Xiaoyang Shi and James Tanner and Quan Vuong and Anna Walling and Haohuan Wang and Ury Zhilinsky}, year = {2024}, eprint = {2410.24164}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2410.24164}, } @misc{intelligence2025vision, title = {{$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization}}, author = {Physical Intelligence and Kevin Black and Noah Brown and James Darpinian and Karan Dhabalia and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Manuel Y. Galliker and Dibya Ghosh and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and James Tanner and Quan Vuong and Homer Walke and Anna Walling and Haohuan Wang and Lili Yu and Ury Zhilinsky}, year = {2025}, eprint = {2504.16054}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2504.16054}, } @misc{pertsch2025fast, title = {{FAST: Efficient Action Tokenization for Vision-Language-Action Models}}, author = {Karl Pertsch and Kyle Stachowicz and Brian Ichter and Danny Driess and Suraj Nair and Quan Vuong and Oier Mees and Chelsea Finn and Sergey Levine}, year = {2025}, eprint = {2501.09747}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2501.09747}, } @misc{liu2024rdt, title = {{RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation}}, author = {Songming Liu and Lingxuan Wu and Bangguo Li and Hengkai Tan and Huayu Chen and Zhengyi Wang and Ke Xu and Hang Su and Jun Zhu}, year = {2024}, eprint = {2410.07864}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.07864}, } @misc{nvidia2025gr, title = {{GR00T N1: An Open Foundation Model for Generalist Humanoid Robots}}, author = {NVIDIA and : and Johan Bjorck and Fernando Castañeda and Nikita Cherniadev and Xingye Da and Runyu Ding and Linxi "Jim" Fan and Yu Fang and Dieter Fox and Fengyuan Hu and Spencer Huang and Joel Jang and Zhenyu Jiang and Jan Kautz and Kaushil Kundalia and Lawrence Lao and Zhiqi Li and Zongyu Lin and Kevin Lin and Guilin Liu and Edith Llontop and Loic Magne and Ajay Mandlekar and Avnish Narayan and Soroush Nasiriany and Scott Reed and You Liang Tan and Guanzhi Wang and Zu Wang and Jing Wang and Qi Wang and Jiannan Xiang and Yuqi Xie and Yinzhen Xu and Zhenjia Xu and Seonghyeon Ye and Zhiding Yu and Ao Zhang and Hao Zhang and Yizhou Zhao and Ruijie Zheng and Yuke Zhu}, year = {2025}, eprint = {2503.14734}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.14734}, } @misc{shukor2025smolvla, title = {{SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics}}, author = {Mustafa Shukor and Dana Aubakirova and Francesco Capuano and Pepijn Kooijmans and Steven Palma and Adil Zouitine and Michel Aractingi and Caroline Pascal and Martino Russi and Andres Marafioti and Simon Alibert and Matthieu Cord and Thomas Wolf and Remi Cadene}, year = {2025}, eprint = {2506.01844}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2506.01844}, } @misc{team2025gemini, title = {{Gemini Robotics: Bringing AI into the Physical World}}, author = {Gemini Robotics Team and Saminda Abeyruwan and Joshua Ainslie and Jean-Baptiste Alayrac and Montserrat Gonzalez Arenas and Travis Armstrong and Ashwin Balakrishna and Robert Baruch and Maria Bauza and Michiel Blokzijl and Steven Bohez and Konstantinos Bousmalis and Anthony Brohan and Thomas Buschmann and Arunkumar Byravan and Serkan Cabi and Ken Caluwaerts and Federico Casarini and Oscar Chang and Jose Enrique Chen and Xi Chen and Hao-Tien Lewis Chiang and Krzysztof Choromanski and David D'Ambrosio and Sudeep Dasari and Todor Davchev and Coline Devin and Norman Di Palo and Tianli Ding and Adil Dostmohamed and Danny Driess and Yilun Du and Debidatta Dwibedi and Michael Elabd and Claudio Fantacci and Cody Fong and Erik Frey and Chuyuan Fu and Marissa Giustina and Keerthana Gopalakrishnan and Laura Graesser and Leonard Hasenclever and Nicolas Heess and Brandon Hernaez and Alexander Herzog and R. Alex Hofer and Jan Humplik and Atil Iscen and Mithun George Jacob and Deepali Jain and others}, year = {2025}, eprint = {2503.20020}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.20020}, } @misc{driess2023palm, title = {{PaLM-E: An Embodied Multimodal Language Model}}, author = {Danny Driess and Fei Xia and Mehdi S. M. Sajjadi and Corey Lynch and Aakanksha Chowdhery and Brian Ichter and Ayzaan Wahid and Jonathan Tompson and Quan Vuong and Tianhe Yu and Wenlong Huang and Yevgen Chebotar and Pierre Sermanet and Daniel Duckworth and Sergey Levine and Vincent Vanhoucke and Karol Hausman and Marc Toussaint and Klaus Greff and Andy Zeng and Igor Mordatch and Pete Florence}, year = {2023}, eprint = {2303.03378}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2303.03378}, } @misc{reed2022generalist, title = {{A Generalist Agent}}, author = {Scott Reed and Konrad Zolna and Emilio Parisotto and Sergio Gomez Colmenarejo and Alexander Novikov and Gabriel Barth-Maron and Mai Gimenez and Yury Sulsky and Jackie Kay and Jost Tobias Springenberg and Tom Eccles and Jake Bruce and Ali Razavi and Ashley Edwards and Nicolas Heess and Yutian Chen and Raia Hadsell and Oriol Vinyals and Mahyar Bordbar and Nando de Freitas}, year = {2022}, eprint = {2205.06175}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2205.06175}, } @misc{marrie2026reki, title = {{REKI: Registering Knowledge in VLAs}}, author = {Juliette Marrie and Paul Pacaud and Adrien Ramanana Rahary and Shizhe Chen and Moritz Böhle}, year = {2026}, eprint = {2610.22178}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22178}, } @misc{sun2026ltm, title = {{LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models}}, author = {Qixin Sun and WenLong Gao and Xiansheng Chen and Zhongyuan Wang and Si Liu and Pengwei Wang}, year = {2026}, eprint = {2610.21362}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.21362}, } @misc{xu2026fastvla, title = {{FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action Models}}, author = {Jiuyi Xu and Chengyuan Qian and Zhengzhong Tu and Yang Sui and Yangming Shi}, year = {2026}, eprint = {2610.22146}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22146}, } @misc{du2026nestedvla, title = {{NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models}}, author = {Guodong Du and Wanyu Lin}, year = {2026}, eprint = {2610.23271}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23271}, } @misc{li2024cogact, title = {{CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation}}, author = {Qixiu Li and Yaobo Liang and Zeyu Wang and Lin Luo and Xi Chen and Mozheng Liao and Fangyun Wei and Yu Deng and Sicheng Xu and Yizhong Zhang and Xiaofan Wang and Bei Liu and Jianlong Fu and Jianmin Bao and Dong Chen and Yuanchun Shi and Jiaolong Yang and Baining Guo}, year = {2024}, eprint = {2411.19650}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2411.19650}, } @misc{team2025robobrain, title = {{RoboBrain 2.0 Technical Report}}, author = {BAAI RoboBrain Team and Mingyu Cao and Huajie Tan and Yuheng Ji and Xiansheng Chen and Minglan Lin and Zhiyu Li and Zhou Cao and Pengwei Wang and Enshen Zhou and Yi Han and Yingbo Tang and Xiangqi Xu and Wei Guo and Yaoxu Lyu and Yijie Xu and Jiayu Shi and Mengfei Du and Cheng Chi and Mengdi Zhao and Xiaoshuai Hao and Junkai Zhao and Xiaojie Zhang and Shanyu Rong and Huaihai Lyu and Zhengliang Cai and Yankai Fu and Ning Chen and Bolun Zhang and Lingfeng Zhang and Shuyi Zhang and Dong Liu and Xi Feng and Songjing Wang and Xiaodan Liu and Yance Jiao and Mengsi Lyu and Zhuo Chen and Chenrui He and Yulong Ao and Xue Sun and Zheqi He and Jingshu Zheng and Xi Yang and Donghai Shi and Kunchang Xie and Bochao Zhang and Shaokai Nie and Chunlei Men and Yonghua Lin and others}, year = {2025}, eprint = {2507.02029}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.02029}, } @misc{lu2026vla, title = {{VLA-$Δ$: Learning Physical State Transition for Vision-Language-Action Models}}, author = {Qi Lu and Jiarun Li and Ce Zhang and Miao Pan and Yi Pan and Xu Wang and Wenqi Zhang and Xuhong Zhang}, year = {2026}, eprint = {2610.21306}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.21306}, } @misc{pham2026mambaact, title = {{MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models}}, author = {Khuyen Pham and Tran Nguyen Le and Edoardo Fazzari and Cesare Stefanini}, year = {2026}, eprint = {2610.22951}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22951}, } @misc{shi2025hi, title = {{Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models}}, author = {Lucy Xiaoyang Shi and Brian Ichter and Michael Equi and Liyiming Ke and Karl Pertsch and Quan Vuong and James Tanner and Anna Walling and Haohuan Wang and Niccolo Fusai and Adrian Li-Bell and Danny Driess and Lachy Groom and Sergey Levine and Chelsea Finn}, year = {2025}, eprint = {2502.19417}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.19417}, } @misc{jiang2022vima, title = {{VIMA: General Robot Manipulation with Multimodal Prompts}}, author = {Yunfan Jiang and Agrim Gupta and Zichen Zhang and Guanzhi Wang and Yongqiang Dou and Yanjun Chen and Li Fei-Fei and Anima Anandkumar and Yuke Zhu and Linxi Fan}, year = {2022}, eprint = {2210.03094}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2210.03094}, } @misc{hong2026condensevla, title = {{CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA}}, author = {Feiyang Hong and Yujie Wei and Bo Zhao and Xiu Su and Hongxun Yao and Shuo Yang}, year = {2026}, eprint = {2610.25927}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.25927}, } @misc{cheang2025gr, title = {{GR-3 Technical Report}}, author = {Chilam Cheang and Sijin Chen and Zhongren Cui and Yingdong Hu and Liqun Huang and Tao Kong and Hang Li and Yifeng Li and Yuxiao Liu and Xiao Ma and Hao Niu and Wenxuan Ou and Wanli Peng and Zeyu Ren and Haixin Shi and Jiawen Tian and Hongtao Wu and Xin Xiao and Yuyang Xiao and Jiafeng Xu and Yichu Yang}, year = {2025}, eprint = {2507.15493}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.15493}, } @misc{bu2025univla, title = {{UniVLA: Learning to Act Anywhere with Task-centric Latent Actions}}, author = {Qingwen Bu and Yanting Yang and Jisong Cai and Shenyuan Gao and Guanghui Ren and Maoqing Yao and Ping Luo and Hongyang Li}, year = {2025}, eprint = {2505.06111}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.06111}, } @misc{qu2025spatialvla, title = {{SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model}}, author = {Delin Qu and Haoming Song and Qizhi Chen and Yuanqi Yao and Xinyi Ye and Yan Ding and Zhigang Wang and JiaYuan Gu and Bin Zhao and Dong Wang and Xuelong Li}, year = {2025}, eprint = {2501.15830}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2501.15830}, } @misc{keller2026post, title = {{Post-hoc Epistemic Uncertainty for Vision-Language-Action Policies}}, author = {Johannes Keller and Albrecht M. Bloße and Adrian Lindenmeyer and Thomas Neumuth and Daniel Schneider}, year = {2026}, eprint = {2610.29730}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29730}, } @misc{sujit2026when, title = {{When One Step Is Enough: An Empirical Study of Euler Integration in Flow-Matching Policies}}, author = {Shivakanth Sujit and Luca Nunziante and Rousslan Fernand Julien Dossa and Kai Arulkumaran}, year = {2026}, eprint = {2610.30735}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30735}, } @misc{he2026vla, title = {{VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse}}, author = {Sicheng He and Yi Pan and Qiuting Yu and Jiaming Huang and Qi Lu and Shuyan Wu and Hongyan Feng and Xuanyu Liu and Jun Zhang and Jie Zhang and Wenqi Zhang and Xuhong Zhang and Jianwei Yin}, year = {2026}, eprint = {2610.25043}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2610.25043}, } @misc{sensenova2026has, title = {{Has GPT-6-Astra Achieved Embodied Intelligence?}}, author = {SenseNova and Joint Research Team and Zhongang Cai and Ziang Cao and Tailai Chen and Han Chong Chua and Linjun Dai and Hanming Deng and Hokin Deng and Haiwen Diao and Chenjing Ding and Weichen Fan and Xiao Fu and Zerui Gong and Chenyang Gu and Zexin He and Zhi Hou and Bo Li and Qinyue Li and Quanzhou Li and Xiaowan Li and Zhichao Liao and Dahua Lin and Zilong Lin and Bo Liu and Chunxiao Liu and Pengfei Liu and Tianqi Liu and Ziwei Liu and Chen Change Loy and Lewei Lu and Jiapeng Luo and Yuexiao Ma and Liang Pan and Xingang Pan and Oscar Qian and Ziyi Shang and Yuyao Shao and Dawei Su and Dacheng Tao and Qingyi Tao and Quan Wang and Ruisi Wang and Xiaogang Wang and Ziyi Wang and Beichen Wen and Donghao Wu and Jiaxu Wu and Silei Wu and Xiaoming Wu and others}, year = {2026}, eprint = {2610.22471}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22471}, } @misc{ma2024survey, title = {{A Survey on Vision-Language-Action Models for Embodied AI}}, author = {Yueen Ma and Zixing Song and Yuzheng Zhuang and Jianye Hao and Irwin King}, year = {2024}, eprint = {2405.14093}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2405.14093}, } @misc{firoozi2023foundation, title = {{Foundation Models in Robotics: Applications, Challenges, and the Future}}, author = {Roya Firoozi and Johnathan Tucker and Stephen Tian and Anirudha Majumdar and Jiankai Sun and Weiyu Liu and Yuke Zhu and Shuran Song and Ashish Kapoor and Karol Hausman and Brian Ichter and Danny Driess and Jiajun Wu and Cewu Lu and Mac Schwager}, year = {2023}, eprint = {2312.07843}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.07843}, } @misc{liu2024aligning, title = {{Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI}}, author = {Yang Liu and Weixing Chen and Yongjie Bai and Xiaodan Liang and Guanbin Li and Wen Gao and Liang Lin}, year = {2024}, eprint = {2407.06886}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2407.06886}, } @misc{wang2026wave, title = {{WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction}}, author = {Haomin Wang and Anqiong Ji and Ke Wang and Zhongshan Liu and Ru Ying and Ran Zheng and Zhipeng Zhang}, year = {2026}, eprint = {2610.18568}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18568}, } @misc{liu2026morphact, title = {{MorphAct: Robot Policies Morphing with the Worlds They Act In}}, author = {Ziyan Liu and Jiting Liu and Weihong Zhong and Wenda Yu and Yeqiu Chen and Jason Li and Xiaojiang Peng and Shuyuan Hu and Kai Wang and Bo Zhao}, year = {2026}, eprint = {2610.20019}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.20019}, } @misc{wang2026carryon, title = {{CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance}}, author = {Zixuan Wang and Yuqi Liu and Yuxin Chen and Sengqiao Yang and Jinhui Ye and Pengguang Chen and Changsheng Lu and Shu Liu and Bei Yu and Jiaya Jia}, year = {2026}, eprint = {2610.21453}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.21453}, } @misc{qin2026towards, title = {{Towards Agentic Robots: Model, Data, Environment, and Harness}}, author = {Chonghan Qin and Dongming Wu and Kaituo Feng and Jiaxu Wang and Xinlei Yu and Peiwen Sun and Yijia Fan and Xilin He and Bingao Chen and Weitong Lian and Ryan Ji and Wenqi Ren and Xiaobin Hu and Dahua Lin and Yu-Gang Jiang and Xiangyu Yue}, year = {2026}, eprint = {2610.20442}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.20442}, } @misc{chen2026multimodal, title = {{Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use}}, author = {Yanzhe Chen and Ziyi Yang and Jifeng Zhu and Qiming Huang and Ruihe An and Peiyao Xu and Hesen Yang and Runda Liu and Chang Gong and Zhijun Cao and Zechen Bai and Wenzheng Zeng and Yiqi Lin and Guoqiang Liang and Kevin Yuchen Ma and Kevin Qinghong Lin and Mike Zheng Shou}, year = {2026}, eprint = {2610.30108}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30108}, } @misc{lee2025molmoact, title = {{MolmoAct: Action Reasoning Models that can Reason in Space}}, author = {Jason Lee and Jiafei Duan and Haoquan Fang and Yuquan Deng and Shuo Liu and Boyang Li and Bohan Fang and Jieyu Zhang and Yi Ru Wang and Sangho Lee and Winson Han and Wilbert Pumacay and Angelica Wu and Rose Hendrix and Karen Farley and Eli VanderBilt and Ali Farhadi and Dieter Fox and Ranjay Krishna}, year = {2025}, eprint = {2508.07917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.07917}, } @misc{fang2026molmoact, title = {{MolmoAct2: Action Reasoning Models for Real-world Deployment}}, author = {Haoquan Fang and Jiafei Duan and Donovan Clay and Sam Wang and Shuo Liu and Weikai Huang and Xiang Fan and Wei-Chuan Tsai and Shirui Chen and Yi Ru Wang and Shanli Xing and Jaemin Cho and Jae Sung Park and Ainaz Eftekhar and Peter Sushko and Karen Farley and Angad Wadhwa and Cole Harrison and Winson Han and Ying-Chun Lee and Eli VanderBilt and Rose Hendrix and Suveen Ellawela and Lucas Ngoo and Joyce Chai and Zhongzheng Ren and Ali Farhadi and Dieter Fox and Ranjay Krishna}, year = {2026}, eprint = {2605.02881}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.02881}, } @misc{deng2025graspvla, title = {{GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data}}, author = {Shengliang Deng and Mi Yan and Songlin Wei and Haixin Ma and Yuxin Yang and Jiayi Chen and Zhiqi Zhang and Taoyu Yang and Xuheng Zhang and Wenhao Zhang and Heming Cui and Zhizheng Zhang and He Wang}, year = {2025}, eprint = {2505.03233}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.03233}, } @misc{intelligence2025vla, title = {{π*0.6: a VLA That Learns From Experience}}, author = {Physical Intelligence and Ali Amin and Raichelle Aniceto and Ashwin Balakrishna and Kevin Black and Ken Conley and Grace Connors and James Darpinian and Karan Dhabalia and Jared DiCarlo and Danny Driess and Michael Equi and Adnan Esmail and Yunhao Fang and Chelsea Finn and Catherine Glossop and Thomas Godden and Ivan Goryachev and Lachy Groom and Hunter Hancock and Karol Hausman and Gashon Hussein and Brian Ichter and Szymon Jakubczak and Rowan Jen and Tim Jones and Ben Katz and Liyiming Ke and Chandra Kuchi and Marinda Lamb and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Yao Lu and Vishnu Mano and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Charvi Sharma and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and Will Stoeckle and Alex Swerdlow and James Tanner and Marcel Torne and Quan Vuong and Anna Walling and others}, year = {2025}, eprint = {2511.14759}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2511.14759}, } @misc{zheng2025x, title = {{X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model}}, author = {Jinliang Zheng and Jianxiong Li and Zhihao Wang and Dongxiu Liu and Xirui Kang and Yuchun Feng and Yinan Zheng and Jiayin Zou and Yilun Chen and Jia Zeng and Ya-Qin Zhang and Jiangmiao Pang and Jingjing Liu and Tai Wang and Xianyuan Zhan}, year = {2025}, eprint = {2510.10274}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.10274}, } @misc{chen2025internvla, title = {{InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy}}, author = {Xinyi Chen and Yilun Chen and Yanwei Fu and Ning Gao and Jiaya Jia and Weiyang Jin and Hao Li and Yao Mu and Jiangmiao Pang and Yu Qiao and Yang Tian and Bin Wang and Bolun Wang and Fangjing Wang and Hanqing Wang and Tai Wang and Ziqin Wang and Xueyuan Wei and Chao Wu and Shuai Yang and Jinhui Ye and Junqiu Yu and Jia Zeng and Jingjing Zhang and Jinyu Zhang and Shi Zhang and Feng Zheng and Bowen Zhou and Yangkun Zhu}, year = {2025}, eprint = {2510.13778}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.13778}, } @misc{yang2025magma, title = {{Magma: A Foundation Model for Multimodal AI Agents}}, author = {Jianwei Yang and Reuben Tan and Qianhui Wu and Ruijie Zheng and Baolin Peng and Yongyuan Liang and Yu Gu and Mu Cai and Seonghyeon Ye and Joel Jang and Yuquan Deng and Lars Liden and Jianfeng Gao}, year = {2025}, eprint = {2502.13130}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2502.13130}, } @misc{luo2025being, title = {{Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos}}, author = {Hao Luo and Yicheng Feng and Wanpeng Zhang and Sipeng Zheng and Ye Wang and Haoqi Yuan and Jiazheng Liu and Chaoyi Xu and Qin Jin and Zongqing Lu}, year = {2025}, eprint = {2507.15597}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2507.15597}, } @misc{zhai2025igniting, title = {{Igniting VLMs toward the Embodied Space}}, author = {Andy Zhai and Brae Liu and Bruno Fang and Chalse Cai and Ellie Ma and Ethan Yin and Hao Wang and Hugo Zhou and James Wang and Lights Shi and Lucy Liang and Make Wang and Qian Wang and Roy Gan and Ryan Yu and Shalfun Li and Starrick Liu and Sylas Chen and Vincent Chen and Zach Xu}, year = {2025}, eprint = {2509.11766}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.11766}, } @misc{wang2024scaling, title = {{Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers}}, author = {Lirui Wang and Xinlei Chen and Jialiang Zhao and Kaiming He}, year = {2024}, eprint = {2409.20537}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.20537}, } @misc{ye2024latent, title = {{Latent Action Pretraining from Videos}}, author = {Seonghyeon Ye and Joel Jang and Byeongguk Jeon and Sejune Joo and Jianwei Yang and Baolin Peng and Ajay Mandlekar and Reuben Tan and Yu-Wei Chao and Bill Yuchen Lin and Lars Liden and Kimin Lee and Jianfeng Gao and Luke Zettlemoyer and Dieter Fox and Minjoon Seo}, year = {2024}, eprint = {2410.11758}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.11758}, } @misc{li2025hamster, title = {{HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation}}, author = {Yi Li and Yuquan Deng and Jesse Zhang and Joel Jang and Marius Memmel and Raymond Yu and Caelan Reed Garrett and Fabio Ramos and Dieter Fox and Anqi Li and Abhishek Gupta and Ankit Goyal}, year = {2025}, eprint = {2502.05485}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.05485}, } @misc{zhen2024d, title = {{3D-VLA: A 3D Vision-Language-Action Generative World Model}}, author = {Haoyu Zhen and Xiaowen Qiu and Peihao Chen and Jincheng Yang and Xin Yan and Yilun Du and Yining Hong and Chuang Gan}, year = {2024}, eprint = {2403.09631}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2403.09631}, } @misc{dang2026rynnbrain, title = {{RynnBrain: Open Embodied Foundation Models}}, author = {Ronghao Dang and Jiayan Guo and Bohan Hou and Sicong Leng and Kehan Li and Xin Li and Jiangpin Liu and Yunxuan Mao and Zhikai Wang and Yuqian Yuan and Minghao Zhu and Xiao Lin and Yang Bai and Qian Jiang and Yaxi Zhao and Minghua Zeng and Junlong Gao and Yuming Jiang and Jun Cen and Siteng Huang and Liuyi Wang and Wenqiao Zhang and Chengju Liu and Jianfei Yang and Shijian Lu and Deli Zhao}, year = {2026}, eprint = {2602.14979}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.14979}, } @misc{singh2026full, title = {{Full-Weight VLA Fine-Tuning Without an fp32 Master Copy Silently Erases Most Updates}}, author = {Shubham Singh}, year = {2026}, eprint = {2610.31859}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31859}, } @misc{cheang2024gr, title = {{GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation}}, author = {Chi-Lam Cheang and Guangzeng Chen and Ya Jing and Tao Kong and Hang Li and Yifeng Li and Yuxiao Liu and Hongtao Wu and Jiafeng Xu and Yichu Yang and Hanbo Zhang and Minzhao Zhu}, year = {2024}, eprint = {2410.06158}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.06158}, } @misc{zheng2024tracevla, title = {{TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies}}, author = {Ruijie Zheng and Yongyuan Liang and Shuaiyi Huang and Jianfeng Gao and Hal Daumé and Andrey Kolobov and Furong Huang and Jianwei Yang}, year = {2024}, eprint = {2412.10345}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.10345}, } @misc{lin2025onetwovla, title = {{OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning}}, author = {Fanqi Lin and Ruiqian Nai and Yingdong Hu and Jiacheng You and Junming Zhao and Yang Gao}, year = {2025}, eprint = {2505.11917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.11917}, } @misc{wen2025dexvla, title = {{DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control}}, author = {Junjie Wen and Yichen Zhu and Jinming Li and Zhibin Tang and Chaomin Shen and Feifei Feng}, year = {2025}, eprint = {2502.05855}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.05855}, } @misc{wen2024tinyvla, title = {{TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation}}, author = {Junjie Wen and Yichen Zhu and Jinming Li and Minjie Zhu and Kun Wu and Zhiyuan Xu and Ning Liu and Ran Cheng and Chaomin Shen and Yaxin Peng and Feifei Feng and Jian Tang}, year = {2024}, eprint = {2409.12514}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.12514}, } @misc{zhou2025chatvla, title = {{ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model}}, author = {Zhongyi Zhou and Yichen Zhu and Minjie Zhu and Junjie Wen and Ning Liu and Zhiyuan Xu and Weibin Meng and Ran Cheng and Yaxin Peng and Chaomin Shen and Feifei Feng}, year = {2025}, eprint = {2502.14420}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.14420}, } @misc{song2025hume, title = {{Hume: Introducing System-2 Thinking in Visual-Language-Action Model}}, author = {Haoming Song and Delin Qu and Yuanqi Yao and Qizhi Chen and Qi Lv and Yiwen Tang and Modi Shi and Guanghui Ren and Maoqing Yao and Bin Zhao and Dong Wang and Xuelong Li}, year = {2025}, eprint = {2505.21432}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.21432}, } @misc{im2025twinvla, title = {{TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models}}, author = {Hokyun Im and Euijin Jeong and Andrey Kolobov and Jianlong Fu and Youngwoon Lee}, year = {2025}, eprint = {2511.05275}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.05275}, } @misc{wang2025vq, title = {{VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers}}, author = {Yating Wang and Haoyi Zhu and Mingyu Liu and Jiange Yang and Hao-Shu Fang and Tong He}, year = {2025}, eprint = {2507.01016}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.01016}, } @misc{team2025gigabrain, title = {{GigaBrain-0: A World Model-Powered Vision-Language-Action Model}}, author = {GigaBrain Team and Angen Ye and Boyuan Wang and Chaojun Ni and Guan Huang and Guosheng Zhao and Haoyun Li and Jie Li and Jiagang Zhu and Lv Feng and Peng Li and Qiuping Deng and Runqi Ouyang and Wenkang Qin and Xinze Chen and Xiaofeng Wang and Yang Wang and Yifan Li and Yilong Li and Yiran Ding and Yuan Xu and Yun Ye and Yukun Zhou and Zhehao Dong and Zhenan Wang and Zhichao Liu and Zheng Zhu}, year = {2025}, eprint = {2510.19430}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.19430}, } @misc{team2026gigabrain, title = {{GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning}}, author = {GigaBrain Team and Boyuan Wang and Bohan Li and Chaojun Ni and Guan Huang and Guosheng Zhao and Hao Li and Jie Li and Jindi Lv and Jingyu Liu and Lv Feng and Mingming Yu and Peng Li and Qiuping Deng and Tianze Liu and Xinyu Zhou and Xinze Chen and Xiaofeng Wang and Yang Wang and Yifan Li and Yifei Nie and Yilong Li and Yukun Zhou and Yun Ye and Zhichao Liu and Zheng Zhu}, year = {2026}, eprint = {2602.12099}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2602.12099}, } @misc{jiang2025galaxea, title = {{Galaxea Open-World Dataset and G0 Dual-System VLA Model}}, author = {Tao Jiang and Tianyuan Yuan and Yicheng Liu and Chenhao Lu and Jianning Cui and Xiao Liu and Shuiqi Cheng and Jiyang Gao and Huazhe Xu and Hang Zhao}, year = {2025}, eprint = {2509.00576}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.00576}, } @misc{tan2025roboos, title = {{RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration}}, author = {Huajie Tan and Xiaoshuai Hao and Cheng Chi and Minglan Lin and Yaoxu Lyu and Mingyu Cao and Dong Liang and Zhuo Chen and Mengsi Lyu and Cheng Peng and Chenrui He and Yulong Ao and Yonghua Lin and Pengwei Wang and Zhongyuan Wang and Shanghang Zhang}, year = {2025}, eprint = {2505.03673}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.03673}, } @misc{espinola2026from, title = {{From Reasoning to Action: Benchmarking Frontier AI Models on LIBERO-10 Robot Manipulation Tasks}}, author = {May Espinola and Qifan Zhang and Yu Xiang}, year = {2026}, eprint = {2610.30051}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30051}, } @misc{lin2026fastharness, title = {{FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies}}, author = {Tao Lin and Yuxin Du and Haoxiao Wang and Zile Zhong and Bo Zhao}, year = {2026}, eprint = {2610.31427}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31427}, } @misc{zhang2026vision, title = {{Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation}}, author = {Lingsen Zhang and Wei Li and Jie He and Henghua Zhang and Kai Mo and Shiyong Li and Yanpeng Wang and Rui Shao}, year = {2026}, eprint = {2610.25874}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25874}, } @misc{yang2026coupling, title = {{Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies}}, author = {Jiabing Yang and Yuan Xu and Yixiang Chen and Qisen Ma and Peiyan Li and Kai Wang and Chenhang Cui and Tao Yu and Zichen Wen and Wen Ye and Bowen Fang and Ziheng He and Xiangnan Wu and Yingda Li and Yan Huang and Liang Wang}, year = {2026}, eprint = {2610.32102}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32102}, } @misc{yao2026profiling, title = {{Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy}}, author = {Yifei Yao and Yude Zou and Guanbo Jiao and Xing Gao and Ning Gao and Yukai Wang and Jiantong Chen and Zihou Zhu and Xinyu Li and Ningyu Yan and Shuai Wang and Jianming Ma and Haoyu Guo and Weinan Zhang and Chunhua Shen}, year = {2026}, eprint = {2610.35832}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35832}, } @misc{wang2026robot, title = {{Robot-Aligned 3D Gaussian Splatting for Precise Reaching with Wrist-Camera VLA Policies}}, author = {Zuoxu Wang and Xiao Liang}, year = {2026}, eprint = {2610.35626}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35626}, } @misc{qiu2026agq, title = {{AGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models}}, author = {Xuhong Qiu and Zhuoyu Wu and Qiawei Zheng and Wenhui Ou and Wenqi Fang and Raphaël C. -W. Phan}, year = {2026}, eprint = {2610.33074}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.33074}, } @misc{zhao2026rynnvla, title = {{RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions}}, author = {Haoyu Zhao and Xingyue Zhao and Zhian Su and Bohan Hou and Yinzhou Tang and Fengyi Wang and Kehan Li and Yuming Jiang and Siteng Huang and Xin Li and Zhenyu Zeng and Mingxiu Chen and Deli Zhao and Zhongyu Li}, year = {2026}, eprint = {2610.34356}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34356}, } @misc{zhang2026vista, title = {{VISTA: Active Exploration for Self-Improvement in Embodied Agents}}, author = {Zhang Zhang and Shengjun Zhang and Simin Huang and Min Chen and Chong Xia and Xin Fei and Yueqi Duan}, year = {2026}, eprint = {2610.35051}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35051}, } @misc{liu2026echo, title = {{Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models}}, author = {Yufeng Liu and Bohao Fan and Juntu Zhao and Xinyi Wang and Hang Yu and Wenzhuan Luo and Yingzhi Wang and Qinghai Li and Yingdong Hu and Junliang Guo and Richard Wang and Dequan Wang and Yang Gao and Cheng Ma}, year = {2026}, eprint = {2610.31569}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31569}, } @misc{hausdorfer2026multi, title = {{Multi-View Latent Action Pretraining for Cross-Embodiment Robot Learning from Videos}}, author = {Oliver Hausdörfer and Felix Minzenmay and Mani Majd and Maximilian P. Christof and Shiyuan Zhang and Angela P. Schoellig}, year = {2026}, eprint = {2610.27794}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27794}, } @misc{yu2026vision, title = {{Vision-Language-Action or World-Action? Just Action Models}}, author = {Yonghao Yu and Lang Huang and Runyi Li and Toshihiko Yamasaki}, year = {2026}, eprint = {2610.37219}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.37219}, } @misc{jeon2026pacevla, title = {{PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models}}, author = {Hojin Jeon and Jimin Lee and Taekwan Kim and Nayoung Oh and Taeyoung Kim and Myungkyu Koo and Jinmo Koo and Joonwoo Ahn and Jinwoo Shin}, year = {2026}, eprint = {2610.25961}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25961}, } @misc{team2026omnibrain, title = {{OmniBrain-0: A Unified Agentic Model for Embodied Intelligence}}, author = {Xiaomi Embodied Intelligence Team and Yuechen Luo and Chong He and Fang Li and Shaoqing Xu and Jingkai Wang and Menglun Su and Jiaxin Liu and Shengyin Jiang and Zhiyi Lai and Long Chen and Longlong Wang and Liang Hu and Haochen Liu and Yuncheng Jiang and Hongwei Xie and Jieming Cui and Hanbing Li and Junjie Huang and Zhixiang Duan and Hexin Zhang and Weixiang Liang and Ying Gong and Yuhan Wang and Yong Pan and Pengna Li and Kangyi Wu and Ken Deng and Kun Ma and Fuxi Wen and Zhi-xin Yang and Hangjun Ye}, year = {2026}, eprint = {2610.36013}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, url = {https://arxiv.org/abs/2610.36013}, } @misc{kim2026thinkworld, title = {{ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning}}, author = {Chaehyun Kim and Chi-Pin Huang and Jisoo Kim and Min-Hung Chen and Yu-Chiang Frank Wang and Seungryong Kim and Fu-En Yang}, year = {2026}, eprint = {2610.37666}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37666}, } @misc{quang2026retrieve, title = {{Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution}}, author = {Pham Tri Quang and Bao-Ngoc Dao and Minh Duc Nguyen and Duc-Duy Nguyen and Hung T. Ho and Linh Dang Le and Trong-Bao Ho and Thien-Loc Ha and Tan Q. Nguyen and Tuan Dam and Vu N. Duong and Daniel Sonntag and Ngan Le and Khoa D. Doan and Jan Peters and An Thai Le and Duy M. H. Nguyen and Vien Anh Ngo}, year = {2026}, eprint = {2610.37215}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37215}, } @misc{wang2026pdrvla, title = {{PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations}}, author = {Hanqing Wang and Zhaotian Cai and Ruichuan An and Bohan Zeng and Tao Zhang and Yilin Chen and Xu Jiang and Kaiquan Chen and Chongyang Wu and Haoran Li and Fan Yang and Mingan Lin and Wentao Zhang and Zenan Zhou and Youzheng Wu}, year = {2026}, eprint = {2610.37381}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37381}, } @misc{xu2026focusvla, title = {{FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models}}, author = {Huixin Xu and Ziya Yu and Peng Li}, year = {2026}, eprint = {2610.31423}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31423}, } @misc{xie2026sensorimotor, title = {{Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success}}, author = {Yunfei Xie and Howard H. Qian and Shiyi Lan and Kaiyu Hang and Chen Wei}, year = {2026}, eprint = {2610.31670}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.31670}, } @misc{liu2026plan, title = {{Plan First, Act Later: Streaming Reasoning for Executable Memory in Robot Control}}, author = {Qinghang Liu and Conglin Wang and Zongsheng Li and Boyong He and Han Gao and Pengcheng Wang and Tao Sun and Lige Liu and Chang Liu}, year = {2026}, eprint = {2610.29329}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29329}, } @misc{xu2026quantize, title = {{Quantize by Doing: Task-Guided Mixed-Precision Quantization of Vision-Language-Action Models}}, author = {Jiuyi Xu and Xiao Hu and Meida Chen and Song Wang and Yang Ye and Yangming Shi}, year = {2026}, eprint = {2610.38661}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38661}, } @misc{liu2026huge, title = {{HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience}}, author = {Yang Liu and Jiacheng Liu and Hengtao Li and Yuheng Huang and Zijian Yang and Ji Dai and Maoxin Wang and Yi Gao and Qishen Wang and Baohua Yin and Peiyang Li and Shuanghao Bai and Mingyang Sun and Pengxiang Ding and Jianqin Yin and Lixin Yang and Donglin Wang}, year = {2026}, eprint = {2610.34186}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34186}, } @misc{hammele2026what, title = {{What Actually Matters? A Paired Evaluation of Inference Settings for π0.5 on BEHAVIOR-1K}}, author = {Ruben Hammele and Samira Huber and Mohammad Nazeri and Amirreza Payandeh and Alexandyr T. Card and Aaron Nguyen and Anuj Pokhrel and Daeun Song and Xuesu Xiao and Sören Pirk}, year = {2026}, eprint = {2610.37917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37917}, } @misc{ma2026roboseed, title = {{RoboSeed: Multidimensional Evaluation of Vision-Language-Action and World-Action Models: Capability, Resource Affordability, and Research Evidence}}, author = {Xin Ma and Furong Chen and Xinlong Man and Bo Zhang and Yalong Guo and Haolan Lei and Chaochen Cui and Hongyuan Zhang and Mulin Chen and Yi Wang and Lap-pui Chau and Chuang Yang}, year = {2026}, eprint = {2610.40026}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40026}, } @misc{yu2026wall, title = {{Wall-OSS-0.5 Technical Report}}, author = {Ryan Yu and Pushi Zhang and Starrick Liu and Brae Liu and Miracle Kang and Shalfun Li and Lights Shi and Ellie Ma and Ping Yang and Chris Pan and Jerry Chen and Dongxiu Liu and Rain Sun and Miles Guo and Byron Zhang and Hugo Zhou and Zach Xu and Vincent Chen and Harrison Huang and James Wang and Dance Kuzi and Andy Zhai and Hang Su and Roy Gan and Lucy Liang and Hao Wang and Qian Wang}, year = {2026}, eprint = {2605.30877}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.30877}, } @misc{yang2026eaglevla, title = {{EagleVLA: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference}}, author = {Zebin Yang and Qi Wang and Yunhe Wang and Xiurui Guo and Bo Yu and Shaoshan Liu and Jiafeng Xu and Hao Dong and Meng Li}, year = {2026}, eprint = {2607.12659}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.12659}, } @misc{wang2026never, title = {{Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection}}, author = {Yi Wang and Wendi Chen and Zimo Wen and Han Xue and Xueqi Li and Wenye Yu and Zhijie Chen and Hao Yang and Jun Lv and Chuan Wen and Cewu Lu}, year = {2026}, eprint = {2607.14236}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.14236}, } @misc{zhou2026automating, title = {{Automating the Design of Embodied Agent Architectures}}, author = {Jian Zhou and Sihao Lin and Jin Li and Shuai Fu and Gengze Zhou and Qi Wu}, year = {2026}, eprint = {2606.30111}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.30111}, } @misc{lin2026fibertune, title = {{FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning}}, author = {Haihao Lin and Xiangsheng Huang and Xiao Yang and Weibang Zhou and Yiqi Zhang and Bo Yang and Simin Zeng and Jiawei Yang and Zhengyang Wang and Jiahui Du}, year = {2026}, eprint = {2606.08653}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.08653}, } @misc{jang2026vla, title = {{VLA Policies Do Not Know When Not to Act: Unintended Task Execution and Start Suppression}}, author = {Minsu Jang and Jae-Woo Choi and Youngwoo Yoon and Dohyung Kim}, year = {2026}, eprint = {2610.41609}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41609}, } @misc{gong2026tinyastral, title = {{TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents}}, author = {Kehong Gong and Xiaoxu Zheng and Guanli Hou and Seunghun Lee and Mengqi Guo and Runjia Tan and Zhengyu Wen and Qi Wang and Xiaoyu He and Mingyuan Zhang and Michael Bi Mi}, year = {2026}, eprint = {2610.41216}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41216}, } @misc{zhou2026rea, title = {{REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control}}, author = {Pengfei Zhou and Yixing Ma and Zhengfeiyang Zhang and Haoyuan Chen and Zhenglin Wan and Hexin Wang and Wangbo Zhao and Yang You}, year = {2026}, eprint = {2610.42053}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.42053}, } @misc{xiong2026react, title = {{REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models}}, author = {Houlong Xiong and Zhenqi Qiu and Zechen Wang and Suohang Zhang and Yiyu Ren and Wanting Xu and Hongfei Niu and Chengyang He and Ge Sun and Ran Cheng and Qian Zhu}, year = {2026}, eprint = {2610.12007}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.12007}, } @misc{paresmorlans2026demystifying, title = {{Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them}}, author = {Carlota Parés-Morlans and Nils Kuhn and Y. Isabel Liu and Alberta Longhini and Jeannette Bohg}, year = {2026}, eprint = {2608.01402}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.01402}, } @misc{fan2026captain, title = {{CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents}}, author = {Yijia Fan and Xilin He and Yilei Jiang and Dongming Wu and Jiaxu Wang and Xiangyu Yue}, year = {2026}, eprint = {2610.40799}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40799}, } @misc{wu2026roboarchitect, title = {{RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory}}, author = {Shengguang Wu and Suning Huang and Cherie Ho and Ria Doshi and Hao Zhu and Serena Yeung-Levy}, year = {2026}, eprint = {2610.42141}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.42141}, } @misc{yang2026cross, title = {{Cross-Controller Transfer via In-Context Behavior Adaptation}}, author = {Jonathan Yang and Chelsea Finn and Dorsa Sadigh}, year = {2026}, eprint = {2610.39280}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39280}, } @misc{zhang2026from, title = {{From Reasoning to Action: Consequence-Grounded Alignment for Vision-Language-Action Models}}, author = {Yixue Zhang and Wenke Xia and Kun Wu and Wenbo Yu and Pei Ren and Junnan Nie and Di Hu and Zhengping Che and Chang Liu}, year = {2026}, eprint = {2610.39543}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39543}, } @misc{perezhaiek2026embodied, title = {{Embodied at Sea: Imitation Learning for Multi-Task Underwater Manipulation}}, author = {Greta Perez-Haiek and Luca Macesanu and Kevin Angers and Mohammed Imam and Timothy Gambin and Christopher Clark}, year = {2026}, eprint = {2610.38199}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38199}, } @misc{luo2026being, title = {{Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization}}, author = {Hao Luo and Ye Wang and Wanpeng Zhang and Sipeng Zheng and Ziheng Xi and Chaoyi Xu and Haiweng Xu and Haoqi Yuan and Chi Zhang and Yiqing Wang and Yicheng Feng and Zongqing Lu}, year = {2026}, eprint = {2601.12993}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2601.12993}, } @misc{jiang2026robottt, title = {{RoboTTT: Context Scaling for Robot Policies}}, author = {Yunfan Jiang and Yevgen Chebotar and Ruijie Zheng and Fengyuan Hu and Yunhao Ge and Jimmy Wu and Tianyuan Dai and Scott Reed and Li Fei-Fei and Yuke Zhu and Linxi "Jim" Fan}, year = {2026}, eprint = {2607.15275}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.15275}, } @misc{intelligence2026steerable, title = {{$π_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities}}, author = {Physical Intelligence and Bo Ai and Ali Amin and Raichelle Aniceto and Ashwin Balakrishna and Greg Balke and Kevin Black and George Bokinsky and Shihao Cao and Thomas Charbonnier and Vedant Choudhary and Foster Collins and Ken Conley and Grace Connors and James Darpinian and Karan Dhabalia and Maitrayee Dhaka and Jared DiCarlo and Danny Driess and Michael Equi and Adnan Esmail and Yunhao Fang and Chelsea Finn and Catherine Glossop and Thomas Godden and Ivan Goryachev and Lachlan Groom and Haroun Habeeb and Hunter Hancock and Karol Hausman and Gashon Hussein and Victor Hwang and Brian Ichter and Connor Jacobsen and Szymon Jakubczak and Rowan Jen and Tim Jones and Gregg Kammerer and Ben Katz and Liyiming Ke and Mairbek Khadikov and Chandra Kuchi and Marinda Lamb and Devin LeBlanc and Brendon LeCount and Sergey Levine and Xinyu Li and Adrian Li-Bell and Vladislav Lialin and Zhonglin Liang and others}, year = {2026}, eprint = {2604.15483}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2604.15483}, } @misc{feng2026tempo, title = {{TEMPO: Learning Temporal Context for Dynamic Robot Manipulation}}, author = {Zhenyang Feng and Jimin Heo and Erik B. Sudderth and Unnat Jain}, year = {2026}, eprint = {2609.16864}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.16864}, } @misc{torne2026mem, title = {{MEM: Multi-Scale Embodied Memory for Vision Language Action Models}}, author = {Marcel Torne and Karl Pertsch and Homer Walke and Kyle Vedder and Suraj Nair and Brian Ichter and Allen Z. Ren and Haohuan Wang and Jiaming Tang and Kyle Stachowicz and Karan Dhabalia and Michael Equi and Quan Vuong and Jost Tobias Springenberg and Sergey Levine and Chelsea Finn and Danny Driess}, year = {2026}, eprint = {2603.03596}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.03596}, } @misc{jeong2026learning, title = {{Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering}}, author = {Hyun Joe Jeong and Gokul Swamy and Andrea Bajcsy}, year = {2026}, eprint = {2606.12299}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12299}, } @misc{wang2026embodisteer, title = {{EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment}}, author = {Shihefeng Wang and Kangchen Lv and Mingrui Yu and Xiang Li}, year = {2026}, eprint = {2606.12965}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12965}, } @misc{fang2026when, title = {{When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs}}, author = {Yu Fang and Yuchun Feng and Dong Jing and Jiaqi Liu and Yue Yang and Zhenyu Wei and Daniel Szafir and Mingyu Ding}, year = {2026}, eprint = {2602.17659}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2602.17659}, } @misc{yan2026zeta, title = {{ZETA: A Controlled Study of Zero-Shot Cross-Embodiment VLA Transfer for Tabletop Manipulation}}, author = {Mi Yan and Wenhao Zhang and Zhiqi Zhang and Yu Peng and Tangxinyu Wang and Lingfei Zhai and Jiayi Su and Shengliang Deng and Lin Peng and Yaowei Liu and Yuxing Chen and Zhiyuan Wei and Jilong Wang and Jiayi Chen and Jiangran Lyu and Zhizheng Zhang and He Wang}, year = {2026}, eprint = {2609.02546}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.02546}, } @misc{wang2025bitvla, title = {{BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation}}, author = {Hongyu Wang and Chuyan Xiong and Ruiping Wang and Xilin Chen}, year = {2025}, eprint = {2506.07530}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.07530}, } @misc{wang2026diagnosing, title = {{Diagnosing Compositional Generalization in Sequential Robot Tasks}}, author = {Yixiao Wang and Cheng-En Wu and Lingfeng Sun and Pengcheng Wang and Xiang Ji and Boyuan Liang and Guojian Zhan and Masayoshi Tomizuka}, year = {2026}, eprint = {2607.29687}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.29687}, } @misc{chen2026gap, title = {{GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks}}, author = {Kaiyuan Chen and Shuangyu Xie and Letian Fu and Justin Yu and William Pacini and Sandeep Bajamahal and Hudson Kim and Jaimyn Drake and Daehwa Kim and Haoru Xue and Jonathan Francis and Christian Juette and Peter Schaldenbrand and Muhammet Yunus Seker and Ruwan Wickramarachchi and Uksang Yoo and Guanzhi Wang and Adithyavairavan Murali and Balakumar Sundaralingam and S. Shankar Sastry and Yuke Zhu and Linxi "Jim" Fan and Spencer Huang and Ken Goldberg}, year = {2026}, eprint = {2607.05369}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.05369}, } @misc{zhang2026playful, title = {{Playful Agentic Robot Learning}}, author = {Junyi Zhang and Jiaxin Ge and Hanjun Yoo and Letian Fu and Zihan Yang and Yaowei Liu and Raj Saravanan and Shaofeng Yin and Justin Yu and Dantong Niu and Zirui Wang and Roei Herzig and Ken Goldberg and Yutong Bai and David M. Chan and Ion Stoica and Angjoo Kanazawa and Jiahui Lei and Haiwen Feng and Trevor Darrell}, year = {2026}, eprint = {2606.19419}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.19419}, } @misc{zhu2026resmerge, title = {{ResMerge: Residual Policy Learning and Merging for Continual Adaptation of Pre-trained Robot Policies}}, author = {Kefei Zhu and Lingyun Xu and Yue Xin and Xiaoqi Li and Caixin Guo and Xincheng Du and Yuanpei Chen and Yaodong Yang and Hao Dong}, year = {2026}, eprint = {2610.41663}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41663}, } @misc{zhao2026star, title = {{STAR: Steering Action Representations with Proprioception for VLA Inference}}, author = {Guangyu Zhao and Yongchang Zhang and Haoxuan Ru and Kaichen He and Haoran Wen and Kun Zhan and Zeyu Zhang and Yin Li and Yiwu Zhong}, year = {2026}, eprint = {2610.41009}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41009}, } @misc{ding2026hifor, title = {{HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model}}, author = {Rongxing Ding and Hongyu Qu and Kehong Wu and Xudong Wang and Fan Zhang and Xinguang Xiang and Xiangbo Shu}, year = {2026}, eprint = {2610.40373}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.40373}, } @misc{yu2026robodoctor, title = {{RoboDoctor: Training-Free Recursive Self-Improvement for Robot Policies}}, author = {Heyang Yu and Haomin Li and Sihang Li and Jixin Yan and Shiyun Peng and Wanqi Zhong and Tianyu Xin and Yuan Yao and Xiaoyu Tian and Yiming Li}, year = {2026}, eprint = {2610.35604}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35604}, } @misc{nguyen2026robocolosseum, title = {{RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild}}, author = {Tan Sang Nguyen and Yi Ru Wang and Shailesh Shailesh and Gang Yang and Jiamo Hu and Jianuo Jiang and Haoquan Fang and Zhongzheng Ren and Zhongyi Luo and Ian Chong and Aaron Tung and Santiago Pravisani and Minghui Lin and Yao Mo and Ishneet Singh and Benjamin Tee and Harold Soh and Siddhartha Srinivasa and Dieter Fox and David Hsu and Haoming Song and Maxime Ellerbach and Thomas Wolf and Pepijn Kooijmans and Ruijie He and Michael Cho and Jiafei Duan}, year = {2026}, eprint = {2611.02497}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02497}, } @misc{yuan2026democratizing, title = {{Democratizing Robot-Use Agents: A Unified Harness with Open Models}}, author = {Jiarui Yuan and Yuxin Zuo and Xiaoyu Huang and Wenbo Zhang and Kwanyoung Park and Junlin Yang and Tianxiang Zhang and Ruoqu Chen and Yutao Ouyang and Bingxiang He and Xingtai Lv and Hongjin Wu and Jiajun Liu and Jiahao Zhao and Tianwei Luo and Haozhan Li and Cheng Qian and Jiaxin Ge and Huan-ang Gao and Kaisen Yang and Jiaqi Deng and Qixin Xu and Siqiao Huang and Bowen Zhou and Mengdi Xu and Zhiyuan Liu and Pieter Abbeel and Ning Ding}, year = {2026}, eprint = {2611.01560}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01560}, } @misc{wang2026auriga, title = {{Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation}}, author = {Chengcheng Wang and Yuheng Shi and Siyu Xu and Yutong Wang and Jinjing Zhao and Chenghao Xia and Jinqi Liao and Jiankun Peng and Ligong Bi and Yuechuan Ma and Jiaqi Liu and Wenbo Wang and Zijian Wang and Yuemin Wu and Minjing Dong and Xiu Su and Tao Huang and Jianyuan Guo and Chengbin Du and Yunke Wang and Chang Xu}, year = {2026}, eprint = {2611.01112}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01112}, } @misc{wen2026vlalagbench, title = {{VLALagBench: Understanding When and Why VLA Inference Latency Matters}}, author = {Qi Wen and Borui Xu and Hussein Amro and Hongshi Tan and Hanmin Lin and Chaoyi Ruan and Shanghao Liu and Gang Yang and Yuejiang Liu and Jiafei Duan and Bingsheng He and Jason Clemons and Christos Kozyrakis and Wenqi Jiang}, year = {2026}, eprint = {2611.03103}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03103}, } @misc{kim2026helm, title = {{HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation}}, author = {Gyeonghun Kim and Donghoon Kim and Minsoo Choi and Suyun Lee}, year = {2026}, eprint = {2611.02660}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02660}, } @misc{wu2026pragmatic, title = {{A Pragmatic VLA Foundation Model}}, author = {Wei Wu and Fan Lu and Yunnan Wang and Shuai Yang and Shi Liu and Fangjing Wang and Qian Zhu and He Sun and Yong Wang and Shuailei Ma and Yiyu Ren and Kejia Zhang and Hui Yu and Jingmei Zhao and Shuai Zhou and Zhenqi Qiu and Houlong Xiong and Ziyu Wang and Zechen Wang and Ran Cheng and Yong-Lu Li and Yongtao Huang and Xing Zhu and Yujun Shen and Kecheng Zheng}, year = {2026}, eprint = {2601.18692}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2601.18692}, } @misc{team2025gemini, title = {{Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer}}, author = {Gemini Robotics Team and Abbas Abdolmaleki and Saminda Abeyruwan and Joshua Ainslie and Jean-Baptiste Alayrac and Montserrat Gonzalez Arenas and Ashwin Balakrishna and Nathan Batchelor and Alex Bewley and Jeff Bingham and Michael Bloesch and Konstantinos Bousmalis and Philemon Brakel and Anthony Brohan and Thomas Buschmann and Arunkumar Byravan and Serkan Cabi and Ken Caluwaerts and Federico Casarini and Christine Chan and Oscar Chang and London Chappellet-Volpini and Jose Enrique Chen and Xi Chen and Hao-Tien Lewis Chiang and Krzysztof Choromanski and Adrian Collister and David B. D'Ambrosio and Sudeep Dasari and Todor Davchev and Meet Kirankumar Dave and Coline Devin and Norman Di Palo and Tianli Ding and Carl Doersch and Adil Dostmohamed and Yilun Du and Debidatta Dwibedi and Sathish Thoppay Egambaram and Michael Elabd and Tom Erez and Xiaolin Fang and Claudio Fantacci and Cody Fong and Erik Frey and Chuyuan Fu and Ruiqi Gao and Marissa Giustina and Keerthana Gopalakrishnan and Laura Graesser and others}, year = {2025}, eprint = {2510.03342}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.03342}, } @misc{sun2026vla, title = {{VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model}}, author = {Jingwen Sun and Wenyao Zhang and Zekun Qi and Shaojie Ren and Zezhi Liu and Hanxin Zhu and Guangzhong Sun and Xin Jin and Zhibo Chen}, year = {2026}, eprint = {2602.10098}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.10098}, } @misc{lu2026faster, title = {{FASTER: Rethinking Real-Time Flow VLAs}}, author = {Yuxiang Lu and Zhe Liu and Xianzhe Fan and Zhenya Yang and Jinghua Hou and Junyi Li and Kaixin Ding and Hengshuang Zhao}, year = {2026}, eprint = {2603.19199}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.19199}, } @misc{yue2024deer, title = {{DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution}}, author = {Yang Yue and Yulin Wang and Bingyi Kang and Yizeng Han and Shenzhi Wang and Shiji Song and Jiashi Feng and Gao Huang}, year = {2024}, eprint = {2411.02359}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2411.02359}, } @misc{zawalski2024robotic, title = {{Robotic Control via Embodied Chain-of-Thought Reasoning}}, author = {Michał Zawalski and William Chen and Karl Pertsch and Oier Mees and Chelsea Finn and Sergey Levine}, year = {2024}, eprint = {2407.08693}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.08693}, } @misc{zhong2025survey, title = {{A Survey on Vision-Language-Action Models: An Action Tokenization Perspective}}, author = {Yifan Zhong and Fengshuo Bai and Shaofei Cai and Xuchuan Huang and Zhang Chen and Xiaowei Zhang and Yuanfei Wang and Shaoyang Guo and Tianrui Guan and Ka Nam Lui and Zhiquan Qi and Yitao Liang and Yuanpei Chen and Yaodong Yang}, year = {2025}, eprint = {2507.01925}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.01925}, } @misc{zhang2025pure, title = {{Pure Vision Language Action (VLA) Models: A Comprehensive Survey}}, author = {Dapeng Zhang and Jing Sun and Chenghui Hu and Xiaoyan Wu and Zhenlong Yuan and Rui Zhou and Fei Shen and Qingguo Zhou}, year = {2025}, eprint = {2509.19012}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.19012}, } @misc{dey2026asynchronous, title = {{Asynchronous Robot Policies}}, author = {Sombit Dey and Luc Van Gool and Danda Pani Paudel}, year = {2026}, eprint = {2611.05155}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05155}, } @misc{feng2026say, title = {{Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs}}, author = {Zihao Feng and Qingzhao Zhang and Chunyu Xia and Bo Yu and Z. Morley Mao and Ramesh Govindan}, year = {2026}, eprint = {2611.04166}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2611.04166}, } @misc{budzianowski2025edgevla, title = {{EdgeVLA: Efficient Vision-Language-Action Models}}, author = {Paweł Budzianowski and Wesley Maa and Matthew Freed and Jingxiang Mo and Winston Hsiao and Aaron Xie and Tomasz Młoduchowski and Viraj Tipnis and Benjamin Bolte}, year = {2025}, eprint = {2507.14049}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.14049}, } @misc{liu2024robomamba, title = {{RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation}}, author = {Jiaming Liu and Mengzhen Liu and Zhenyu Wang and Pengju An and Xiaoqi Li and Kaichen Zhou and Senqiao Yang and Renrui Zhang and Yandong Guo and Shanghang Zhang}, year = {2024}, eprint = {2406.04339}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2406.04339}, } @misc{li2025pointvla, title = {{PointVLA: Injecting the 3D World into Vision-Language-Action Models}}, author = {Chengmeng Li and Junjie Wen and Yan Peng and Yaxin Peng and Feifei Feng and Yichen Zhu}, year = {2025}, eprint = {2503.07511}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.07511}, } @misc{sun2024emma, title = {{Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning}}, author = {Qi Sun and Pengfei Hong and Tej Deep Pala and Vernon Toh and U-Xuan Tan and Deepanway Ghosal and Soujanya Poria}, year = {2024}, eprint = {2412.11974}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.11974}, } @misc{yu2025survey, title = {{A Survey on Efficient Vision-Language-Action Models}}, author = {Zhaoshu Yu and Bo Wang and Pengpeng Zeng and Haonan Zhang and Ji Zhang and Zheng Wang and Lianli Gao and Jingkuan Song and Nicu Sebe and Heng Tao Shen}, year = {2025}, eprint = {2510.24795}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2510.24795}, } @misc{ji2025robobrain, title = {{RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete}}, author = {Yuheng Ji and Huajie Tan and Jiayu Shi and Xiaoshuai Hao and Yuan Zhang and Hengyuan Zhang and Pengwei Wang and Mengdi Zhao and Yao Mu and Pengju An and Xinda Xue and Qinghang Su and Huaihai Lyu and Xiaolong Zheng and Jiaming Liu and Zhongyuan Wang and Shanghang Zhang}, year = {2025}, eprint = {2502.21257}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.21257}, } @misc{qiu2026efficient, title = {{Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement}}, author = {Weikang Qiu and Huashuo Lei and Tinglin Huang and Rex Ying}, year = {2026}, eprint = {2602.03983}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.03983}, } @misc{park2026human, title = {{Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs}}, author = {Junhyeong Park and Wook Jung and Taeyoung Kim and Huiwon Jang and Jinwoo Shin}, year = {2026}, eprint = {2611.04391}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2611.04391}, } @misc{liu2026do, title = {{Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action}}, author = {Yihang Liu and Yiming Chen and Mingzhe Zheng}, year = {2026}, eprint = {2611.05058}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05058}, } @misc{xu2026semantic, title = {{Semantic Anchoring for Robotic Action Representations}}, author = {Yuan Xu and Youheng Shi and Chengyang Li and Wentao Zhu and Yizhou Wang}, year = {2026}, eprint = {2607.13597}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.13597}, } @misc{zhang2026prts, title = {{PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations}}, author = {Yang Zhang and Jiangyuan Zhao and Chenyou Fan and Fangzheng Yan and Tian Li and Haitong Tang and Sen Fu and Xuan'er Wu and Qizhen Weng and Weinan Zhang and Xiu Li and Chi Zhang and Chenjia Bai and Xuelong Li}, year = {2026}, eprint = {2604.27472}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2604.27472}, } @misc{yidouweng2026meta, title = {{Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints}}, author = {Gwen Yidou-Weng and Edward Sun and Tianyi Ma and Metin Alp Dogan and Benjie Wang and Allen Peng and Guy Van den Broeck and Yuchen Cui}, year = {2026}, eprint = {2608.22149}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.22149}, } @misc{li2026bayesian, title = {{Bayesian Active Learning for Intent Disambiguation in Interactive Robot Planning}}, author = {Huao Li and Carson Sobolewski and Augustinos Saravanos and William Tan and John Karigiannis and Chuchu Fan}, year = {2026}, eprint = {2609.34270}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.34270}, } @misc{yuan2025being, title = {{Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills}}, author = {Haoqi Yuan and Yu Bai and Yuhui Fu and Bohan Zhou and Yicheng Feng and Xinrun Xu and Yi Zhan and Börje F. Karlsson and Zongqing Lu}, year = {2025}, eprint = {2503.12533}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.12533}, } @misc{xue2025leverb, title = {{LeVERB: Humanoid Whole-Body Control with Latent Vision-Language Instruction}}, author = {Haoru Xue and Xiaoyu Huang and Dantong Niu and Qiayuan Liao and Thomas Kragerud and Jan Tommy Gravdahl and Xue Bin Peng and Guanya Shi and Trevor Darrell and Koushil Sreenath and Shankar Sastry}, year = {2025}, eprint = {2506.13751}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.13751}, } @misc{wei2026open, title = {{$Ψ_0$: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation}}, author = {Songlin Wei and Hongyi Jing and Boqian Li and Zhenyu Zhao and Jiageng Mao and Zhenhao Ni and Sicheng He and Jie Liu and Xiawei Liu and Kaidi Kang and Sheng Zang and Weiduo Yuan and Marco Pavone and Di Huang and Yue Wang}, year = {2026}, eprint = {2603.12263}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.12263}, } @misc{yang2025egovla, title = {{EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos}}, author = {Ruihan Yang and Qinxi Yu and Yecheng Wu and Rui Yan and Borui Li and An-Chieh Cheng and Xueyan Zou and Yunhao Fang and Xuxin Cheng and Ri-Zhao Qiu and Hongxu Yin and Sifei Liu and Song Han and Yao Lu and Xiaolong Wang}, year = {2025}, eprint = {2507.12440}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.12440}, } @misc{zhang2026finecraft, title = {{FineCraft: Enhancing VLA Models for Fine-Grained Manipulation}}, author = {Shuaike Zhang and Ziheng Quan and Junhao Ran and Muhe Ding and Shaokun Wang and Jianlong Wu}, year = {2026}, eprint = {2611.03163}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03163}, } @misc{fan2026from, title = {{From Pixels to Actions - Towards Native Vision-Language-Action Policies}}, author = {Weichen Fan and Haiwen Diao and Penghao Wu and Siyuan Hu and Ziqi Huang and Tianqi Liu and Mingze Sun and Ziyi Wang and Zhongang Cai and Hanming Deng and Quan Wang and Lei Yang and Lewei Lu and Fangzhou Hong and Zhaoxi Chen and Dahua Lin and Ziwei Liu}, year = {2026}, eprint = {2611.06918}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2611.06918}, } @misc{ma2026open, title = {{Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models}}, author = {Juncheng Ma and Jiaxin Li and Jiankai Tu and Bo Liang and Guodong Lv and Yufan Deng and Junzhe Tang and Liangzhu Yang and Chen Bian and Zicong Cao and Baohao Zhu and Jianxin Bi and Tengfei Yan and Yinyuan Zhang and Kewei Zhang and Xinglong Chen and Kaiqi Chen and Duomin Wang and Xiaotian Tang and Liang Tan and Li Li and Yuan Xu and Haosen Yang and Yuqi Wang and Jingfei Xia and Songyan Huang and Zhiyang Dou and Zhen Dong and Enze Xie and Tat-Seng Chua and Daquan Zhou}, year = {2026}, eprint = {2611.06817}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2611.06817}, } @misc{li2024what, title = {{What Matters in Building Vision-Language-Action Models for Generalist Robots}}, author = {Xinghang Li and Peiyan Li and Long Qian and Minghuan Liu and Dong Wang and Jirong Liu and Bingyi Kang and Xiao Ma and Xinlong Wang and Di Guo and Tao Kong and Hanbo Zhang and Huaping Liu}, year = {2024}, eprint = {2412.14058}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.14058}, } @misc{liu2026rdt, title = {{RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization}}, author = {Songming Liu and Bangguo Li and Kai Ma and Lingxuan Wu and Hengkai Tan and Xiao Ouyang and Hang Su and Jun Zhu}, year = {2026}, eprint = {2602.03310}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.03310}, } @misc{yang2026abot, title = {{ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning}}, author = {Yandan Yang and Shuang Zeng and Tong Lin and Xinyuan Chang and Dekang Qi and Junjin Xiao and Haoyun Liu and Ronghan Chen and Yuzhi Chen and Dongjie Huo and Feng Xiong and Xing Wei and Zhiheng Ma and Mu Xu}, year = {2026}, eprint = {2602.11236}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2602.11236}, } @misc{wang2026qwen, title = {{Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments}}, author = {Qiuyue Wang and Mingsheng Li and Jian Guan and Jinhui Ye and Sicheng Xie and Yitao Liu and Junhao Chen and Zhixuan Liang and Jie Zhang and Xintong Hu and Xuhong Huang and Pei Lin and Junyang Lin and Dayiheng Liu and Shuai Bai and Jingren Zhou and Jiazhao Zhang and Haoqi Yuan and Gengze Zhou and Hang Yin and Ye Wang and Yiyang Huang and Zixing Lei and Wujian Peng and Delin Chen and Yingming Zheng and Jingyang Fan and Xianwei Zhuang and Xin Zhou and Haoyang Li and Anzhe Chen and Tong Zhang and Xuejing Liu and Yuchong Sun and Ruizhe Chen and Zhaohai Li and Chenxu Lü and Zhibo Yang and Tao Yu and Xionghui Chen}, year = {2026}, eprint = {2605.30280}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.30280}, } @misc{li2025scalable, title = {{Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos}}, author = {Qixiu Li and Yu Deng and Yaobo Liang and Lin Luo and Lei Zhou and Chengtang Yao and Lingqi Zeng and Zhiyuan Feng and Huizhi Liang and Sicheng Xu and Yizhong Zhang and Xi Chen and Hao Chen and Lily Sun and Dong Chen and Jiaolong Yang and Baining Guo}, year = {2025}, eprint = {2510.21571}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.21571}, } @misc{liu2025what, title = {{What Can RL Bring to VLA Generalization? An Empirical Study}}, author = {Jijia Liu and Feng Gao and Bingwen Wei and Xinlei Chen and Qingmin Liao and Yi Wu and Chao Yu and Yu Wang}, year = {2025}, eprint = {2505.19789}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2505.19789}, } @misc{liu2024robouniview, title = {{RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation}}, author = {Fanfan Liu and Feng Yan and Liming Zheng and Chengjian Feng and Yiyang Huang and Lin Ma}, year = {2024}, eprint = {2406.18977}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.18977}, } @misc{xiao2023robot, title = {{Robot Learning in the Era of Foundation Models: A Survey}}, author = {Xuan Xiao and Jiahang Liu and Zhipeng Wang and Yanmin Zhou and Yong Qi and Qian Cheng and Bin He and Shuo Jiang}, year = {2023}, eprint = {2311.14379}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2311.14379}, } @misc{hu2023toward, title = {{Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis}}, author = {Yafei Hu and Quanting Xie and Vidhi Jain and Jonathan Francis and Jay Patrikar and Nikhil Keetha and Seungchan Kim and Yaqi Xie and Tianyi Zhang and Hao-Shu Fang and Shibo Zhao and Shayegan Omidshafiei and Dong-Ki Kim and Ali-akbar Agha-mohammadi and Katia Sycara and Matthew Johnson-Roberson and Dhruv Batra and Xiaolong Wang and Sebastian Scherer and Chen Wang and Zsolt Kira and Fei Xia and Yonatan Bisk}, year = {2023}, eprint = {2312.08782}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.08782}, } @misc{chen2026can, title = {{Can Astra Solve RoboMME without Breaking the Bank?}}, author = {Bingao Chen and Haoquan Fang and C. Karen Liu}, year = {2026}, eprint = {2611.06184}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.06184}, } @misc{wang2026pyrua, title = {{PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World}}, author = {Qiang Wang and Jianxin Bi and Shulong Jiang and Ruiyang Si and Wenbo Huang and Kaiqi Chen and Jiaxin Li and Liyun Li and Xuanyi Li and Daquan Zhou}, year = {2026}, eprint = {2611.06768}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.06768}, } @misc{yang2026world, title = {{World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis}}, author = {Yi Yang and Zhihong Liu and Siqi Kou and Yiyang Chen and Yanzhe Hu and Jianbo Zhou and Boyuan Zhao and Zhijie Wei and Xiao Xia and Xueqi Li and Pengfei Liu and Zhijie Deng}, year = {2026}, eprint = {2606.05979}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.05979}, } @misc{yang2026eventvla, title = {{EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies}}, author = {Ganlin Yang and Zhangzheng Tu and Yuqiang Yang and Sitong Mao and Junyi Dong and Tianxing Chen and Jiaqi Peng and Jing Xiong and Jiafei Cao and Jifeng Dai and Wengang Zhou and Yao Mu and Tai Wang}, year = {2026}, eprint = {2606.20092}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.20092}, } @misc{jeong2026huro, title = {{HuRo: Robotizing Human Videos for Scalable VLA Pretraining}}, author = {Jinho Jeong and Se June Joo and Jaehyun Kang and Dongyun Kim and Yena Kim and Hanjung Kim and Seon Joo Kim}, year = {2026}, eprint = {2609.10706}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.10706}, } @misc{li2026ace, title = {{ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining}}, author = {Hao Li and Ganlong Zhao and Yufei Liu and Haotian Hou and Guoquan Ye and Tongyan Fang and Chunxiao Liu and Siyuan Huang and Jianbo Liu and Xiaogang Wang and Hongsheng Li}, year = {2026}, eprint = {2606.17200}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.17200}, } @misc{xu2026apt, title = {{APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies}}, author = {Kechun Xu and Zhenjie Zhu and Anzhe Chen and Rong Xiong and Yue Wang}, year = {2026}, eprint = {2606.12366}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12366}, } @misc{ho2026start, title = {{Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection}}, author = {Trong-Bao Ho and Quang-Tan Nguyen and Thien-Loc Ha and Gia-Binh Nguyen and Viet-Thanh Nguyen and Long Dinh and Minh N. Vu and Duy M. H. Nguyen and An Thai Le and Ngo Anh Vien}, year = {2026}, eprint = {2606.19774}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.19774}, } @misc{jeong2026polar, title = {{PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning}}, author = {Youngjoon Jeong and Jihwan Yu and Minsoo Jo and Junha Chun and Taesup Kim}, year = {2026}, eprint = {2606.21139}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.21139}, } @misc{li2026sla, title = {{SLA: Scaling Spatial-Language-Action Model via Continual Pre-training}}, author = {Fuhao Li and Wenxuan Song and Qizhou Huang and Ziyang Zhou and Jingbo Wang and Junwu E and Pengwei Wang and Yan Wang and Shunbo Zhou and Haoang Li}, year = {2026}, eprint = {2611.08373}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08373}, } @misc{wang2026concertina, title = {{Concertina: Embodying Manipulation and Cognition in One Diffusion Vision-Language Model}}, author = {Chengcheng Wang and Wei He and Wenhao Li and Hongguang Li and Kai Han and Jianyuan Guo and Chang Xu}, year = {2026}, eprint = {2611.07513}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2611.07513}, } @misc{podolinsky2026failure, title = {{Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing}}, author = {Michal P. Podolinsky and Yunhao Yang and Daniel Little and Hong Lu and Rohan Siva and Olin Goudey and Neel P. Bhatt and Matthias Scheutz and Ufuk Topcu}, year = {2026}, eprint = {2611.08425}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08425}, } @misc{li2026graph, title = {{Graph-Reweighted Behavior Cloning with Human Interventions for Precise Robotic Manipulation}}, author = {Xiaoman Li and Zhiqiang Yang and Jiayu Hu and Jipeng Kong and Yang Zhang and Jingwei Zhang and Fangzheng Yan and Chunhua Shen and Chenjia Bai}, year = {2026}, eprint = {2610.20504}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.20504}, } @misc{kim2026disentangling, title = {{Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead}}, author = {Junghyun Kim and Ngseo Kim and ChungWoo Lee and Seoyeon Lee and Woo-Jeong Baek and Adam Zhou and Chip Huyen and Jun-Ki Lee and Gi-Cheon Kang and Byoung-Tak Zhang}, year = {2026}, eprint = {2609.37165}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.37165}, } @misc{ji2026catch, title = {{Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs}}, author = {Yiheng Ji and Xingru Zhou and Luis Sentis and Mingyo Seo}, year = {2026}, eprint = {2609.21022}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.21022}, } @misc{xiong2026geomvla, title = {{GeomVLA: Unifying Scene, Motion, and Action in 3D}}, author = {Ziyin Xiong and Nikolaos Gkanatsios and Moritz Reuss and Katerina Fragkiadaki}, year = {2026}, eprint = {2609.13812}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.13812}, } @misc{liu2026long, title = {{Long-Horizon Manipulation via Trace-Conditioned VLA Planning}}, author = {Isabella Liu and An-Chieh Cheng and Rui Yan and Geng Chen and Ri-Zhao Qiu and Xueyan Zou and Sha Yi and Hongxu Yin and Xiaolong Wang and Sifei Liu}, year = {2026}, eprint = {2604.21924}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.21924}, } @misc{sun2026artificial, title = {{Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models}}, author = {Xiatao Sun and Yuan Zhuang and Mateo Sanchez Lopez Negrete and Matei-Victor Coldea and Chen Liang and Haoyang Zhang and Che Liu and Ziyao Zeng and Shawn Li and Qian Wang and Fei Miao and Daniel Rakita}, year = {2026}, eprint = {2607.10655}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.10655}, } @misc{xu2026learning, title = {{Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration}}, author = {Leo Xu and Letian Li and Alex Cuellar and Michael Hagenow}, year = {2026}, eprint = {2606.12475}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12475}, } @misc{kang2026x, title = {{X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining}}, author = {Miracle Kang and Lights Shi and Lucy Liang and Roy Gan and Dongxiu Liu and Pushi Zhang and Sylas Chen and Shawn Qin and Yinan Zheng and Jinliang Zheng and Hao Wang and Xianyuan Zhan and Hang Su}, year = {2026}, eprint = {2606.14752}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.14752}, } @misc{wu2026see, title = {{See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs}}, author = {Yueh-Hua Wu and Tatsuya Matsushima and Kei Ota}, year = {2026}, eprint = {2606.02735}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.02735}, } @misc{zhu2026harp, title = {{HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model}}, author = {Xiang Zhu and Puzhen Yuan and Yichen Liu and Jianyu Chen}, year = {2026}, eprint = {2605.31234}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.31234}, } @misc{doshi2026chorus, title = {{CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy}}, author = {Ria Doshi and Tian Gao and Annie Chen and Chelsea Finn and Jeannette Bohg}, year = {2026}, eprint = {2606.12352}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12352}, } @misc{lee2026tbd, title = {{TBD-VLA: Temporal Block Diffusion Vision Language Action Model}}, author = {Sung-Wook Lee and Xuhui Kang and Yen-Ling Kuo}, year = {2026}, eprint = {2606.07895}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.07895}, } @misc{song2026omniguide, title = {{OmniGuide: Universal Spatial Guidance Fields for Enhancing Generalist Robot Policies}}, author = {Yunzhou Song and Long Le and Yong-Hyun Park and Jie Wang and Junyao Shi and Lingjie Liu and Jiatao Gu and Eric Eaton and Dinesh Jayaraman and Kostas Daniilidis}, year = {2026}, eprint = {2603.10052}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.10052}, } @misc{chen2026volo, title = {{VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation}}, author = {Siyi Chen and Hugo Hadfield and Alex Zook and Mikaela Angelina Uy and Chan Hee Song and Erwin Coumans and Xuning Yang and Faisal Ladhak and Qing Qu and Stan Birchfield and Jonathan Tremblay and Valts Blukis}, year = {2026}, eprint = {2606.07723}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.07723}, } @misc{kao2026flow, title = {{Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs}}, author = {Jonathan C. Kao and Jason Chan and Andy Wang}, year = {2026}, eprint = {2606.10180}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.10180}, } @misc{ishitoya2026clap, title = {{CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding}}, author = {Yuri Ishitoya and Jeremy Siburian and Masashi Hamaya and Haruto Suzuki and Kuniaki Saito and Toshihiko Fukushima and Cristian C. Beltran-Hernandez and Mai Nishimura}, year = {2026}, eprint = {2607.08974}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.08974}, } @misc{chan2026steering, title = {{Steering Autoregressive Vision-Language-Action Policies via Action Token Intervention}}, author = {Jason Chan and Jonathan C. Kao}, year = {2026}, eprint = {2606.15021}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15021}, } @misc{lyu2026sentryvla, title = {{SentryVLA: Uncertainty-Guided Action Selection and State Monitoring for Vision-Language-Action Robotic Control}}, author = {Zongyao Lyu and Lingling Chen and William J. Beksi}, year = {2026}, eprint = {2604.16677}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.16677}, } @misc{vanjani2026dam, title = {{DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model}}, author = {Pankhuri Vanjani and Zhuoyue Li and Jakub Suliga and Moritz Reuss and Gianluca Geraci and Xinkai Jiang and Rudolf Lioutikov}, year = {2026}, eprint = {2606.12105}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12105}, } @misc{bansal2026action, title = {{Action Chunk Scheduling for Batched Robot Policy Serving}}, author = {Rohan Bansal and David He and Nadun Ranawaka Arachchige and Zhenyang Chen and Soobum Kim and Kexin Rong and Danfei Xu}, year = {2026}, eprint = {2608.00337}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.00337}, } @misc{swann2026sparse, title = {{Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models}}, author = {Aiden Swann and Lachlain McGranahan and Hugo Buurmeijer and Monroe Kennedy and Mac Schwager}, year = {2026}, eprint = {2603.19183}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.19183}, } @misc{puthumanaillam2026trajectory, title = {{Trajectory-Level Redirection Attacks on Vision-Language-Action Models}}, author = {Gokul Puthumanaillam and Vardhan Dongre and Pranay Thangeda and Hooshang Nayyeri and Dilek Hakkani-Tür and Melkior Ornik}, year = {2026}, eprint = {2606.12978}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12978}, } @misc{kondoh2026counteralign, title = {{CounterAlign: Counterfactual Supervision for Vision-Language-Action Models}}, author = {Haru Kondoh and Kei Ota and Asako Kanezaki and Yueh-Hua Wu}, year = {2026}, eprint = {2608.21740}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.21740}, } @misc{chen2026geoalign, title = {{GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models}}, author = {Yizhi Chen and Zhanxiang Cao and Xinyi Peng and Yixiao Zheng and Xiaxi Si and Yiheng Li and Liyun Yan and Keqi Zhu and Xueyun Chen and Shengcheng Fu and Tianyue Zhan and Yufei Jia and Jinming Yao and Yan Xie and Kun Wang and Cewu Lu and Yue Gao}, year = {2026}, eprint = {2606.03240}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.03240}, } @misc{seligmann2026vla, title = {{VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models}}, author = {Florian Seligmann and Emiliyan Gospodinov and Enes Ulas Dincer and Gerhard Neumann}, year = {2026}, eprint = {2606.21386}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2606.21386}, } @misc{kim2026pri, title = {{Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation}}, author = {Jisoo Kim and Jungbin Cho and Sanghyeok Chu and Ananya Bal and Jinhyung Kim and Gunhee Lee and Sihaeng Lee and Seung Hwan Kim and Bohyung Han and Hyunmin Lee and Laszlo A. Jeni and Seungryong Kim}, year = {2026}, eprint = {2603.01549}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2603.01549}, } @misc{tucker2026but, title = {{$π$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation}}, author = {Johnathan Tucker and Denis Liu and Aiden Swann and Allen Ren and Javier Yu and Jiankai Sun and Brandon Kim and Lachlain McGranahan and Quan Vuong and Mac Schwager}, year = {2026}, eprint = {2603.25038}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.25038}, } @misc{wang2026cue, title = {{Cue the Flow: Steering Flow-Matching Policies for Open-World Delivery Manipulation}}, author = {Haoxuan Wang and Griffin Galimi and Junhua Huang and Selina Song and Wayne Wu and Yan Yan and Bolei Zhou}, year = {2026}, eprint = {2609.38989}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.38989}, } @misc{kim2026object, title = {{Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement}}, author = {Kinam Kim and Namiko Saito and Heecheol Kim and Katsushi Ikeuchi and Jaegul Choo and Yasuyuki Matsushita}, year = {2026}, eprint = {2606.18953}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.18953}, } @misc{zhou2026dexterity, title = {{Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning}}, author = {Huayi Zhou and Wei Gao and Dekun Lu and Ruiji Liu and Zhanqi Zhang and Ziyang Zhang and Jian Chen and Wenlve Zhou and Sheng Xu and Shumin Li and Kangyi Guo and Shichen Xu and Zixin Huang and Yongyi Su and Kui Jia}, year = {2026}, eprint = {2606.02274}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.02274}, } @misc{wu2026coarse, title = {{Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models}}, author = {Jinhao Wu and Shiduo Zhang and Yicheng Liu and Xiaopeng Yu and Sixian Li and Siyin Wang and Hang Zhao and Jing Huo and Yang Gao and Jingjing Gong and Xipeng Qiu and Yu-Gang Jiang}, year = {2026}, eprint = {2606.07107}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.07107}, } @misc{jawaid2026nac, title = {{NAC: Neural Action Codec for Vision-Language-Action Models}}, author = {Ahad Jawaid and Yu Xiang}, year = {2026}, eprint = {2606.21372}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.21372}, } @misc{yuan2026motionvla, title = {{MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model}}, author = {Shanglin Yuan and Weiheng Zhao and Xianda Guo and Wei Sui and Li Yu and Wenyu Liu and Xinggang Wang}, year = {2026}, eprint = {2606.08288}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08288}, } @misc{li2026trust, title = {{Trust-Calibrated VLA Policy Post-Training with Evolving Imagination}}, author = {Wenzhan Li and Yiran Qin and Heng Zhou and Huirui Wang and Yulan Guo and Ruimao Zhang}, year = {2026}, eprint = {2610.16517}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16517}, } @misc{zhang2026core, title = {{CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts}}, author = {Haozhe Zhang and Sixian Li and Yifei Zhang and Zezheng Huai and Hao Chen and Chunhua Shen and Jingjing Gong and Xipeng Qiu}, year = {2026}, eprint = {2607.03693}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.03693}, } @misc{dong2026expo, title = {{EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models}}, author = {Perry Dong and Kuo-Han Hung and Tian Gao and Dorsa Sadigh and Chelsea Finn}, year = {2026}, eprint = {2605.25477}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.25477}, } @misc{yi2026watch, title = {{Watch, Recall, Act: Always-On Robots in Concurrent Embodied Streams}}, author = {Ding Yi and Peiwen Sun and Chenchu Rong and Jianan Wang and Xili Dai and Xiangyu Yue and Xi Lin}, year = {2026}, eprint = {2609.28429}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.28429}, } @misc{dong2026actioncodec, title = {{ActionCodec: What Makes for Good Action Tokenizers}}, author = {Zibin Dong and Yicheng Liu and Shiduo Zhang and Baijun Ye and Yifu Yuan and Fei Ni and Jingjing Gong and Xipeng Qiu and Hang Zhao and Yinchuan Li and Jianye Hao}, year = {2026}, eprint = {2602.15397}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.15397}, } @misc{wang2026think, title = {{Think Proprioceptively: State-Grounded Visual Token Selection for VLA Policies}}, author = {Fangyuan Wang and Peng Zhou and Jiaming Qi and Shipeng Lyu and Chengyang He and David Navarro-Alarcon and Guodong Guo}, year = {2026}, eprint = {2602.06575}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.06575}, } @misc{lu2026thinkingvla, title = {{ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation}}, author = {Tianyi Lu and Hui Zhang and Zijie Diao and Junke Wang and Shengqi Xu and Xingyao Lin and Guojin Zhong and Ziyi Ye and Peng Wang and Zuxuan Wu and Yu-Gang Jiang}, year = {2026}, eprint = {2606.17937}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.17937}, } @misc{go2026flowvla, title = {{FlowVLA: Enabling World Dynamics Understanding through Pluggable 3D Flow Learning}}, author = {Junhyeong Go and Mingyu Jung and Woobin Im and Jongbin Ryu}, year = {2026}, eprint = {2610.16160}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16160}, } @misc{he2026towards, title = {{Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation}}, author = {Yao He and Gan Sun and Wenqi Liang and Fazeng Li and Yang Cong}, year = {2026}, eprint = {2607.14852}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.14852}, } @misc{li2026elastic, title = {{ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies}}, author = {Andrew Zou Li and Gokul Swamy and Yonatan Bisk and Andrea Bajcsy}, year = {2026}, eprint = {2606.31132}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.31132}, } @misc{li2026flashvla, title = {{FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference}}, author = {Zekai Li and Jiaming Tang and Zhijian Liu}, year = {2026}, eprint = {2608.27384}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.27384}, } @misc{piseno2026cloak, title = {{Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA}}, author = {Michael Piseno and Guy Tevet and C. Karen Liu}, year = {2026}, eprint = {2606.22836}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22836}, } @misc{peng2026h, title = {{H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space}}, author = {Xiongfeng Peng and Lu Xu and Yandong Wang and Jiaqian Yu and Zirui Zheng and Yamin Mao and Weiming Li and Inseop Chung and Hyun-woong Cho and Jaewook Yoo and Dongwook Lee and Daehyun Ji and Chao Zhang}, year = {2026}, eprint = {2609.22895}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.22895}, } @misc{tsai2026direct, title = {{Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization}}, author = {Shiang-Feng Tsai and Jin-Cheng Jhang and Yen-Ling Tai and Jia-Hong Lai and Shih-Yun Wong and Kang-Tung Hsu and Yi-Ting Chen and Min Sun}, year = {2026}, eprint = {2606.27663}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.27663}, } @misc{he2026elan, title = {{ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation}}, author = {Zeyuan He and Bowen Yang and Zhirui Fang and Keru Zhou and Lei Jiang and Jingjing Qian and Fan Mo and Junchi Yan and Philip Torr and Xiu Li and Li Jiang and Jialin Yu}, year = {2026}, eprint = {2605.30484}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.30484}, } @misc{dao2026direct, title = {{DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?}}, author = {Jadelynn Dao and Milan Ganai and Yasmina Abukhadra and Ajay Sridhar and Mozhgan Nasr Azadani and Katie Luo and Clark Barrett and Jiajun Wu and Chelsea Finn and Marco Pavone}, year = {2026}, eprint = {2606.12402}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12402}, } @misc{zhao2026information, title = {{Information-Theoretic Constraints for Continual Vision-Language-Action Alignment}}, author = {Libang Zhao and Qixin Zeng and Hongyin Zhang and Donglin Wang}, year = {2026}, eprint = {2603.13335}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2603.13335}, } @misc{lee2026real, title = {{Real-Time Execution with Autoregressive Policies}}, author = {Sangkyu Lee and Seohyeon Park and Tackgeun You and Avi Caciularu and Idan Szpektor and Hwasup Lim and Youngjae Yu}, year = {2026}, eprint = {2606.13355}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13355}, } @misc{son2026seetraceact, title = {{SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos}}, author = {Jaehyeon Son and Junhyun Kim and Kyle Kam and Jeremiah Coholich and Seok Joon Kim and Jinhoo Kim and Chris Dongjoo Kim and Jaemin Cho and Dieter Fox and Zsolt Kira}, year = {2026}, eprint = {2606.02745}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.02745}, } @misc{yu2026barrier, title = {{Barrier-Constrained Guidance For Real-time Asynchronous VLA Execution}}, author = {Wenbo Yu and Jifan Li and Wenke Xia and Yuchen Li and Yizhuo Zhang and Pei Ren and Zhengping Che and Di hu}, year = {2026}, eprint = {2610.14997}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.14997}, } @misc{yang2026mast, title = {{MAST-VLA: Skill-Conditioned Adaptation with Trajectory-Affordance Priors for Multi-Skill Robot Manipulation}}, author = {Jiachi Yang and Zhiyi Xu and Hongquan Zhang and Xin Tan and Zhizhong Zhang and Jingyu Gong and Yuan Xie}, year = {2026}, eprint = {2610.32312}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32312}, } @misc{zhu2026relational, title = {{Relational Spatial Alignment for Vision-Language-Action Models}}, author = {Chaoran Zhu and Hengyi Wang and Chenglin Cui and Yazhe Wan and Taein Kwon and Changjae Oh}, year = {2026}, eprint = {2610.24705}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24705}, } @misc{shin2026back, title = {{Back to the Familiar Future: Failure Recovery for VLA Policies via Pre-Imagined Milestone Selection}}, author = {Suyeon Shin and Juwon Kim and Hyeonbin Park and Hyunseo Kim and Hyundo Lee and Hyung-Sin Kim and Byoung-Tak Zhang}, year = {2026}, eprint = {2606.09258}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.09258}, } @misc{xiang2026lapt, title = {{LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos}}, author = {Zhiyuan Xiang and Peidong Liu and Mingyang Li and Jiawei Li and Wenhow Li and Wenbo Ding and Xiang Deng}, year = {2026}, eprint = {2610.13732}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.13732}, } @misc{wang2026align, title = {{ALIGN: Aligning Condition Estimation and Expression in Advantage-Conditioned Behavior Cloning}}, author = {Zechen Wang and Zhenqi Qiu and Houlong Xiong and Suohang Zhang and Yiyu Ren and Wanting Xu and Hongfei Niu and Chengyang He and Ge Sun and Ran Cheng and Qian Zhu}, year = {2026}, eprint = {2610.26455}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26455}, } @misc{qi2026scale, title = {{Scale Up Strategically: Learning Compositional Generalization via Bias-Aware Evaluation and Data Collection for Robotic Manipulation}}, author = {Yu Qi and Zhang Ye and Xinyi Xu and Yuxuan Lu and Amitoj Sandhu and Boce Hu and Haojie Huang and Jonathan Tremblay and Lawson L. S. Wong}, year = {2026}, eprint = {2607.21582}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.21582}, } @misc{watanabe2026lights, title = {{Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color}}, author = {Marino Watanabe and Takami Sato and Kentaro Yoshioka}, year = {2026}, eprint = {2607.14698}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.14698}, } @misc{chen2026where, title = {{Where Success Breaks: Failure-Boundary Learning for Robust Vision-Language-Action Models}}, author = {Yanzhe Chen and Zhijun Cao and Mike Zheng Shou}, year = {2026}, eprint = {2609.06114}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.06114}, } @misc{syed2026intercepting, title = {{Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation}}, author = {Shahram Najam Syed and Arthur Jakobsson and Haoran Hao and Jeffrey Ichnowski}, year = {2026}, eprint = {2606.02486}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.02486}, } @misc{liu2026plaw, title = {{PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies}}, author = {Yu Liu and Hetian Guo and Tianlv Huang and Ziyi Cai and Wudi Chen and Hantang Wang and Qiutong Liu and Yingzhi Peng and Wei Han and Peijun Tang and Jianan Wang and Zipei Fan and Zhiyuan Zha and Xuan Song}, year = {2026}, eprint = {2610.12285}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.12285}, } @misc{he2026fr, title = {{FR-VLA: Implicit Force Reasoning VLA for Contact-Rich Manipulation}}, author = {Jiaju He and Zhiyuan Yang and Ruyang Han and Jiahong Tang and Zhiping Lin and Haiyue Zhu}, year = {2026}, eprint = {2610.25981}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25981}, } @misc{yang2026vista, title = {{VISTA: Vision-Grounded and Physics-Validated Adaptation of UMI data for VLA Training}}, author = {Siyuan Yang and Linzheng Guo and Ouyang Lu and Zhaxizhuoma and Daoran Zhang and Xinmiao Wang and Ting Xiao and Fangzheng Yan and Zhijun Chen and Yan Ding and Chao Yu and Chenjia Bai and Xuelong Li}, year = {2026}, eprint = {2606.04708}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.04708}, } @misc{zhou2026gaze, title = {{Gaze Prompts: Temporally Dense Human Attention for Vision-Language-Action Fine-Tuning}}, author = {Yihan Zhou and Rui Yan and Mingcong Li and Zheyuan Huang and Xu Yang and Xueyang Guo and Yilin Mo}, year = {2026}, eprint = {2609.34550}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.34550}, } @misc{tang2026safedojo, title = {{SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model}}, author = {Kai Tang and Peidong Jia and Zhong Chu and Jiajun Cao and Jixian Wu and Bohua Zhang and Rui Ma and Fangyuan Zhao and Sixiang Chen and Yichen Guo and Xiaowei Chi and Chun-Kai Fan and Kevin Zhang and Jinchang Xu and Fubing Yang and Weishi Mi and Xiaozhu Ju and Jian Tang and Shanghang Zhang}, year = {2026}, eprint = {2606.20698}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.20698}, } @misc{shi2026beyond, title = {{Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models}}, author = {Liangzhi Shi and Shuaihang Chen and Feng Gao and Yinuo Chen and Kang Chen and Tonghe Zhang and Hongzhi Zang and Jiakai Zhou and Weinan Zhang and Chao Yu and Yu Wang}, year = {2026}, eprint = {2602.12628}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.12628}, } @misc{chen2026supervise, title = {{Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos}}, author = {Danze Chen and Yanzhe Chen and Qiming Huang and Zhijun Cao and Chen Gao and Mike Zheng Shou}, year = {2026}, eprint = {2606.24448}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.24448}, } @misc{dong2025emma, title = {{EMMA: Enhancing Robotic Control Robustness through a Generative Visual Model}}, author = {Zhehao Dong and Xiaofeng Wang and Zheng Zhu and Yirui Wang and Yang Wang and Yukun Zhou and Boyuan Wang and Chaojun Ni and Runqi Ouyang and Wenkang Qin and Xinze Chen and Yun Ye and Guan Huang and Zhen Lu and Yue Yang}, year = {2025}, eprint = {2509.22407}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2509.22407}, } @misc{zhao2026advdex, title = {{AdvDex: Learning Dexterous Manipulation from Human Demonstrations via Joint-Aligned Actions and Adversarial Learning}}, author = {Zhiyue Zhao and Jingyi Wu and Hairuo Liu and Mingyu Liu and Liyang Li and Hengdi Zhang and Tong He and Zhengxue Cheng}, year = {2026}, eprint = {2608.14028}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.14028}, } @misc{liu2026pacer, title = {{PACER: Process-Aware VLA Policy Learning from Human Corrections for Robotic Disassembly}}, author = {Chang Liu and Sibo Tian and Litian Gong and Zhiwen Fan and Jiachen Li and Xiao Liang and Minghui Zheng}, year = {2026}, eprint = {2610.19248}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.19248}, } @misc{kim2026compvla, title = {{CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation}}, author = {Jongmin Kim and Junsu Ha and Che-Sang Park and Minchang Song and Hyeokju Jeong and Himchan Hwang and Jianlong Fu and Frank C. Park}, year = {2026}, eprint = {2609.23614}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.23614}, } @misc{gu2026haf, title = {{HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control}}, author = {Langzhe Gu and Chengkai Hou and Meng Li and Xinhua Wang and Xinyuan Lv and Shuanghao Bai and Guangrun Li and Jingyang He and Ziluo Ding and Zhiyuan Xu and Ning Ding and Kuan Cheng and Jian Tang and Shanghang Zhang and Zhengping Che}, year = {2026}, eprint = {2610.26584}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26584}, } @misc{chen2026clift, title = {{CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning}}, author = {Yuxin Chen and Hari Srikanth and Nathan Jew and Menglin Wu and Pengcheng Wang and Junli Ren and Masayoshi Tomizuka and Peng Xu and Jinyu Xie and Thomas Tian}, year = {2026}, eprint = {2607.29172}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.29172}, } @misc{shi2025maestro, title = {{MAESTRO: Orchestrating Robotics Modules with Coding Agents for Zero-Shot Generalist Robots}}, author = {Junyao Shi and Rujia Yang and Kaitian Chao and Selina Bingqing Wan and Yifei Shao and Jiahui Lei and Jianing Qian and Long Le and Pratik Chaudhari and Kostas Daniilidis and Chuan Wen and Dinesh Jayaraman}, year = {2025}, eprint = {2511.00917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.00917}, } @misc{chou2026vflash, title = {{VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding}}, author = {Yu-Cheng Chou and Shihao Wang and Jin Huang and Chi-Pin Huang and Chiao-An Yang and Xianzhe Fan and Jing Wang and Zhiqi Li and Yuanguo Kuang and Ruijie Zheng and Johan Bjorck and Sifei Liu and Hang Su and Abhishek Badki and Lei Zhang and Alan Yuille and Linxi "Jim'' Fan and Jan Kautz and Zhiding Yu}, year = {2026}, eprint = {2611.08449}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08449}, } @misc{chen2026agentic, title = {{On Agentic Manipulation Policies}}, author = {Chen Chen and Omid Bagherieh and Naveen Nikamanth Appiah Balaji and Jesse T. Gonzalez and Negin Heravi and Fahad Islam and Xueting Li and Jean-Baptiste Regli and Kejia Ren and Petr Švec and David J. Yoon and Matthias Müller and Vladlen Koltun}, year = {2026}, eprint = {2611.09892}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09892}, } @misc{tao2026prism, title = {{PRISM: Primitive Routing via In-context Skill Mixing for Retentive VLA Adaptation}}, author = {Jiachen Tao and Gengyu Zhang and Haoxuan Wang and Bing Liu and Yan Yan}, year = {2026}, eprint = {2611.08917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08917}, } @misc{aggarwal2026computer, title = {{Computer-Use Agents Are Embodied Generalists}}, author = {Pranjal Aggarwal and Sean Welleck}, year = {2026}, eprint = {2611.09847}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2611.09847}, } @misc{deng2026dobottrack, title = {{DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking}}, author = {Shengjun Deng and Yinghan Zhang and Chengrui Wei and Liu Liang and Songyuan Liu and Pengkun Zheng and Yajun Zheng and Ying Zhang and Yuan Tian and Xi Li and Teng Wang}, year = {2026}, eprint = {2611.09041}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09041}, } @misc{park2026spatial, title = {{Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models}}, author = {Jungin Park and Chaoran Zhu and Changjae Oh and Kwanghoon Sohn}, year = {2026}, eprint = {2611.10443}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10443}, } @misc{chi2023diffusion, title = {{Diffusion Policy: Visuomotor Policy Learning via Action Diffusion}}, author = {Cheng Chi and Zhenjia Xu and Siyuan Feng and Eric Cousineau and Yilun Du and Benjamin Burchfiel and Russ Tedrake and Shuran Song}, year = {2023}, eprint = {2303.04137}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2303.04137}, } @misc{zhao2023learning, title = {{Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware}}, author = {Tony Z. Zhao and Vikash Kumar and Sergey Levine and Chelsea Finn}, year = {2023}, eprint = {2304.13705}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2304.13705}, } @misc{fu2024mobile, title = {{Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation}}, author = {Zipeng Fu and Tony Z. Zhao and Chelsea Finn}, year = {2024}, eprint = {2401.02117}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2401.02117}, } @misc{ze2024d, title = {{3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations}}, author = {Yanjie Ze and Gu Zhang and Kangning Zhang and Chenyuan Hu and Muhan Wang and Huazhe Xu}, year = {2024}, eprint = {2403.03954}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.03954}, } @misc{chi2024universal, title = {{Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots}}, author = {Cheng Chi and Zhenjia Xu and Chuer Pan and Eric Cousineau and Benjamin Burchfiel and Siyuan Feng and Russ Tedrake and Shuran Song}, year = {2024}, eprint = {2402.10329}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2402.10329}, } @misc{wang2024dexcap, title = {{DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation}}, author = {Chen Wang and Haochen Shi and Weizhuo Wang and Ruohan Zhang and Li Fei-Fei and C. Karen Liu}, year = {2024}, eprint = {2403.07788}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.07788}, } @misc{openai2018learning, title = {{Learning Dexterous In-Hand Manipulation}}, author = {OpenAI and Marcin Andrychowicz and Bowen Baker and Maciek Chociej and Rafal Jozefowicz and Bob McGrew and Jakub Pachocki and Arthur Petron and Matthias Plappert and Glenn Powell and Alex Ray and Jonas Schneider and Szymon Sidor and Josh Tobin and Peter Welinder and Lilian Weng and Wojciech Zaremba}, year = {2018}, eprint = {1808.00177}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1808.00177}, } @misc{openai2019solving, title = {{Solving Rubik's Cube with a Robot Hand}}, author = {OpenAI and Ilge Akkaya and Marcin Andrychowicz and Maciek Chociej and Mateusz Litwin and Bob McGrew and Arthur Petron and Alex Paino and Matthias Plappert and Glenn Powell and Raphael Ribas and Jonas Schneider and Nikolas Tezak and Jerry Tworek and Peter Welinder and Lilian Weng and Qiming Yuan and Wojciech Zaremba and Lei Zhang}, year = {2019}, eprint = {1910.07113}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1910.07113}, } @misc{chen2022visual, title = {{Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes}}, author = {Tao Chen and Megha Tippur and Siyang Wu and Vikash Kumar and Edward Adelson and Pulkit Agrawal}, year = {2022}, eprint = {2211.11744}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2211.11744}, } @misc{huang2023voxposer, title = {{VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models}}, author = {Wenlong Huang and Chen Wang and Ruohan Zhang and Yunzhu Li and Jiajun Wu and Li Fei-Fei}, year = {2023}, eprint = {2307.05973}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2307.05973}, } @misc{nair2022r, title = {{R3M: A Universal Visual Representation for Robot Manipulation}}, author = {Suraj Nair and Aravind Rajeswaran and Vikash Kumar and Chelsea Finn and Abhinav Gupta}, year = {2022}, eprint = {2203.12601}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2203.12601}, } @misc{jedlicki2026can, title = {{Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?}}, author = {Jack B. Jedlicki and Amish Sethi and Heng Yang}, year = {2026}, eprint = {2610.17350}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17350}, } @misc{bronars2026blind, title = {{Blind Precise Assembly: Proprioceptive Sim-to-Real Peg-in-Hole for Diverse Parts}}, author = {Antonia Bronars and Younghyo Park and Kushal Kedia and Pulkit Agrawal}, year = {2026}, eprint = {2610.23849}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23849}, } @misc{huang2026beyond, title = {{Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations}}, author = {Bo-Ruei Huang and Daniel Seita and Erdem Bıyık}, year = {2026}, eprint = {2610.17802}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17802}, } @misc{gao2026hexashell, title = {{HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World}}, author = {Hongcheng Gao and Alex Zhou and Jay Zhu and Zelin Zheng and Shijia Ge and Xiping Li and Di Wu and Yazhe Wang and Jianshu Zeng and Xuan Shangguan and Yongli Wang and Yexing Wan and Lingyu He and Zhiqi Jia and Sihang Wu and Xiao He}, year = {2026}, eprint = {2610.23479}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23479}, } @misc{wang2022dexgraspnet, title = {{DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation}}, author = {Ruicheng Wang and Jialiang Zhang and Jiayi Chen and Yinzhen Xu and Puhao Li and Tengyu Liu and He Wang}, year = {2022}, eprint = {2210.02697}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2210.02697}, } @misc{shafiullah2023bringing, title = {{On Bringing Robots Home}}, author = {Nur Muhammad Mahi Shafiullah and Anant Rai and Haritheja Etukuru and Yiqian Liu and Ishan Misra and Soumith Chintala and Lerrel Pinto}, year = {2023}, eprint = {2311.16098}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2311.16098}, } @misc{xiong2026modex, title = {{MoDex: Towards Universal Multi-Object Dexterous Grasping}}, author = {Jing Xiong and Jiale Xie and Haoqi Yuan and Chaoyi Xu and Zongqing Lu}, year = {2026}, eprint = {2610.23888}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23888}, } @misc{hu2026learn, title = {{Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning}}, author = {Shuyuan Hu and Deng-Ke Wu and Yifan Jin and Qianhang Luo and Mingchen Ju and Kai Ye and Bo Zhao}, year = {2026}, eprint = {2610.26507}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26507}, } @misc{zeng2020transporter, title = {{Transporter Networks: Rearranging the Visual World for Robotic Manipulation}}, author = {Andy Zeng and Pete Florence and Jonathan Tompson and Stefan Welker and Jonathan Chien and Maria Attarian and Travis Armstrong and Ivan Krasin and Dan Duong and Ayzaan Wahid and Vikas Sindhwani and Johnny Lee}, year = {2020}, eprint = {2010.14406}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2010.14406}, } @misc{shridhar2021cliport, title = {{CLIPort: What and Where Pathways for Robotic Manipulation}}, author = {Mohit Shridhar and Lucas Manuelli and Dieter Fox}, year = {2021}, eprint = {2109.12098}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2109.12098}, } @misc{shridhar2022perceiver, title = {{Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation}}, author = {Mohit Shridhar and Lucas Manuelli and Dieter Fox}, year = {2022}, eprint = {2209.05451}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2209.05451}, } @misc{goyal2023rvt, title = {{RVT: Robotic View Transformer for 3D Object Manipulation}}, author = {Ankit Goyal and Jie Xu and Yijie Guo and Valts Blukis and Yu-Wei Chao and Dieter Fox}, year = {2023}, eprint = {2306.14896}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2306.14896}, } @misc{huang2024rekep, title = {{ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation}}, author = {Wenlong Huang and Chen Wang and Yunzhu Li and Ruohan Zhang and Li Fei-Fei}, year = {2024}, eprint = {2409.01652}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.01652}, } @misc{sundermeyer2021contact, title = {{Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes}}, author = {Martin Sundermeyer and Arsalan Mousavian and Rudolph Triebel and Dieter Fox}, year = {2021}, eprint = {2103.14127}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2103.14127}, } @misc{fang2022anygrasp, title = {{AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains}}, author = {Hao-Shu Fang and Chenxi Wang and Hongjie Fang and Minghao Gou and Jirong Liu and Hengxu Yan and Wenhai Liu and Yichen Xie and Cewu Lu}, year = {2022}, eprint = {2212.08333}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2212.08333}, } @misc{sun2026donic, title = {{DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations}}, author = {Mingze Sun and Ziang Cao and Yuan Fei and Qiankuan Tao and Zihan Wang and Tianqi Liu and Junhao Chen and Haiwen Diao and Fangzhou Hong and Zhaoxi Chen and Ziwei Liu}, year = {2026}, eprint = {2610.29997}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29997}, } @misc{du2026from, title = {{From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation}}, author = {Tingwen Du and Haoyu Guo and Hanxue Zhang and Xuanxu Wang and Junting Dong and Chao Gao and Mingfei Han and Tao Lu and Mulin Yu and Chunhua Shen and Xiaojun Chang and Zhihui Li}, year = {2026}, eprint = {2610.29560}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29560}, } @misc{kareer2024egomimic, title = {{EgoMimic: Scaling Imitation Learning via Egocentric Video}}, author = {Simar Kareer and Dhruv Patel and Ryan Punamiya and Pranay Mathur and Shuo Cheng and Chen Wang and Judy Hoffman and Danfei Xu}, year = {2024}, eprint = {2410.24221}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.24221}, } @misc{tian2024predictive, title = {{Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation}}, author = {Yang Tian and Sizhe Yang and Jia Zeng and Ping Wang and Dahua Lin and Hao Dong and Jiangmiao Pang}, year = {2024}, eprint = {2412.15109}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.15109}, } @misc{zhong2025dexgraspvla, title = {{DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping}}, author = {Yifan Zhong and Xuchuan Huang and Ruochong Li and Ceyao Zhang and Zhang Chen and Tianrui Guan and Fanlian Zeng and Ka Num Lui and Yuyao Ye and Yitao Liang and Yaodong Yang and Yuanpei Chen}, year = {2025}, eprint = {2502.20900}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.20900}, } @misc{tan2026forca, title = {{FORCA: A Force-Aware Coding Agent for Contact-Rich Robot Manipulation}}, author = {Xiao Tan and Yixuan Wang and Zhexi Wang and Wenzhen Yuan}, year = {2026}, eprint = {2610.31841}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31841}, } @misc{xiang2026contactbench, title = {{ContactBench 1.0: A Benchmark for Everyday Contact-Rich Robotic Manipulation}}, author = {Jingyi Xiang and Yixuan Wang and Jeannette Bohg and Wenzhen Yuan}, year = {2026}, eprint = {2610.24512}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24512}, } @misc{yang2026cowboy, title = {{COWBOY: A Scalable Sim-to-Real Framework for Learning Contextual Whole-Body Manipulation}}, author = {Jiahui Yang and Jason Jingzhou Liu and Ray Muxin Liu and Andrew E. Wang and Kenneth Shaw and Deepak Pathak and Ruslan Salakhutdinov}, year = {2026}, eprint = {2610.28948}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28948}, } @misc{xu2026scaling, title = {{Scaling Dexterous Manipulation via Action Representation Pretraining}}, author = {Yanjinghao Xu and Jiexin Zhang and Huan Zhao and Jianjia Mo and Zhenghao Yin and Dingkang Liang and Xiang Bai and Han Ding}, year = {2026}, eprint = {2610.34453}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34453}, } @misc{adalibieke2026adadextrack, title = {{AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking}}, author = {Jianibieke Adalibieke and Qianwei Han and Xueyi Liu and Yuzhe Qin and Li Yi}, year = {2026}, eprint = {2610.33852}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.33852}, } @misc{yang2026adapolicy, title = {{AdaPolicy: Action-Driven Anticipatory Robot Policies via Next-Chunk Prediction}}, author = {Fan Yang and Yuting Su and Chen Zhao and Fugui Fan and Peiguang Jing}, year = {2026}, eprint = {2610.34280}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34280}, } @misc{saha2026long, title = {{Long-Horizon Multi-Object Rearrangement via Distilled Tree Search over Continuous Actions}}, author = {Kallol Saha and Yining Hong and Amber Li and Yejin Choi and Maxim Likhachev and David Held}, year = {2026}, eprint = {2610.25785}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25785}, } @misc{strong2026real, title = {{Real2Sem2Real: 3D Semantic Augmentations for Robot Learning from a Single Human RGB Demonstration}}, author = {Matthew Strong and Ankush K. Dhawan and Julien Poffet and Giuse Pham and Jinho So and Monroe Kennedy}, year = {2026}, eprint = {2610.28880}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28880}, } @misc{chuang2026dexterous, title = {{Dexterous In-Hand Object Pose Reaching with Learned Safety Filters}}, author = {Ian Chuang and Hiya Shah and Vamsi Chilamkur and Iman Soltani and Claire Tomlin}, year = {2026}, eprint = {2610.37652}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37652}, } @misc{dai2026card, title = {{CARD: Contact-Anchored Retargeting for Dexterous Manipulation}}, author = {Cunxi Dai and Botao He and Francois R Hogan and Wei Pan and Rao Fu and Wen-Han Hsieh and Ruoshi Liu and Jitendra Malik and Guanya Shi and Akash Sharma}, year = {2026}, eprint = {2610.36539}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36539}, } @misc{chen2026robolongr, title = {{RoboLongR: Causally Consistent Rewards Teach Robots to Progressively Master Long-Horizon Manipulation}}, author = {Zixuan Chen and Lin Cao and Fenggang Zhang and Haotong Zhang and Yangtao Chen and Jieqi Shi and Jing Huo and Yang Gao}, year = {2026}, eprint = {2610.33863}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.33863}, } @misc{wu2026robostd, title = {{RoboSTD: Zero-Shot Single-to-Dual Transfer via Sagittal Mirroring for Bimanual Learning}}, author = {Hongyu Wu and Chong Liu and Shaoxuan Xie and Shaqi Luo and Hanyu Feng and Shihan Wu and Guocai Yao}, year = {2026}, eprint = {2610.36685}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36685}, } @misc{huang2026cuarms, title = {{cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation}}, author = {Philip Huang and Fabio Ramos and Jiaoyang Li and Caelan Garrett and Lars Johannsmeier}, year = {2026}, eprint = {2610.36250}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36250}, } @misc{he2026reconstruction, title = {{Reconstruction-Augmented Visuomotor Pre-Training of 3D-Grounded Bimanual Dexterity from RGB-Only Human Videos}}, author = {Xingyi He and Zhiwen Qiu and Adhitya Polavaram and Yunhao Cao and Cory Fan and Julius Samwer and Saleh Kalantari and Kuan Fang}, year = {2026}, eprint = {2610.29716}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29716}, } @misc{jawale2026schedulegen, title = {{ScheduleGen: Demonstration Generation via Skill Scheduling for Multi-Arm Imitation Learning}}, author = {Neel Jawale and Stephan Pleines and Soha Pouya and Yuke Zhu and Ajay Mandlekar and Caelan Garrett}, year = {2026}, eprint = {2610.39429}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39429}, } @misc{xu2026contact, title = {{Contact Imitation Interface: Transferring Dexterous Skills by Showing How Contact Unfolds}}, author = {Zhixuan Xu and Yichen Li and Bingchen Wu and Rui Wang and Yiwen Hou and Zixuan Liu and Tianyu Qiu and Lin Shao}, year = {2026}, eprint = {2610.41028}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41028}, } @misc{hou2026rtpolicy, title = {{RTPolicy: Real-Time (32.9 Hz) Multi-View Visuomotor Policy for Robotic Manipulation on Edge Devices}}, author = {Xianbao Hou and Zehao Ni and Yonghao He and Lingfeng Qian and Xin Shi and Hu Su and Wei Sui and Cong Yang}, year = {2026}, eprint = {2610.41625}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41625}, } @misc{cuiralzueco2026tutorial, title = {{A Tutorial on Shape Servoing of Deformable Objects-Part I: Fundamentals}}, author = {Ignacio Cuiral-Zueco and Alessio Caporali and Miguel Aranda and Gianluca Palli and Gonzalo López-Nicolás and Youcef Mezouar}, year = {2026}, eprint = {2610.40559}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40559}, } @misc{zheng2026egoscale, title = {{EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data}}, author = {Ruijie Zheng and Dantong Niu and Yuqi Xie and Jing Wang and Mengda Xu and Yunfan Jiang and Fernando Castañeda and Fengyuan Hu and You Liang Tan and Letian Fu and Trevor Darrell and Furong Huang and Yuke Zhu and Danfei Xu and Linxi Fan}, year = {2026}, eprint = {2602.16710}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.16710}, } @misc{zhang2026opendexgrasp, title = {{OpenDexGrasp: Open-vocabulary Task-Oriented Dexterous Grasping}}, author = {Jiyao Zhang and Junhan Wang and Tianyu Wang and Zeyuan Chen and Anthony Bolton and Yitong Peng and Hao Dong}, year = {2026}, eprint = {2609.18117}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.18117}, } @misc{lum2026play, title = {{Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?}}, author = {Tyler Ga Wei Lum and Kushal Kedia and C. Karen Liu and Jeannette Bohg}, year = {2026}, eprint = {2606.26428}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26428}, } @misc{lin2026bidexgrasp, title = {{BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes}}, author = {Mu Lin and Yi-Lin Wei and Jiaxuan Chen and Yuhao Lin and Shuoyu Chen and Jiangran Lyu and Jiayi Chen and Yansong Tang and He Wang and Wei-Shi Zheng}, year = {2026}, eprint = {2604.06589}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.06589}, } @misc{sha2026efficient, title = {{Efficient and Reliable Teleoperation through Real-to-Sim-to-Real Shared Autonomy}}, author = {Shuo Sha and Yixuan Wang and Binghao Huang and Antonio Loquercio and Yunzhu Li}, year = {2026}, eprint = {2603.17016}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.17016}, } @misc{park2026constraint, title = {{Constraint-Decomposed Impedance Control from Generative Policy for Articulated Object Manipulation}}, author = {Kyungseo Park and Byeongdo Lim and Jungbin Lim and Minseok Choi and Frank C. Park}, year = {2026}, eprint = {2610.16316}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16316}, } @misc{kim2026serf, title = {{SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation}}, author = {Sunghwan Kim and Byeonghyun Pak and Kehan Long and Yulun Tian and Nikolay Atanasov}, year = {2026}, eprint = {2606.12956}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12956}, } @misc{liu2026pixel, title = {{Pixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human Demonstrations}}, author = {Jason Jingzhou Liu and Tony Tao and Deepak Pathak and Ruslan Salakhutdinov}, year = {2026}, eprint = {2611.03647}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03647}, } @misc{tang2026forceldm, title = {{ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation}}, author = {Peiyuan Tang and Yao Li and Xiaodong Zhang and Wuyang Zhang and Qin Xia and Yanyong Zhang and Zijiang Yang}, year = {2026}, eprint = {2611.03294}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03294}, } @misc{mishra2026tampagent, title = {{TAMPAgent: Agentic Belief-Space Planning for Mobile Manipulation}}, author = {Utkarsh A. Mishra and Alperen Degirmenci and Yongxin Chen and Danfei Xu and Tucker Hermans and Caelan Garrett}, year = {2026}, eprint = {2611.03584}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03584}, } @misc{yang2026beyondcontact, title = {{BeyondContact: A Reinforcement Learning Framework for Airflow-Based Non-Contact Manipulation}}, author = {Peiyu Yang and Mohamad S. Moudallal and Antonio Langella and Giulio Turrisi and Victor Barasuol and Claudio Semini}, year = {2026}, eprint = {2611.03059}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03059}, } @misc{liu2026roboauto, title = {{RoboAuto: Autonomous Robot Program Search through Multi-Level Physical Understanding}}, author = {Buzhao Liu and Jianing Ye and Xiu Yuan and Yangtong Feng and Chengsong Huang and Tyler Dinh and Yevgeniy Vorobeychik and Ning Zhang and Chongjie Zhang}, year = {2026}, eprint = {2610.36533}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36533}, } @misc{agarwal2026knowing, title = {{Knowing Where to Look: Interactive Object Search via Spatial-Semantic Fusion}}, author = {Aditya Agarwal and Lucy Cai and Kelly Lu and Travis Manderson and Nicholas Roy and Tomás Lozano-Pérez and Leslie Pack Kaelbling}, year = {2026}, eprint = {2611.00499}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.00499}, } @misc{ze2024generalizable, title = {{Generalizable Humanoid Manipulation with 3D Diffusion Policies}}, author = {Yanjie Ze and Zixuan Chen and Wenhao Wang and Tianyi Chen and Xialin He and Ying Yuan and Xue Bin Peng and Jiajun Wu}, year = {2024}, eprint = {2410.10803}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.10803}, } @misc{hu2025slac, title = {{SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training}}, author = {Jiaheng Hu and Peter Stone and Roberto Martín-Martín}, year = {2025}, eprint = {2506.04147}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.04147}, } @misc{wu2026airoa, title = {{AIRoA-0: Long-Horizon, Precise, Cross-Embodiment Manipulation from Handheld Data}}, author = {Yueh-Hua Wu and Kei Ota and Hanlong Li and Hayata Yuasa and Jason Wang and Kengo Ikeuchi and Kensuke Chiyoma and Makoto Sugiura and Masafumi Takahashi and Masatoshi Tateno and Naoaki Kanazawa and Nicola Scianca and Petr Khrapchenkov and Satoshi Otsubo and Takehiko Ohkawa and Takuya Okubo and Tatsuya Matsushima and Yuki Noguchi and Yuma Shin and Zixuan Zhong}, year = {2026}, eprint = {2611.03815}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03815}, } @misc{lee2026synthesizing, title = {{Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On}}, author = {Seungyong Lee and Suhyeok Jang and Minyoung Kim and Jinwoo Shin}, year = {2026}, eprint = {2611.05163}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05163}, } @misc{agarwal2026feijoa, title = {{FEIJOA: Task-Driven Grounding and Execution for Mobile Manipulation}}, author = {Aditya Agarwal and William Shen and Sahit Chintalapudi and Lucy Cai and Nishanth Kumar and Aidan Curtis and Travis Manderson and Tomás Lozano-Pérez and Leslie Pack Kaelbling}, year = {2026}, eprint = {2611.04080}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04080}, } @misc{gui2026dexhot, title = {{DexHOT: Learning Hand-Object Configuration Transfer for Dexterous Manipulation}}, author = {Zhewei Gui and Anthony Bolton and Jiyao Zhang and Zeyuan Chen and Qiyang Yan and Tianyu Wang and Hao Dong}, year = {2026}, eprint = {2611.05119}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05119}, } @misc{kelemen2026robot, title = {{Robot-Matched Soft Fingers for UMI Data Collection: Lessons from 100 Hours of Pick and Place}}, author = {Kobi Kelemen and Tomasz Niedziałkowski and Marcin Paszczak and Victoriano Montesinos}, year = {2026}, eprint = {2611.03779}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03779}, } @misc{cuiralzueco2026tutorial, title = {{A Tutorial on Shape Servoing of Deformable Objects-Part II: Advanced Concepts}}, author = {Ignacio Cuiral-Zueco and Alessio Caporali and Miguel Aranda and Gianluca Palli and Gonzalo López-Nicolás and Youcef Mezouar}, year = {2026}, eprint = {2611.03825}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03825}, } @misc{li2026robustness, title = {{Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation}}, author = {Wei-Chen Li and Jeffrey Fang and Sasanka Polisetti and Yuexi Song and Glen Chou}, year = {2026}, eprint = {2606.14188}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14188}, } @misc{liu2026enabling, title = {{Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement}}, author = {Xin Liu and Yulin Li and Ziming Li and Pengyu Jing and Zhenhao Huang and Bingyang Zhou and Ziqiu Zeng and Siyuan Luo and Chenkun Qi and Fan Shi}, year = {2026}, eprint = {2606.24552}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.24552}, } @misc{yang2026noise, title = {{Noise-Invariant Spatial Encoding for 3D Manipulation Policies under Depth Corruption}}, author = {Zhiyuan Yang and Jiaju He and Ruiteng Zhao and Anqi Cheng and Haiyue Zhu and Kezhi Mao}, year = {2026}, eprint = {2610.24674}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24674}, } @misc{huang2026kpgrasp, title = {{KPGrasp: Scalable Keypoint Flow Matching for Dexterous Grasp Generation}}, author = {Yuansen Huang and Jiayi Chen and Haoran Liu and Yubin Ke and Bing Han and Jiangran Lyu and Mi Yan and Li Yi and He Wang}, year = {2026}, eprint = {2606.09314}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.09314}, } @misc{toussaint2026combining, title = {{Combining Constrained Sampling and Reinforcement Learning for Manipulation}}, author = {Marc Toussaint and Cornelius V. Braun and Armand Jordana and Sayantan Auddy and Eckart Cobo-Briesewitz and Denis Shcherba and Tilman Burghoff and Justin Carpentier}, year = {2026}, eprint = {2602.08557}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.08557}, } @misc{qiu2025humanoid, title = {{Humanoid Policy ~ Human Policy}}, author = {Ri-Zhao Qiu and Shiqi Yang and Xuxin Cheng and Chaitanya Chawla and Jialong Li and Tairan He and Ge Yan and David J. Yoon and Ryan Hoque and Lars Paulsen and Ge Yang and Jian Zhang and Sha Yi and Guanya Shi and Xiaolong Wang}, year = {2025}, eprint = {2503.13441}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.13441}, } @misc{xiong2025vision, title = {{Vision in Action: Learning Active Perception from Human Demonstrations}}, author = {Haoyu Xiong and Xiaomeng Xu and Jimmy Wu and Yifan Hou and Jeannette Bohg and Shuran Song}, year = {2025}, eprint = {2506.15666}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.15666}, } @misc{bi2025h, title = {{H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation}}, author = {Hongzhe Bi and Lingxuan Wu and Tianwei Lin and Hengkai Tan and Zhizhong Su and Hang Su and Jun Zhu}, year = {2025}, eprint = {2507.23523}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2507.23523}, } @misc{yin2025lightning, title = {{Lightning Grasp: High Performance Procedural Grasp Synthesis with Contact Fields}}, author = {Zhao-Heng Yin and Pieter Abbeel}, year = {2025}, eprint = {2511.07418}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.07418}, } @misc{li2026spectrally, title = {{Spectrally Routed Diffusion Policy for Multi-Task Robotic Manipulation}}, author = {Mingcong Li and Yihan Zhou and Jiayu Qu and Xueyang Guo and Yilin Mo}, year = {2026}, eprint = {2611.04477}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04477}, } @misc{liu2026grasp, title = {{GRASP: Gradient-Guided Sampling for Contact-Rich Physics-Based Motion Retargeting}}, author = {Yang Liu and Tong Wang and Yiming Bao and Heng Yang}, year = {2026}, eprint = {2611.05754}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05754}, } @misc{gervet2023act, title = {{Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation}}, author = {Theophile Gervet and Zhou Xian and Nikolaos Gkanatsios and Katerina Fragkiadaki}, year = {2023}, eprint = {2306.17817}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2306.17817}, } @misc{ke2024d, title = {{3D Diffuser Actor: Policy Diffusion with 3D Scene Representations}}, author = {Tsung-Wei Ke and Nikolaos Gkanatsios and Katerina Fragkiadaki}, year = {2024}, eprint = {2402.10885}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2402.10885}, } @misc{ma2024hierarchical, title = {{Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation}}, author = {Xiao Ma and Sumit Patidar and Iain Haughton and Stephen James}, year = {2024}, eprint = {2403.03890}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.03890}, } @misc{prasad2024consistency, title = {{Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation}}, author = {Aaditya Prasad and Kevin Lin and Jimmy Wu and Linqi Zhou and Jeannette Bohg}, year = {2024}, eprint = {2405.07503}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2405.07503}, } @misc{gao2024manicm, title = {{ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation}}, author = {Zifeng Gao and Guanxing Lu and Tianxing Chen and Wenxun Dai and Ziwei Wang and Chao Shang and Wenbo Ding and Yansong Tang}, year = {2024}, eprint = {2406.01586}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.01586}, } @misc{heg2024streaming, title = {{Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models}}, author = {Sigmund H. Høeg and Yilun Du and Olav Egeland}, year = {2024}, eprint = {2406.04806}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.04806}, } @misc{wang2024sparse, title = {{Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning}}, author = {Yixiao Wang and Yifei Zhang and Mingxiao Huo and Ran Tian and Xiang Zhang and Yichen Xie and Chenfeng Xu and Pengliang Ji and Wei Zhan and Mingyu Ding and Masayoshi Tomizuka}, year = {2024}, eprint = {2407.01531}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.01531}, } @misc{reuss2024multimodal, title = {{Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals}}, author = {Moritz Reuss and Ömer Erdinç Yağmurlu and Fabian Wenzel and Rudolf Lioutikov}, year = {2024}, eprint = {2407.05996}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.05996}, } @misc{li2023crossway, title = {{Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning}}, author = {Xiang Li and Varun Belagali and Jinghuan Shang and Michael S. Ryoo}, year = {2023}, eprint = {2307.01849}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2307.01849}, } @misc{fang2025sam, title = {{SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation}}, author = {Haoquan Fang and Markus Grotz and Wilbert Pumacay and Yi Ru Wang and Dieter Fox and Ranjay Krishna and Jiafei Duan}, year = {2025}, eprint = {2501.18564}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2501.18564}, } @misc{qian2024thinkgrasp, title = {{ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter}}, author = {Yaoyao Qian and Xupeng Zhu and Ondrej Biza and Shuo Jiang and Linfeng Zhao and Haojie Huang and Yu Qi and Robert Platt}, year = {2024}, eprint = {2407.11298}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.11298}, } @misc{ha2023scaling, title = {{Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition}}, author = {Huy Ha and Pete Florence and Shuran Song}, year = {2023}, eprint = {2307.14535}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2307.14535}, } @misc{black2023zero, title = {{Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models}}, author = {Kevin Black and Mitsuhiko Nakamoto and Pranav Atreya and Homer Walke and Chelsea Finn and Aviral Kumar and Sergey Levine}, year = {2023}, eprint = {2310.10639}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2310.10639}, } @misc{duan2024manipulate, title = {{Manipulate-Anything: Automating Real-World Robots using Vision-Language Models}}, author = {Jiafei Duan and Wentao Yuan and Wilbert Pumacay and Yi Ru Wang and Kiana Ehsani and Dieter Fox and Ranjay Krishna}, year = {2024}, eprint = {2406.18915}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.18915}, } @misc{duan2024aha, title = {{AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation}}, author = {Jiafei Duan and Wilbert Pumacay and Nishanth Kumar and Yi Ru Wang and Shulin Tian and Wentao Yuan and Ranjay Krishna and Dieter Fox and Ajay Mandlekar and Yijie Guo}, year = {2024}, eprint = {2410.00371}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.00371}, } @misc{hu2023look, title = {{Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning}}, author = {Yingdong Hu and Fanqi Lin and Tong Zhang and Li Yi and Yang Gao}, year = {2023}, eprint = {2311.17842}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2311.17842}, } @misc{gao2023physically, title = {{Physically Grounded Vision-Language Models for Robotic Manipulation}}, author = {Jensen Gao and Bidipta Sarkar and Fei Xia and Ted Xiao and Jiajun Wu and Brian Ichter and Anirudha Majumdar and Dorsa Sadigh}, year = {2023}, eprint = {2309.02561}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.02561}, } @misc{zheng2024survey, title = {{A Survey of Embodied Learning for Object-Centric Robotic Manipulation}}, author = {Ying Zheng and Lei Yao and Yuejiao Su and Yi Zhang and Yi Wang and Sicheng Zhao and Yiyi Zhang and Lap-Pui Chau}, year = {2024}, eprint = {2408.11537}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2408.11537}, } @misc{jiang2026correct, title = {{Correct Robots Before They Make Mistakes: Proactive Human-in-the-Loop Intervention via Preference Learning}}, author = {Xinkai Jiang and Jing Jiang and Hongyi Zhou and Pankhuri Vanjani and Ahmad Baki and Jakub Suliga and Ge Li and Zhuoyue Li and Gerhard Neumann and Rudolf Lioutikov}, year = {2026}, eprint = {2611.05667}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05667}, } @misc{xiang2026cso, title = {{CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization}}, author = {Zhiyuan Xiang and Xiang Deng and Wanjie Tao and Xu Chen and Zhao Jielun and Weili Guan}, year = {2026}, eprint = {2610.38357}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38357}, } @misc{hong2026learning, title = {{Learning Object-Centric Motion Priors from Human for Robotic Dexterous Manipulation}}, author = {Zhengdong Hong and Guofeng Zhang}, year = {2026}, eprint = {2611.05979}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05979}, } @misc{kajitsuka2026online, title = {{Online Adaptation to Latent Physical Properties for Learning from Demonstration}}, author = {Kotaro Kajitsuka and Masaki Murooka and Fumio Kanehiro}, year = {2026}, eprint = {2611.06118}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.06118}, } @misc{liu2026vls, title = {{VLS: Steering Pretrained Robot Policies via Vision-Language Models}}, author = {Shuo Liu and Ishneet Sukhvinder Singh and Yiqing Xu and Jiafei Duan and Ranjay Krishna}, year = {2026}, eprint = {2602.03973}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.03973}, } @misc{fu2026decal, title = {{DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination}}, author = {Yankai Fu and Ning Chen and Junkai Zhao and Heng Zhang and Guocai Yao and Pengwei Wang and Zhongyuan Wang and Shanghang Zhang}, year = {2026}, eprint = {2609.09119}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.09119}, } @misc{liu2026mobiagent, title = {{MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation}}, author = {Chenzhi Liu and Yue Zhang and Jiehong Lin and Jianan Wang and Bo Wang and Zhongrui Wang and Xiaojuan Qi}, year = {2026}, eprint = {2610.03476}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.03476}, } @misc{zhuang2026attention, title = {{Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning}}, author = {Zheyu Zhuang and Ruiyu Wang and Nick Heppert and Johannes Fabian Hahn and Abhinav Valada and Florian T. Pokorny and Danica Kragic}, year = {2026}, eprint = {2608.13422}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.13422}, } @misc{yuan2026spatial, title = {{Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation}}, author = {Weiduo Yuan and Ze Yuan and Sihan Liu and Jionghao Wang and Liang Heng and Zhenyu Zhao and Yue Wang}, year = {2026}, eprint = {2611.07229}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.07229}, } @misc{kumar2026momasplat, title = {{MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation}}, author = {Sateesh Kumar and Arnav Balaji and Arpit Bahety and Skand Peri and Georgios Pavlakos and Roberto Martín-Martín}, year = {2026}, eprint = {2611.08372}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08372}, } @misc{wang2026latent, title = {{Latent RL Priors for Data-Efficient Dexterous Manipulation}}, author = {Yixiao Wang and Peiyi Chen and Mustafa Mukadam and Shreekant Gayaka and Masayoshi Tomizuka and Son Tran}, year = {2026}, eprint = {2611.08458}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08458}, } @misc{tang2026awls, title = {{AWLS: Advantage-Weighted Latent Steering for One-Step Generative Robotic Manipulation Policies}}, author = {Jiahong Tang and Jiaju He and Zhiyuan Yang and Ruyang Han and Haiyue Zhu}, year = {2026}, eprint = {2610.27736}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27736}, } @misc{huang2026hifun, title = {{HiFun: a Hierarchical Framework for Efficient Functional Dexterous Manipulation Learning}}, author = {Linyi Huang and Guowei Huai and Weibin Liu and Shulong Jiang and Ping Tan and Weixuan Zhang and Hui Zhang and Jie Song}, year = {2026}, eprint = {2610.19518}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.19518}, } @misc{chen2026phase, title = {{Phase-Conditioned Affordance Fields for SE(3)-Equivariant Visuomotor Policies}}, author = {Xinzhe Chen and Liqi Huang and Sihua Ren and Haowen Sun and Mingyang Li and Zeyang Liu and Xingyu Chen and Xuguang Lan}, year = {2026}, eprint = {2610.17281}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17281}, } @misc{li2026scouting, title = {{Scouting the Dynamics Gap: Test-Time Policy Adaptation via Action-Outcome Feedback}}, author = {Yishu Li and Liyuan Geng and Xinyi Mao and Amber Li and David Held}, year = {2026}, eprint = {2609.36107}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.36107}, } @misc{chen2026lima, title = {{LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion}}, author = {Ning Chen and Yankai Fu and Junkai Zhao and Qianpu Sun and Guocai Yao and Pengwei Wang and Zhongyuan Wang and Shanghang Zhang}, year = {2026}, eprint = {2609.28431}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.28431}, } @misc{song2026learning, title = {{Learning Beyond What Humans Can Demonstrate}}, author = {Yuchen Song and Aditya Mittal and Unnat Jain}, year = {2026}, eprint = {2609.24996}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.24996}, } @misc{bai2026proxidex, title = {{ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulation}}, author = {Yushan Bai and Boyu Zheng and Zhiyang Mao and Hongzheng Sun and Yuchuang Tong and En Li and Zhengtao Zhang}, year = {2026}, eprint = {2609.16586}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.16586}, } @misc{pei2026assembling, title = {{Assembling Two Parts in One Hand}}, author = {Liuao Pei and Tianyue Wu and Hui Zhang and Ping Luo and Jie Song}, year = {2026}, eprint = {2609.10137}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.10137}, } @misc{fu2026foci, title = {{FOCI Policy: Focus on Object-Centric Interactions for Relational Manipulation Policies}}, author = {Ze Fu and Pinhao Song and Yutong Hu and Renaud Detry}, year = {2026}, eprint = {2609.08743}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.08743}, } @misc{zhao2026geoprop, title = {{GeoProp: Grounding Robot State in Vision for Generalist Manipulation}}, author = {Guoyang Zhao and Quanhao Qian and Gongjie Zhang and Wenhao Li and Jiuniu Wang and Xiaowei Lu and Deli Zhao and Ran Xu}, year = {2026}, eprint = {2607.07101}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.07101}, } @misc{lin2026how, title = {{How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preference}}, author = {Toru Lin and Shuying Deng and Zhao-Heng Yin and Pieter Abbeel and Jitendra Malik}, year = {2026}, eprint = {2603.03280}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.03280}, } @misc{palma2026bimanual, title = {{Bimanual Robot Manipulation via Multi-Agent In-Context Learning}}, author = {Alessio Palma and Indro Spinelli and Vignesh Prasad and Luca Scofano and Yufeng Jin and Georgia Chalvatzaki and Fabio Galasso}, year = {2026}, eprint = {2604.20348}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.20348}, } @misc{fang2026sim, title = {{Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation}}, author = {Kaipeng Fang and Weiqing Liang and Yuyang Li and Ji Zhang and Pengpeng Zeng and Heng Tao Shen and Jingkuan Song and Lianli Gao}, year = {2026}, eprint = {2601.19406}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2601.19406}, } @misc{shin2026static, title = {{Static In, Dynamic Out: Counterfactual Action Augmentation for Moving Object Manipulation}}, author = {Woo Chul Shin and Zhenyang Chen and Alfred Cueva and Nadun Ranawaka Arachchige and Yingyan Celine Lin and Benjamin Joffe and Shreyas Kousik and Danfei Xu}, year = {2026}, eprint = {2607.27890}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.27890}, } @misc{chen2026costream, title = {{CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation}}, author = {Haonan Chen and Yuxiang Ma and Stephen Tian and Xiaoshen Han and Wenlong Huang and Feiyang Wu and Yunzhu Li and Jiajun Wu and Edward H. Adelson and Yilun Du}, year = {2026}, eprint = {2606.26423}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26423}, } @misc{hiratsuka2026s, title = {{S2A2: Audio-Visual Imitation Learning for Manipulation Tasks Using Acoustic Spatial Information}}, author = {Kaneyoshi Hiratsuka and Benjamin Yen and Ryosuke Kojima}, year = {2026}, eprint = {2607.26047}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.26047}, } @misc{li2024multi, title = {{Multi-GraspLLM: A Multimodal LLM for Multi-Hand Semantic Guided Grasp Generation}}, author = {Haosheng Li and Weixin Mao and Weipeng Deng and Chenyu Meng and Haoqiang Fan and Tiancai Wang and Yoshie Osamu and Ping Tan and Hongan Wang and Xiaoming Deng}, year = {2024}, eprint = {2412.08468}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.08468}, } @misc{yu2026hugs, title = {{HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors}}, author = {Mingrui Yu and Yongpeng Jiang and Yongyi Jia and Kangchen Lv and Li Huang and Yi Ren and Xiang Li}, year = {2026}, eprint = {2607.04554}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.04554}, } @misc{zhang2026fingervip, title = {{FingerViP: Learning Real-World Dexterous Manipulation with Fingertip Visual Perception}}, author = {Zhen Zhang and Weinan Wang and Hejia Sun and Qingpeng Ding and Xiangyu Chu and Guoxin Fang and K. W. Samuel Au}, year = {2026}, eprint = {2604.21331}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.21331}, } @misc{yuan2026from, title = {{From Grasps to Dexterity: Large-Scale Grasp Pretraining for Dexterous Manipulation}}, author = {Ying Yuan and Xinyu Liu and Sriram Krishna and David Held}, year = {2026}, eprint = {2606.30749}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.30749}, } @misc{wang2026instant, title = {{Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation}}, author = {Yilong Wang and Cheng Qian and Edward Johns}, year = {2026}, eprint = {2606.04269}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.04269}, } @misc{schiavi2026continual, title = {{Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations}}, author = {Giulio Schiavi and Andrei Cramariuc and Michael Pantic and Roland Siegwart}, year = {2026}, eprint = {2610.01301}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.01301}, } @misc{wu2026diffmorphgrasp, title = {{DiffMorphGrasp: A Diffusion Framework Conditioned on Hand Morphology for Cross-Embodiment Grasp Generation}}, author = {Zhiyuan Wu and Xiangyu Zhang and Zhuo Chen and Jiankang Deng and Rolandos Alexandros Potamias and Shan Luo}, year = {2026}, eprint = {2602.00915}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.00915}, } @misc{jakobsson2026wiggle, title = {{Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation}}, author = {Arthur Jakobsson and Abhinav Mahajan and Karthik Pullalarevu and Krishna Suresh and Yunchao Yao and Yuemin Mao and Bardienus Duisterhof and Shahram Najam Syed and Jeffrey Ichnowski}, year = {2026}, eprint = {2604.22102}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.22102}, } @misc{ma2026current, title = {{Current as Touch: Proprioceptive Contact Feedback for Compliant Dexterous Manipulation}}, author = {Chenyang Ma and Yunchao Yao and Zhenyu Wei and Ruogu Li and Daniel Szafir and Mingyu Ding}, year = {2026}, eprint = {2607.03529}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.03529}, } @misc{han2026going, title = {{Going with the Flow: Koopman Behavioral Models as Pseudo Planners for Visuo-Motor Dexterity}}, author = {Yunhai Han and Jiaqi Fu and Linhao Bai and Ziyu Xiao and Zhaodong Yang and Yogita Choudhary and Krishna Jha and Chuizheng Kong and Shreyas Kousik and Harish Ravichandar}, year = {2026}, eprint = {2602.07413}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.07413}, } @misc{wang2026roboaug, title = {{RoboAug: One Annotation to Hundreds of Scenes via Region-Contrastive Data Augmentation for Robotic Manipulation}}, author = {Xinhua Wang and Kun Wu and Zhen Zhao and Hu Cao and Yinuo Zhao and Zhiyuan Xu and Meng Li and Shichao Fan and Di Wu and Yixue Zhang and Ning Liu and Zhengping Che and Jian Tang}, year = {2026}, eprint = {2602.14032}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.14032}, } @misc{feng2026minimalist, title = {{A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation}}, author = {Yunhai Feng and Natalie Leung and Jiaxuan Wang and Lujie Yang and Haozhi Qi and Preston Culbertson}, year = {2026}, eprint = {2607.11874}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.11874}, } @misc{li2026towards, title = {{Towards Human-level Dexterous Teleoperation}}, author = {Puhao Li and Zeyuan Chen and Yingying Wu and Pengkun Wei and Yuyang Li and Tianyu Wang and Jiaxiao Shi and Mingrui Yu and Baoxiong Jia and Song-chun Zhu and Tengyu Liu and Siyuan Huang}, year = {2026}, eprint = {2607.11481}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.11481}, } @misc{lee2026adept, title = {{ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning}}, author = {Jayjun Lee and Jessica Yin and Asif Rana and Nicholas Blauch and Octi Zhang and Sam Mady and Mohak Bhardwaj and Nima Fazeli and Nathan Ratliff and Karl Van Wyk and Ankur Handa}, year = {2026}, eprint = {2608.19182}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.19182}, } @misc{cheng2026human, title = {{Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planning}}, author = {Shuo Cheng and Chuye Zhang and Alfred Cueva and Caelan Garrett and Ajay Mandlekar and Danfei Xu}, year = {2026}, eprint = {2606.28813}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.28813}, } @misc{kuang2026dex, title = {{Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation}}, author = {Yuxuan Kuang and Sungjae Park and Katerina Fragkiadaki and Shubham Tulsiani}, year = {2026}, eprint = {2602.15828}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.15828}, } @misc{jing2026assemlm, title = {{AssemLM: A Spatial Reasoning Multimodal Large Language Model for Robotic Assembly}}, author = {Zhi Jing and Jinbin Qiao and Ouyang Lu and Jicong Ao and Shuang Qiu and Huazhe Xu and Yu-Gang Jiang and Chenjia Bai}, year = {2026}, eprint = {2604.08983}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.08983}, } @misc{wang2026mixture, title = {{Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation}}, author = {Dian Wang and Jisang Park and Xiaomeng Xu and Han Zhang and Shuran Song and Jeannette Bohg}, year = {2026}, eprint = {2607.11884}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.11884}, } @misc{scheidemann2026reactive, title = {{Reactive Task-Oriented Robot-Human Handovers via Generative Hypothesis Selection}}, author = {Carmen Scheidemann and Andreea Tulbure and Pascal Burkhardt and Marco Hutter}, year = {2026}, eprint = {2610.08003}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.08003}, } @misc{qiao2026semantics, title = {{Semantics-to-Contact: A Stagewise Framework for Robust Contact-Rich Manipulation}}, author = {Guanren Qiao and Ruixiang Ouyang and Sheng Xu and Yueci Deng and Yunxin Tai and Kui Jia and Guiliang Liu}, year = {2026}, eprint = {2611.07532}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.07532}, } @misc{shen2026biroad, title = {{BiRoAD: Learning Shared and Role-Adaptive Representations for Bimanual Manipulation}}, author = {Yan Shen and Yuchen Liu and Feng Jiang and Hangtian Hu and Xiaoqi Li and Shu Chen and Ruihai Wu and Hao Dong}, year = {2026}, eprint = {2609.23445}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.23445}, } @misc{deng2026grow, title = {{GROW$^2$: Grounding Which and Where for Robot Tool Use}}, author = {Yuhong Deng and Yuyao Liu and David Hsu}, year = {2026}, eprint = {2606.30632}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.30632}, } @misc{zhu2026geohat, title = {{GeoHAT: Geometry-Adaptive Hybrid Action Transformer for Mobile Manipulation}}, author = {Xiangyu Zhu and Renjun Wu and Luzhou Ge and Jinyan Liu and Xuesong Li}, year = {2026}, eprint = {2606.13394}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13394}, } @misc{swoboda2026reap, title = {{REAP: Learning General Rearrangement Heuristics from Motion-Planner Feedback}}, author = {Daniel Swoboda and Hector Geffner}, year = {2026}, eprint = {2610.23973}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23973}, } @misc{wei2026f, title = {{F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation}}, author = {Haoyu Wei and Xiuwei Xu and Ziyang Cheng and Hang Yin and Angyuan Ma and Jie Zhou and Jiwen Lu and Bingyao Yu}, year = {2026}, eprint = {2604.02408}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.02408}, } @misc{liu2026perfect, title = {{Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments}}, author = {Mingyu Liu and Zeju Li and Jiuhe Shu and Hanqing Wang and Yuhao Chao and Hao Chen and Chunhua Shen}, year = {2026}, eprint = {2606.15587}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15587}, } @misc{bodmer2026grounding, title = {{Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control}}, author = {Sabrina Bodmer and René Zurbrügg and Tifanny Portela and Hao Ma and Alexandre Didier and Marco Hutter and Colin Jones and Melanie Zeilinger}, year = {2026}, eprint = {2606.24208}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.24208}, } @misc{pan2026inference, title = {{Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure}}, author = {Yiyuan Pan and Hanjiang Hu and Shangtao Li and Xusheng Luo and Changliu Liu}, year = {2026}, eprint = {2606.26588}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26588}, } @misc{shen2026escape, title = {{ESCAPE: Egocentric Sensing for Collision Avoidance and Policy Execution}}, author = {Weiqing Shen and Wenhao Huang and Baokang Zhang and Shuo Shang and Yanmiao Hu and Haojun Li and Yifan Han and Wenzhao Lian}, year = {2026}, eprint = {2610.23943}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23943}, } @misc{bhardwaj2026goaldex, title = {{GoalDex: Learning Image-Goal-Conditioned Policies for Dexterous In-Hand Manipulation}}, author = {Arjun Bhardwaj and Mayank Mittal and Maximum Wilder-Smith and Vaishakh Patil and Marco Hutter}, year = {2026}, eprint = {2611.02171}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02171}, } @misc{yang2026artmanip, title = {{ArtManip: Category-Level Articulated In-Hand Manipulation}}, author = {Yang Yang and Tengyu Liu and Puhao Li and Zeyuan Chen and Yuyang Li and Xingwan Wang and Yingying Wu and Zhaopeng Cui and Siyuan Huang}, year = {2026}, eprint = {2609.12498}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.12498}, } @misc{kaura2026partialbigrasp, title = {{PartialBiGrasp: Inferring Hidden Local Geometry for Bimanual Grasping from Partial Views}}, author = {Ayush Kaura and Vignesh Vembar and Md Faizal Karim and Keshab Patra and K Madhava Krishna}, year = {2026}, eprint = {2608.19188}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.19188}, } @misc{fei2026t, title = {{T(R,O) Grasp++: Cross-Embodiment Dexterous Grasping in Cluttered Environments at Scale}}, author = {Xin Fei and Zhixuan Xu and Huaicong Fang and Fangjun Chen and Zhaoyu Mu and Rui Yang and Zhexi Luo and Lin Shao}, year = {2026}, eprint = {2610.25410}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25410}, } @misc{seno2026flow, title = {{Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation}}, author = {Koki Seno and Daichi Yashima and Yusuke Takagi and Kento Tokura and Komei Sugiura}, year = {2026}, eprint = {2606.23090}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.23090}, } @misc{wang2026obstadiff, title = {{ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations}}, author = {Jiawen Wang and Kevin Yao and Khalid Jawed}, year = {2026}, eprint = {2609.10918}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.10918}, } @misc{kim2026spatially, title = {{Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Camera}}, author = {Seoyoon Kim and Kanghyun Kim and Dongwoo Ko and Yeong Jin Heo and Min Jun Kim}, year = {2026}, eprint = {2606.14535}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14535}, } @misc{lou2026dexninja, title = {{DexNinja: Learning Robust Dexterous Cutting Policy with a Real-to-Sim-to-Real Data Engine}}, author = {Haozhe Lou and Runyi Yang and Wanqi Zhong and Caiyun Liu and Yicheng Liu and Wenhao Liu and Wenlong Ma and Jiawei Xia and Kanzhi Wu and Danda Pani Paudel and Luc Van Gool and Hang Zhao and Yiming Li}, year = {2026}, eprint = {2610.17208}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17208}, } @misc{freeman2026warped, title = {{WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations}}, author = {Harry Freeman and Chung Hee Kim and Jenny Wang and George Kantor}, year = {2026}, eprint = {2604.10809}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.10809}, } @misc{zhu2026learning, title = {{Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration}}, author = {Xinghao Zhu and Zixi Liu and Shalin Jain and Chenran Li and Milad Noori and Michael Andres Lin and Huihua Zhao and John Welsh and Mrinal Verghese and Wei Liu and Tingwu Wang and Xingye Da and Zhengyi Luo and Vishal Kulkarni and Naema Bhatti and Yuke Zhu and Linxi Fan and Bowen Wen and Danfei Xu and Soha Pouya and Yan Chang}, year = {2026}, eprint = {2607.00033}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.00033}, } @misc{zheng2026contactguard, title = {{ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models}}, author = {Gehan Zheng and Matthew Johnson-Roberson and Weiming Zhi}, year = {2026}, eprint = {2608.13438}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.13438}, } @misc{zhou2026physics, title = {{Physics-Aware Object-Centric SE(3) Forecasting for Real-Time Proactive Dynamic Grasping}}, author = {Yirui Zhou and Hongli Xu and Ying Zheng and Yi Wang and Lap-Pui Chau}, year = {2026}, eprint = {2610.17843}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17843}, } @misc{deng2026robot, title = {{Robot-DIFT: Correspondence-Sensitive Diffusion Features for Contact-Rich Robot Manipulation}}, author = {Yu Deng and Yufeng Jin and Xiaogang Jia and Jiahong Xue and Gerhard Neumann and Georgia Chalvatzaki}, year = {2026}, eprint = {2602.11934}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.11934}, } @misc{wan2026dexflex, title = {{DexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexterity}}, author = {Weikang Wan and Zeyu Lai and Jianyu Hou and Yuchen Zhou and Jiawei Fu and Henrik I Christensen and Hao Su}, year = {2026}, eprint = {2610.14372}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.14372}, } @misc{wang2026anydexrt, title = {{AnyDexRT: Calibration-Efficient Dexterous Hand Retargeting with Few-Shot Human Guidance}}, author = {Chenxi Wang and Ying Feng and Hongjie Fang and Shangning Xia and Lixin Yang and Chuan Wen and Cewu Lu}, year = {2026}, eprint = {2607.08341}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.08341}, } @misc{tu2026grasp, title = {{Grasp-TAGS: Task-Aware Grasp Selection via Critic Distillation for Prehensile Loco-Manipulation}}, author = {Xun Tu and Minghao Zou and Karthik Desingh}, year = {2026}, eprint = {2611.09864}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09864}, } @misc{ansari2026auditing, title = {{Auditing Grasp Feasibility Predictors with Planner-Verified Counterfactuals}}, author = {Sajid Ansari and Antony Thomas and Girish Varma}, year = {2026}, eprint = {2611.09130}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09130}, } @misc{yan2026simduoreal, title = {{SimDuoReal: Object-Centric Bimanual Policy for Emergent Dexterity}}, author = {Qiyang Yan and Yulin Liu and Akash Sharma and Haozhi Qi and Guanya Shi and C. Karen Liu}, year = {2026}, eprint = {2611.10410}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10410}, } @misc{chen2026dexforesight, title = {{DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight}}, author = {Zhongxi Chen and Yi Yang and Xinyi Chen and Mingzhe Ye and Yaping Li and Zhihong Liu and Congsheng Xu and Haonan Wang and Zhijie Deng}, year = {2026}, eprint = {2611.11166}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.11166}, } @misc{lambeta2020digit, title = {{DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation}}, author = {Mike Lambeta and Po-Wei Chou and Stephen Tian and Brian Yang and Benjamin Maloon and Victoria Rose Most and Dave Stroud and Raymond Santos and Ahmad Byagowi and Gregg Kammerer and Dinesh Jayaraman and Roberto Calandra}, year = {2020}, eprint = {2005.14679}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2005.14679}, } @misc{wang2020tacto, title = {{TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors}}, author = {Shaoxiong Wang and Mike Lambeta and Po-Wei Chou and Roberto Calandra}, year = {2020}, eprint = {2012.08456}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2012.08456}, } @misc{higuera2024sparsh, title = {{Sparsh: Self-supervised touch representations for vision-based tactile sensing}}, author = {Carolina Higuera and Akash Sharma and Chaithanya Krishna Bodduluri and Taosha Fan and Patrick Lancaster and Mrinal Kalakrishnan and Michael Kaess and Byron Boots and Mike Lambeta and Tingfan Wu and Mustafa Mukadam}, year = {2024}, eprint = {2410.24090}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.24090}, } @misc{yang2024binding, title = {{Binding Touch to Everything: Learning Unified Multimodal Tactile Representations}}, author = {Fengyu Yang and Chao Feng and Ziyang Chen and Hyoungseob Park and Daniel Wang and Yiming Dou and Ziyao Zeng and Xien Chen and Rit Gangopadhyay and Andrew Owens and Alex Wong}, year = {2024}, eprint = {2401.18084}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2401.18084}, } @misc{huang2024d, title = {{3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing}}, author = {Binghao Huang and Yixuan Wang and Xinyi Yang and Yiyue Luo and Yunzhu Li}, year = {2024}, eprint = {2410.24091}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.24091}, } @misc{bhirangi2024anyskin, title = {{AnySkin: Plug-and-play Skin Sensing for Robotic Touch}}, author = {Raunaq Bhirangi and Venkatesh Pattabiraman and Enes Erciyes and Yifeng Cao and Tess Hellebrekers and Lerrel Pinto}, year = {2024}, eprint = {2409.08276}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.08276}, } @misc{bhirangi2021reskin, title = {{ReSkin: versatile, replaceable, lasting tactile skins}}, author = {Raunaq Bhirangi and Tess Hellebrekers and Carmel Majidi and Abhinav Gupta}, year = {2021}, eprint = {2111.00071}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2111.00071}, } @misc{yang2022touch, title = {{Touch and Go: Learning from Human-Collected Vision and Touch}}, author = {Fengyu Yang and Chenyang Ma and Jiacheng Zhang and Jing Zhu and Wenzhen Yuan and Andrew Owens}, year = {2022}, eprint = {2211.12498}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2211.12498}, } @misc{lambeta2024digitizing, title = {{Digitizing Touch with an Artificial Multimodal Fingertip}}, author = {Mike Lambeta and Tingfan Wu and Ali Sengul and Victoria Rose Most and Nolan Black and Kevin Sawyer and Romeo Mercado and Haozhi Qi and Alexander Sohn and Byron Taylor and Norb Tydingco and Gregg Kammerer and Dave Stroud and Jake Khatha and Kurt Jenkins and Kyle Most and Neal Stein and Ricardo Chavira and Thomas Craven-Bartle and Eric Sanchez and Yitian Ding and Jitendra Malik and Roberto Calandra}, year = {2024}, eprint = {2411.02479}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2411.02479}, } @misc{si2021taxim, title = {{Taxim: An Example-based Simulation Model for GelSight Tactile Sensors}}, author = {Zilin Si and Wenzhen Yuan}, year = {2021}, eprint = {2109.04027}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2109.04027}, } @misc{lin2022tactile, title = {{Tactile Gym 2.0: Sim-to-real Deep Reinforcement Learning for Comparing Low-cost High-Resolution Robot Touch}}, author = {Yijiong Lin and John Lloyd and Alex Church and Nathan F. Lepora}, year = {2022}, eprint = {2207.10763}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2207.10763}, } @misc{taylor2021gelslim, title = {{GelSlim 3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Finger}}, author = {Ian Taylor and Siyuan Dong and Alberto Rodriguez}, year = {2021}, eprint = {2103.12269}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2103.12269}, } @misc{lin2022dtact, title = {{DTact: A Vision-Based Tactile Sensor that Measures High-Resolution 3D Geometry Directly from Darkness}}, author = {Changyi Lin and Ziqi Lin and Shaoxiong Wang and Huazhe Xu}, year = {2022}, eprint = {2209.13916}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2209.13916}, } @misc{lin2023dtact, title = {{9DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimation}}, author = {Changyi Lin and Han Zhang and Jikai Xu and Lei Wu and Huazhe Xu}, year = {2023}, eprint = {2308.14277}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2308.14277}, } @misc{lee2018making, title = {{Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks}}, author = {Michelle A. Lee and Yuke Zhu and Krishnan Srinivasan and Parth Shah and Silvio Savarese and Li Fei-Fei and Animesh Garg and Jeannette Bohg}, year = {2018}, eprint = {1810.10191}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1810.10191}, } @misc{li2022see, title = {{See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation}}, author = {Hao Li and Yizhi Zhang and Junzhe Zhu and Shaoxiong Wang and Michelle A Lee and Huazhe Xu and Edward Adelson and Li Fei-Fei and Ruohan Gao and Jiajun Wu}, year = {2022}, eprint = {2212.03858}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2212.03858}, } @misc{fu2024touch, title = {{A Touch, Vision, and Language Dataset for Multimodal Alignment}}, author = {Letian Fu and Gaurav Datta and Huang Huang and William Chung-Ho Panitch and Jaimyn Drake and Joseph Ortiz and Mustafa Mukadam and Mike Lambeta and Roberto Calandra and Ken Goldberg}, year = {2024}, eprint = {2402.13232}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2402.13232}, } @misc{qi2023general, title = {{General In-Hand Object Rotation with Vision and Touch}}, author = {Haozhi Qi and Brent Yi and Sudharshan Suresh and Mike Lambeta and Yi Ma and Roberto Calandra and Jitendra Malik}, year = {2023}, eprint = {2309.09979}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.09979}, } @misc{akinola2024tacsl, title = {{TacSL: A Library for Visuotactile Sensor Simulation and Learning}}, author = {Iretiayo Akinola and Jie Xu and Jan Carius and Dieter Fox and Yashraj Narang}, year = {2024}, eprint = {2408.06506}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2408.06506}, } @misc{yin2023rotating, title = {{Rotating without Seeing: Towards In-hand Dexterity through Touch}}, author = {Zhao-Heng Yin and Binghao Huang and Yuzhe Qin and Qifeng Chen and Xiaolong Wang}, year = {2023}, eprint = {2303.10880}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2303.10880}, } @misc{yuan2023robot, title = {{Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing}}, author = {Ying Yuan and Haichuan Che and Yuzhe Qin and Binghao Huang and Zhao-Heng Yin and Kang-Won Lee and Yi Wu and Soo-Chul Lim and Xiaolong Wang}, year = {2023}, eprint = {2312.01853}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.01853}, } @misc{suresh2023neural, title = {{Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation}}, author = {Sudharshan Suresh and Haozhi Qi and Tingfan Wu and Taosha Fan and Luis Pineda and Mike Lambeta and Jitendra Malik and Mrinal Kalakrishnan and Roberto Calandra and Michael Kaess and Joseph Ortiz and Mustafa Mukadam}, year = {2023}, eprint = {2312.13469}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.13469}, } @misc{xue2025reactive, title = {{Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation}}, author = {Han Xue and Jieji Ren and Wendi Chen and Gu Zhang and Yuan Fang and Guoying Gu and Huazhe Xu and Cewu Lu}, year = {2025}, eprint = {2503.02881}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.02881}, } @misc{slepyan2026opentac, title = {{OpenTac: An Open Ecosystem for Customizable, Scalable, and Transferable 3D Tactile Sensing}}, author = {Ariel Slepyan and Geeta Chandra Raju Bethala and Jiafeng Gu and Anagha Rajendra Dangle and Yinzhe Zhou and Hongyuan Fu and Jade Sim and Tuhin Basu and Xinyi Yin and Md Faizal Karim and Gregory Hager and Homanga Bharadhwaj and Anand Bhattad and Krishna Murthy Jatavallabhula and Nitish V. Thakor}, year = {2026}, eprint = {2610.31661}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31661}, } @misc{wang2026gelslim, title = {{GelSlim 5.0: Unifying Vision and Touch with a Single Fingertip Camera}}, author = {Xiangdong Wang and I-Hsuan Huang and Xiaohao Xu and Xili Yi and Nima Fazeli and Xiaonan Huang}, year = {2026}, eprint = {2610.31334}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31334}, } @misc{xiang2026tactile, title = {{Tactile-Based Robotic Manipulation: From Mechanics-Driven to Data-Driven Perspectives}}, author = {Jingyi Xiang and Yixuan Wang and Wenzhen Yuan}, year = {2026}, eprint = {2610.30438}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30438}, } @misc{hou2026vectile, title = {{VecTile: A Low-Cost Flexible Tactile Array for 3-DoF Force Sensing}}, author = {Jian Hou and Xin Zhou and Adam J. Spiers}, year = {2026}, eprint = {2610.31472}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31472}, } @misc{ma2026acts, title = {{ACTS: Learning Visuo-Tactile World Models from Human Physical Interaction}}, author = {Yuxiang Ma and Weihan Xu and Pengfei Ye and Anna Mei and Yuxin Ray Song and Tingle Li and Haonan Chen and Edward H. Adelson}, year = {2026}, eprint = {2610.24285}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24285}, } @misc{dogan2026visible, title = {{Visible Touch: Rendering Contact for Visuomotor Policies}}, author = {Metin Alp Dogan and Edward Sun and Feng Xu and Daniel Wu and Allen Peng and Dennis Hong and Yuchen Cui}, year = {2026}, eprint = {2609.14156}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.14156}, } @misc{oh2026factr, title = {{FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning}}, author = {Steven Oh and Jason Jingzhou Liu and Tony Tao and Philip Han and Kenneth Shaw and Satoshi Funabashi and Ruslan Salakhutdinov and Deepak Pathak}, year = {2026}, eprint = {2606.12406}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12406}, } @misc{chen2026pace, title = {{PACE: Temporal-Role Tactile Conditioning for Chunk-Based Insertion Policies}}, author = {Zhiyuan Chen and Shixiong Xu and Shuai Chen and Yangwei You}, year = {2026}, eprint = {2610.16308}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16308}, } @misc{wang2026tactilestep, title = {{TactileStep: Sole Tactile Learning for Regulating Foot-Terrain Interaction in Humanoid Locomotion}}, author = {Zizhuo Wang and Ming-ju Lee and Shaoting Zhu and Haozhe Lou and Hang Zhao and Yiming Li}, year = {2026}, eprint = {2609.28959}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.28959}, } @misc{xu2026fingereye, title = {{FingerEye: Learning Dexterous Manipulation with Continuous Vision-Tactile Sensing}}, author = {Zhixuan Xu and Yichen Li and Xuanye Wu and Tianyu Qiu and Lin Shao}, year = {2026}, eprint = {2604.20689}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.20689}, } @misc{zhang2026detac, title = {{DeTac: Dual-branch Decoupling of Texture and Force Signals in Vision-Based Tactile Sensors}}, author = {Zhirui Zhang and Yunkai Tang and Jiahang Li and Fan Fei and Jinnuo Zhang and Kairan Ding and Jieji Ren and Yandong Guo and Boxin Shi}, year = {2026}, eprint = {2610.16463}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16463}, } @misc{binglin2026panotac, title = {{PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation}}, author = {Binglin and Wang and Xiaole and Jiang and Zicheng Teng and Xinqi Liu and Yunzhu Li and Lerrel Pinto and Zichen Jeff Cui and Binghao Huang}, year = {2026}, eprint = {2611.03520}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03520}, } @misc{shi2026tacmind, title = {{TacMind: Benchmarking and Modeling Tactile Interaction States for Robotic Manipulation}}, author = {Jiaxin Shi and Zibin Wu and Yichi Zhang and Jianghua Duan and Siyu Zhu and Weihao Yuan}, year = {2026}, eprint = {2611.00455}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.00455}, } @misc{murooka2026evaluating, title = {{Evaluating Tactile Foundation Models for End-to-End Imitation Learning in Contact-Rich Manipulation}}, author = {Masaki Murooka and Ryoichi Nakajo and Tomohiro Motoda and Koshi Makihara and Hanbit Oh and Keisuke Shirai and Yukiyasu Domae}, year = {2026}, eprint = {2611.00957}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.00957}, } @misc{chen2026tf, title = {{$TF^2$-Steering: Action Refinement with Tactile Forecasts and Feedback via Velocity-Field Steering}}, author = {Yiming Chen and Xiaofei Wei and Chun Gu and Wei Xiao and Peidong Liu and Li Zhang}, year = {2026}, eprint = {2611.01483}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01483}, } @misc{liu2024maniwav, title = {{ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data}}, author = {Zeyi Liu and Cheng Chi and Eric Cousineau and Naveen Kuppuswamy and Benjamin Burchfiel and Shuran Song}, year = {2024}, eprint = {2406.19464}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.19464}, } @misc{liu2025factr, title = {{FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning}}, author = {Jason Jingzhou Liu and Yulong Li and Kenneth Shaw and Tony Tao and Ruslan Salakhutdinov and Deepak Pathak}, year = {2025}, eprint = {2502.17432}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.17432}, } @misc{feng2025anytouch, title = {{AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors}}, author = {Ruoxuan Feng and Jiangyu Hu and Wenke Xia and Tianci Gao and Ao Shen and Yuhao Sun and Bin Fang and Di Hu}, year = {2025}, eprint = {2502.12191}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2502.12191}, } @misc{ai2024robopack, title = {{RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing}}, author = {Bo Ai and Stephen Tian and Haochen Shi and Yixuan Wang and Cheston Tan and Yunzhu Li and Jiajun Wu}, year = {2024}, eprint = {2407.01418}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.01418}, } @misc{yu2024octopi, title = {{Octopi: Object Property Reasoning with Large Tactile-Language Models}}, author = {Samson Yu and Kelvin Lin and Anxing Xiao and Jiafei Duan and Harold Soh}, year = {2024}, eprint = {2405.02794}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2405.02794}, } @misc{dou2024tactile, title = {{Tactile-Augmented Radiance Fields}}, author = {Yiming Dou and Fengyu Yang and Yi Liu and Antonio Loquercio and Andrew Owens}, year = {2024}, eprint = {2405.04534}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2405.04534}, } @misc{lin2025locotouch, title = {{LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing}}, author = {Changyi Lin and Yuxin Ray Song and Boda Huo and Mingyang Yu and Yikai Wang and Shiqi Liu and Yuxiang Yang and Wenhao Yu and Tingnan Zhang and Jie Tan and Yiyue Luo and Ding Zhao}, year = {2025}, eprint = {2505.23175}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.23175}, } @misc{yu2023mimictouch, title = {{MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation}}, author = {Kelin Yu and Yunhai Han and Qixian Wang and Vaibhav Saxena and Danfei Xu and Ye Zhao}, year = {2023}, eprint = {2310.16917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2310.16917}, } @misc{lin2025pp, title = {{PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands}}, author = {Pei Lin and Yuzhe Huang and Wanlin Li and Jianpeng Ma and Chenxi Xiao and Ziyuan Jiao}, year = {2025}, eprint = {2504.16649}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2504.16649}, } @misc{funk2023evetac, title = {{Evetac: An Event-based Optical Tactile Sensor for Robotic Manipulation}}, author = {Niklas Funk and Erik Helmut and Georgia Chalvatzaki and Roberto Calandra and Jan Peters}, year = {2023}, eprint = {2312.01236}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.01236}, } @misc{luo2025tactile, title = {{Tactile Robotics: An Outlook}}, author = {Shan Luo and Nathan F. Lepora and Wenzhen Yuan and Kaspar Althoefer and Gordon Cheng and Ravinder Dahiya}, year = {2025}, eprint = {2508.11261}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.11261}, } @misc{wang2026reflexarc, title = {{ReflexArc: Bottom-Up Integration of Instantaneous Tactile Reflexes into Whole-Body Humanoid Control}}, author = {Mingyu Wang and Si Li and Ziqing Chen and He Wang and Li Yi}, year = {2026}, eprint = {2611.04424}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04424}, } @misc{wong2026equivariant, title = {{Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation}}, author = {Lik Hang Kenny Wong and Yiyao Ma and Xiu-Shen Wei and Zelong Tan and Zhuheng Song and Dongsheng Xie and Kai Chen and Qi Dou}, year = {2026}, eprint = {2610.03333}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.03333}, } @misc{iten2026tactile, title = {{Tactile Curiosity Drives Robot Interaction}}, author = {Klemens Iten and Alexander Proshkin and Bhavya Sukhija and Stelian Coros and Andreas Krause and Pieter Abbeel and Carmelo Sferrazza}, year = {2026}, eprint = {2609.40134}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.40134}, } @misc{lee2026modular, title = {{Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models}}, author = {Jimin Lee and Huiwon Jang and Myungkyu Koo and Jungwoo Park and Jinwoo Shin}, year = {2026}, eprint = {2604.23272}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.23272}, } @misc{chen2026univtac, title = {{UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking}}, author = {Baijun Chen and Weijie Wan and Tianxing Chen and Xianda Guo and Congsheng Xu and Yuanyang Qi and Haojie Zhang and Longyan Wu and Tianling Xu and Zixuan Li and Yizhe Wu and Rui Li and Xiaokang Yang and Ping Luo and Wei Sui and Yao Mu}, year = {2026}, eprint = {2602.10093}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.10093}, } @misc{yu2026omnitactune, title = {{OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies}}, author = {Kelin Yu and Haode Zhang and Harish Ravichandar and Yunhai Han and Ruohan Gao}, year = {2026}, eprint = {2607.03723}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.03723}, } @misc{chen2026ptld, title = {{PTLD: Sim-to-real Privileged Tactile Latent Distillation for Dexterous Manipulation}}, author = {Rosy Chen and Mustafa Mukadam and Michael Kaess and Tingfan Wu and Francois R Hogan and Jitendra Malik and Akash Sharma}, year = {2026}, eprint = {2603.04531}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.04531}, } @misc{li2026fm, title = {{FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulation}}, author = {Ruicheng Li and Qixiu Li and Ruichun Ma and Yu Deng and Lin Luo and Zhiying Du and Jianfeng Xiang and Huizhi Liang and Ruicheng Wang and Jiaolong Yang and Baining Guo}, year = {2026}, eprint = {2607.18231}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.18231}, } @misc{krohn2026multi, title = {{Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation}}, author = {Rickmer Krohn and Erik Helmut and Niklas Funk and Jan Peters and Vignesh Prasad and Georgia Chalvatzaki}, year = {2026}, eprint = {2606.06281}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.06281}, } @misc{ma2026taccorl, title = {{TacCoRL: Integrating Tactile Feedback into VLA via Simulation}}, author = {Siyu Ma and Yuqi Liang and Chang Yu and Yunuo Chen and Hao Su and Yixin Zhu and Yin Yang and Chenfanfu Jiang}, year = {2026}, eprint = {2606.11743}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.11743}, } @misc{yuan2026ftp, title = {{FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation}}, author = {Chengbo Yuan and Zicheng Zhang and Mingjie Zhou and Wendi Chen and Yi Wang and Zhuoyang Liu and Dantong Niu and Shuo Wang and Hui Zhang and Wenkang Zhang and Yingdong Hu and Yuanqing Gong and Wanli Xing and Chuan Wen and Cewu Lu and Kaifeng Zhang and Yang Gao}, year = {2026}, eprint = {2606.13102}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13102}, } @misc{jang2026wt, title = {{WT-UMI: Tactile-based Whole-Body Manipulation via Force-Supervised Contact-Aware Planning}}, author = {Jaehwi Jang and Zhaoyuan Gu and Alfred Cueva and Zimeng Chai and Junjie Sheng and Thong Nguyen and Himank Galundia and Yifan Wu and Huishu Xue and Isaac Legene and Ojas Mediratta and Davin Doan and Andrew Collins and Sarah Sadegh and KyoungMok Kim and Rishita Dhalbisoi and Zun Chen and Ye Zhao}, year = {2026}, eprint = {2606.13232}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13232}, } @misc{bi2026heterogeneous, title = {{Heterogeneous Tactile Transformer}}, author = {Jianxin Bi and Qiang Wang and Jayaram Reddy and Kelvin Lin and Soibkhon Khajikhanov and Ruihan Gao and Harold Soh}, year = {2026}, eprint = {2606.29948}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.29948}, } @misc{wu2026inference, title = {{Inference-time Policy Steering via Vision and Touch}}, author = {Yilin Wu and Zilin Si and Zeynep Temel and Oliver Kroemer and Andrea Bajcsy}, year = {2026}, eprint = {2606.14981}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14981}, } @misc{clark2026multisensory, title = {{Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force}}, author = {Jaden Clark and Changhao Wang and Yihuai Gao and Seongheon Hong and Hojung Choi and Mark Cutkosky and Yifan Hou and Shuran Song}, year = {2026}, eprint = {2606.30988}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.30988}, } @misc{he2026forceband, title = {{ForceBand: Learning Forceful Manipulation with sEMG}}, author = {Botao He and Zhi Wang and Linna Kuang and Ishaan Ghosh and Jitendra Malik and Cornelia Fermuller and Tingfan Wu and Jiayuan Mao and Ruoshi Liu and Haozhi Qi and Yiannis Aloimonos}, year = {2026}, eprint = {2606.26093}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26093}, } @misc{niu2026t, title = {{T-Rex: Tactile-Reactive Dexterous Manipulation}}, author = {Dantong Niu and Zhuoyang Liu and Zekai Wang and Boning Shao and Zhao-Heng Yin and Anirudh Pai and Yuvan Sharma and Stefano Saravalle and Ruijie Zheng and Jing Wang and Ryan Punamiya and Mengda Xu and Yuqi Xie and Yunfan Jiang and Letian Fu and Konstantinos Kallidromitis and Matteo Gioia and Junyi Zhang and Jiaxin Ge and Haiwen Feng and Fabio Galasso and Wei Zhan and David M. Chan and Yutong Bai and Roei Herzig and Jiahui Lei and Li Fei-Fei and Ken Goldberg and Jitendra Malik and Pieter Abbeel and Yuke Zhu and Danfei Xu and Linxi Fan and Trevor Darrell}, year = {2026}, eprint = {2606.17055}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.17055}, } @misc{feng2026what, title = {{What is the Better Curriculum: Controller-Shaped Grasping Behavior for Contact Force-Sensitive Manipulation}}, author = {Ziyan Feng and Zizhao Yuan and Yulong Fu and Yuxin He and Zhiyuan Zhang and Zhengjie Zhang and Jinni Zhou and Renjing Xu and Qiang Nie}, year = {2026}, eprint = {2609.25887}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.25887}, } @misc{yang2026learning, title = {{Learning with Object-centric Representations of Tactile Interactive Perception for Robot Manipulation}}, author = {Xinyi Yang and Zilin Si and Zhuowei Xu and Zeynep Temel and Oliver Kroemer}, year = {2026}, eprint = {2609.33235}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.33235}, } @misc{luo2025controltac, title = {{ControlTac: Scaling Tactile Data with Physically Controlled Tactile Image Generation}}, author = {Dongyu Luo and Kelin Yu and Amir-Hossein Shahidzadeh and Cornelia Fermüller and Yiannis Aloimonos and Ruohan Gao}, year = {2025}, eprint = {2505.20498}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2505.20498}, } @misc{park2026tactx, title = {{TactX: Learning Shared Tactile Representations Across Diverse Sensors}}, author = {Junsung Park and Sachin Bhadang and Carmelo Sferrazza and Sha Yi and Xiaolong Wang}, year = {2026}, eprint = {2606.31236}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.31236}, } @misc{robledo2026tacstyle, title = {{TacStyle: Personalizing Tactile Robot Policies using Structured Behavior Representations}}, author = {Kevin Robledo and Matías I. Torres Galaz and Kumar Dixhant Rai and Shelly Sara Ulman and Tasmia Tasrin and Heramb Nemlekar}, year = {2026}, eprint = {2606.14862}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14862}, } @misc{ye2025learning, title = {{Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation}}, author = {Guo Ye and Zexi Zhang and Xu Zhao and Shang Wu and Haoran Lu and Shihan Lu and Han Liu}, year = {2025}, eprint = {2512.23864}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.23864}, } @misc{luo2026blind, title = {{Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning}}, author = {Shengcheng Luo and Xiyan Huang and Zhe Xu and Wanlin Li and Ziyuan Jiao and Chenxi Xiao}, year = {2026}, eprint = {2606.11767}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.11767}, } @misc{beveridge2026how, title = {{How Firm Should a Grasp Be?}}, author = {Matthew Beveridge and Shree K. Nayar}, year = {2026}, eprint = {2610.11221}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.11221}, } @misc{grimaldi2026touch, title = {{Touch2Trace: Tactile-Driven Imitation Learning for Dexterous Cable Tracing}}, author = {Matteo Grimaldi and David Klee and Ziling Chen and Tong Jian and Wonju Lee and Wenjie Lu and Tao Yu and Saleh Nabi}, year = {2026}, eprint = {2609.15921}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.15921}, } @misc{jian2026slipsense, title = {{SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection}}, author = {Tong Jian and Aditya Thurvas Senthil Kumar and Xinyi Li and Ziling Chen and Tianyu Dai and Ali Sengul and Matteo Grimaldi and Wenjie Lu and Saleh Nabi and Tao Yu}, year = {2026}, eprint = {2609.15910}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.15910}, } @misc{zhang2026revosim, title = {{RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation}}, author = {Ke Zhang and Lixin Xu and Ziyi Wang and Xiyue Dong and Jie Tan and Lianghu Shao and Xianpeng Wang and Chuanyu Li and Renjing Xu}, year = {2026}, eprint = {2611.08939}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08939}, } @misc{huang2026mdf, title = {{MDF++: Visuo-Tactile World Action Model with End-to-end Representation Learning}}, author = {Zixuan Huang and Jinhao Yu and Zachary Charlick and Dmitry Berenson}, year = {2026}, eprint = {2611.09293}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09293}, } @misc{rudin2021learning, title = {{Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning}}, author = {Nikita Rudin and David Hoeller and Philipp Reist and Marco Hutter}, year = {2021}, eprint = {2109.11978}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2109.11978}, } @misc{lee2020learning, title = {{Learning Quadrupedal Locomotion over Challenging Terrain}}, author = {Joonho Lee and Jemin Hwangbo and Lorenz Wellhausen and Vladlen Koltun and Marco Hutter}, year = {2020}, eprint = {2010.11251}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2010.11251}, } @misc{hwangbo2019learning, title = {{Learning Agile and Dynamic Motor Skills for Legged Robots}}, author = {Jemin Hwangbo and Joonho Lee and Alexey Dosovitskiy and Dario Bellicoso and Vassilios Tsounis and Vladlen Koltun and Marco Hutter}, year = {2019}, eprint = {1901.08652}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1901.08652}, } @misc{kumar2021rma, title = {{RMA: Rapid Motor Adaptation for Legged Robots}}, author = {Ashish Kumar and Zipeng Fu and Deepak Pathak and Jitendra Malik}, year = {2021}, eprint = {2107.04034}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2107.04034}, } @misc{zhuang2023robot, title = {{Robot Parkour Learning}}, author = {Ziwen Zhuang and Zipeng Fu and Jianren Wang and Christopher Atkeson and Soeren Schwertfeger and Chelsea Finn and Hang Zhao}, year = {2023}, eprint = {2309.05665}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.05665}, } @misc{cheng2023extreme, title = {{Extreme Parkour with Legged Robots}}, author = {Xuxin Cheng and Kexin Shi and Ananye Agarwal and Deepak Pathak}, year = {2023}, eprint = {2309.14341}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.14341}, } @misc{radosavovic2023real, title = {{Real-World Humanoid Locomotion with Reinforcement Learning}}, author = {Ilija Radosavovic and Tete Xiao and Bike Zhang and Trevor Darrell and Jitendra Malik and Koushil Sreenath}, year = {2023}, eprint = {2303.03381}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2303.03381}, } @misc{cheng2024expressive, title = {{Expressive Whole-Body Control for Humanoid Robots}}, author = {Xuxin Cheng and Yandong Ji and Junming Chen and Ruihan Yang and Ge Yang and Xiaolong Wang}, year = {2024}, eprint = {2402.16796}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2402.16796}, } @misc{he2024learning, title = {{Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation}}, author = {Tairan He and Zhengyi Luo and Wenli Xiao and Chong Zhang and Kris Kitani and Changliu Liu and Guanya Shi}, year = {2024}, eprint = {2403.04436}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.04436}, } @misc{fu2024humanplus, title = {{HumanPlus: Humanoid Shadowing and Imitation from Humans}}, author = {Zipeng Fu and Qingqing Zhao and Qi Wu and Gordon Wetzstein and Chelsea Finn}, year = {2024}, eprint = {2406.10454}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.10454}, } @misc{he2025asap, title = {{ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills}}, author = {Tairan He and Jiawei Gao and Wenli Xiao and Yuanhang Zhang and Zi Wang and Jiashun Wang and Zhengyi Luo and Guanqi He and Nikhil Sobanbab and Chaoyi Pan and Zeji Yi and Guannan Qu and Kris Kitani and Jessica Hodgins and Linxi "Jim" Fan and Yuke Zhu and Changliu Liu and Guanya Shi}, year = {2025}, eprint = {2502.01143}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.01143}, } @misc{liao2026supermimic, title = {{SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model}}, author = {Qiayuan Liao and Yiyang Shao and Junfeng Long and Kevin Zakka and Roberto Horowitz and Pieter Abbeel and Koushil Sreenath}, year = {2026}, eprint = {2610.28480}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28480}, } @misc{miki2022learning, title = {{Learning robust perceptive locomotion for quadrupedal robots in the wild}}, author = {Takahiro Miki and Joonho Lee and Jemin Hwangbo and Lorenz Wellhausen and Vladlen Koltun and Marco Hutter}, year = {2022}, eprint = {2201.08117}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2201.08117}, } @misc{he2024omnih, title = {{OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning}}, author = {Tairan He and Zhengyi Luo and Xialin He and Wenli Xiao and Chong Zhang and Weinan Zhang and Kris Kitani and Changliu Liu and Guanya Shi}, year = {2024}, eprint = {2406.08858}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.08858}, } @misc{he2024hover, title = {{HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots}}, author = {Tairan He and Wenli Xiao and Toru Lin and Zhengyi Luo and Zhenjia Xu and Zhenyu Jiang and Jan Kautz and Changliu Liu and Guanya Shi and Xiaolong Wang and Linxi Fan and Yuke Zhu}, year = {2024}, eprint = {2410.21229}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.21229}, } @misc{margolis2022walk, title = {{Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior}}, author = {Gabriel B Margolis and Pulkit Agrawal}, year = {2022}, eprint = {2212.03238}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2212.03238}, } @misc{nahrendra2023dreamwaq, title = {{DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning}}, author = {I Made Aswin Nahrendra and Byeongho Yu and Hyun Myung}, year = {2023}, eprint = {2301.10602}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2301.10602}, } @misc{hoeller2023anymal, title = {{ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots}}, author = {David Hoeller and Nikita Rudin and Dhionis Sako and Marco Hutter}, year = {2023}, eprint = {2306.14874}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2306.14874}, } @misc{zhuang2024humanoid, title = {{Humanoid Parkour Learning}}, author = {Ziwen Zhuang and Shenzhe Yao and Hang Zhao}, year = {2024}, eprint = {2406.10759}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.10759}, } @misc{heyrman2026watch, title = {{Watch Your Step: Anticipated Perception for Humanoid Locomotion}}, author = {Matthias Heyrman and Chenhao Li and Ioannis Dadiotis and Marco Hutter}, year = {2026}, eprint = {2610.29612}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29612}, } @misc{peng2021amp, title = {{AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control}}, author = {Xue Bin Peng and Ze Ma and Pieter Abbeel and Sergey Levine and Angjoo Kanazawa}, year = {2021}, eprint = {2104.02180}, archivePrefix = {arXiv}, primaryClass = {cs.GR}, url = {https://arxiv.org/abs/2104.02180}, } @misc{he2024agile, title = {{Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion}}, author = {Tairan He and Chong Zhang and Wenli Xiao and Guanqi He and Changliu Liu and Guanya Shi}, year = {2024}, eprint = {2401.17583}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2401.17583}, } @misc{team2026scaling, title = {{$λ_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation}}, author = {Lambda-humanoid Team and : and Chongyang Xu and Jin Chen and Jinhui Ye and Yilun Chen and Yiming Jiang and Zhao Wu and Hu Wei and Lin Qu and Shifeng Zhang and Yisheng He and Yuming Jiang and Zenan Meng and Zheng Wu and Mu Xu and Steven Hoi}, year = {2026}, eprint = {2610.18950}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18950}, } @misc{liao2025beyondmimic, title = {{BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion}}, author = {Qiayuan Liao and Takara E. Truong and Xiaoyu Huang and Yuman Gao and Guy Tevet and Koushil Sreenath and C. Karen Liu}, year = {2025}, eprint = {2508.08241}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.08241}, } @misc{he2026vit, title = {{ViT-H: Generative Video-To-Humanoid Control with Motion Tracking Feedback}}, author = {Zimo He and Tianyi Bian and Zizhong Yang and Hongjie Li and Nan Jiang and Jieming Cui and Baoxiong Jia and Yizhou Wang and Siyuan Huang and Yixin Zhu}, year = {2026}, eprint = {2610.32966}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32966}, } @misc{amiet2026solving, title = {{Solving a Giant Rubik's Cube with a Quadruped Robot}}, author = {Lukas Amiet and Gabriel Sánchez-Blanco Repgen and Mayank Mittal and Victor Klemm and Andrei Cramariuc and Marco Hutter and Cesar Cadena}, year = {2026}, eprint = {2610.24610}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24610}, } @misc{li2026learning, title = {{Learning Force-Reactive Humanoid Loco-Manipulation}}, author = {Sihang Li and Xiaofeng Guo and Jinkun Cao and Charlie Cheng and Ruihan Yang and Chen Feng and Guanya Shi and Haozhi Qi}, year = {2026}, eprint = {2610.35862}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35862}, } @misc{yang2026zero, title = {{Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data}}, author = {Dianyi Yang and Mengya Liu and Zhumei Wang and Yu Liu and Xiaochen Zhang and Yixuan Li and Le Ma and Yuhang Yang and Weiqi Huang and Wei Liang and Baoxiong Jia and Siyuan Huang}, year = {2026}, eprint = {2610.35075}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35075}, } @misc{chen2026humanoidndm, title = {{HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model}}, author = {Chao Chen and Zhenrong Wang and Jilong Wang and Yusen Feng and Jiangran Lyu and Li Yi and He Wang}, year = {2026}, eprint = {2610.34126}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34126}, } @misc{kim2026diffcontact, title = {{DiffContact: Differentiable Contact Dynamics for Policy Learning and Contact-Implicit Trajectory Optimization}}, author = {Gijeong Kim and Seungbin Oh and Dongyun Kang and Hae-Won Park}, year = {2026}, eprint = {2610.35852}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35852}, } @misc{cao2026humit, title = {{HuMiT: Low-Latency Whole-Body Humanoid Teleoperation via Compact Reference Tracking}}, author = {Liu Cao and Botian Xu and Ruoqu Chen and Jiajun Liu and Mingzhi Pei and Zihao Wang and Zhongyu Li and Mengdi Xu}, year = {2026}, eprint = {2610.29903}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29903}, } @misc{yi2026swap, title = {{SWAP: Test-Time Steerable Humanoid Whole-Body Collision Avoidance}}, author = {Zeji Yi and Guanqi He and Xiaofeng Guo and Guannan Qu and Pieter Abbeel and Yan Duan and Karen Liu and Guanya Shi}, year = {2026}, eprint = {2610.25711}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25711}, } @misc{lin2026action, title = {{Action-Aligned Latent Planning for Versatile Humanoid Loco-Manipulation}}, author = {Yutang Lin and Guanya Shi and C. Karen Liu}, year = {2026}, eprint = {2610.24675}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24675}, } @misc{xu2026reach, title = {{REACH: An RL-based Hierarchical Humanoid Crawling Framework for Adaptable Confined Space Traversal}}, author = {Shengzhang Xu and Yuning Guo and Weiyi Hu and Yifeng Xu and Zhongyu Li and He Kong}, year = {2026}, eprint = {2610.36546}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36546}, } @misc{li2026graft, title = {{GRAFT: Geometry-Aware Residual Adaptation for Foundation Trackers}}, author = {Liang Li and Guoyao Zhang and Xingyu Chen and Sikai Wu and Qianyang Wu and Yuhang Lin and Renjing Xu and Mingliang Zhou and Diyun Xiang}, year = {2026}, eprint = {2610.36507}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36507}, } @misc{drolet2026whole, title = {{Whole-Body Humanoid Control via Stochastic Motion Tokenization}}, author = {Michael Drolet and Oleg Arenz and Jan Peters}, year = {2026}, eprint = {2610.36452}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36452}, } @misc{azulay2026test, title = {{Test-Time Motion Steering for Perceptive Humanoid Fall Recovery}}, author = {Osher Azulay and Cheng-Lin Hsieh and Stella X. Yu}, year = {2026}, eprint = {2610.30061}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30061}, } @misc{gu2026smr, title = {{SMR: Learning streaming motion retargeting for humanoids from human semantic}}, author = {Chun Gu and Juntong Zhang and Jingyu Li and Li Zhang}, year = {2026}, eprint = {2610.29169}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29169}, } @misc{tessler2026metatron, title = {{METATRON: A Promptable Whole-Body Execution Layer for Humanoids}}, author = {Chen Tessler and Yifeng Jiang and Alec Otto and Yi Shi and Umar Iqbal and Gal Chechik and Xue Bin Peng}, year = {2026}, eprint = {2610.38027}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38027}, } @misc{kolesnichenko2026sonic, title = {{SONIC-K1: Porting a Universal Humanoid Motion Tracker to a Small Humanoid on a Single GPU}}, author = {Kyrylo Kolesnichenko and Jong-Hoon Kim}, year = {2026}, eprint = {2610.39327}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39327}, } @misc{liu2026elevate, title = {{ELEVATE: Agentic Controller Acquisition from Task Failure for Quadrupedal Manipulation}}, author = {Shiqi Liu and Radu Corcodel and Ding Zhao}, year = {2026}, eprint = {2610.38388}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38388}, } @misc{bu2026movens, title = {{Movens-Zero: Scaling Humanoid Motion Foundation Models with Large-Scale Human Videos}}, author = {Wendong Bu and Tinghong Ye and Qizhou Wang and Jiacheng Li and Zhiqi Ge and Yuze Lin and Zhongqi Yue and Yi Su and Jingyu Wang and Kai Shen and Jingdong Liu and Chengyuan Deng and Xiaoxuan Chen and Xin Tan and Jiaming Ji and Wenqiao Zhang and Chenghong Jiang and Tuoyu Li and Siliang Tang and Jun Xiao and Tat-Seng Chua and Yueting Zhuang and Xingxing Wang and Juncheng Li}, year = {2026}, eprint = {2610.41877}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41877}, } @misc{huang2026diffwbc, title = {{DiffWBC: Unlocking Steerable General Humanoid Motion Tracking via One-Step Diffusion Whole-Body Control}}, author = {Yifei Huang and Yazhao Yang and Weijia Li and Zhiheng Ma and Dian Shen}, year = {2026}, eprint = {2610.41354}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41354}, } @misc{lu2026roof, title = {{ROOF: Learning Humanoid Fall Recovery under Overhead Constraints}}, author = {Yidan Lu and Jiayuan Yu and Zongrui Cai and Jingwen Sun and Jinrui Han and Jing Wang and Ping Luo and Peng Lu}, year = {2026}, eprint = {2610.42097}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.42097}, } @misc{cheng2026cmp, title = {{CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection}}, author = {Ziyang Cheng and Haoyu Wei and Hang Yin and Xiuwei Xu and Bingyao Yu and Jie Zhou and Jiwen Lu}, year = {2026}, eprint = {2604.07457}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.07457}, } @misc{ghansah2026forge, title = {{FORGE: Feasible Online Reduced-Order Reference Generation and Whole-Body Execution for Agile Humanoid Locomotion}}, author = {Adrian B. Ghansah and Yujin An and Jeeseop Kim and Soon-Jo Chung}, year = {2026}, eprint = {2610.37974}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37974}, } @misc{han2026hipc, title = {{HIPC: Humanoid Iterative Planning and Control via Goal-Conditioned Motion Closure}}, author = {Yi Han and Xingyu Chen and Zixuan Lang and Qianyang Wu and Yuhang Lin and Ji Ma and Liang Li and Dongting Li and Xinpeng Liu and Ruoli Dai and Hesheng Wang and Renjing Xu and Lei Han}, year = {2026}, eprint = {2610.41334}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41334}, } @misc{xie2026grail, title = {{GRAIL: Generating Humanoid Loco-Manipulation from World Models}}, author = {Tianyi Xie and Haotian Zhang and Jinhyung Park and Zi Wang and Bowen Wen and Jiefeng Li and Xueting Li and Qingwei Ben and Haoyang Weng and Yufei Ye and David Minor and Tingwu Wang and Chenfanfu Jiang and Sanja Fidler and Jan Kautz and Linxi Fan and Yuke Zhu and Zhengyi Luo and Umar Iqbal and Ye Yuan}, year = {2026}, eprint = {2606.05160}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.05160}, } @misc{zhong2026robonaldo, title = {{RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning}}, author = {Yichao Zhong and Yidan Lu and Yuhang Lu and Tianyang Tang and Haoguang Mai and Yixuan Pan and Tianyu Li and Li Chen and Jingbo Wang and Zhongyu Li and Peng Lu and Hongyang Li}, year = {2026}, eprint = {2606.11092}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.11092}, } @misc{li2026tango, title = {{TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model}}, author = {Anqi Li and Yuxin Chen and Zhaobo Li and Zhuo Cao and Junli Ren and Masayoshi Tomizuka and Dhruv Shah}, year = {2026}, eprint = {2609.09158}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.09158}, } @misc{hu2026openhlm, title = {{OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation}}, author = {Yingdong Hu and Haodong Zhu and Boyuan Zheng and Yihang Hu and Tong Zhang and Zunhao Chen and Junming Zhao and Ruiqian Nai and Yang Gao}, year = {2026}, eprint = {2606.22174}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22174}, } @misc{zhao2026ladderman, title = {{LadderMan: Learning Humanoid Perceptive Ladder Climbing}}, author = {Siheng Zhao and Yuanhang Zhang and Ziqi Lu and Pieter Abbeel and Rocky Duan and Koushil Sreenath and Yue Wang and C. Karen Liu and Guanya Shi}, year = {2026}, eprint = {2606.05873}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.05873}, } @misc{ma2026holoboxing, title = {{HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training}}, author = {Xihan Ma and Bo Zhang and Boxiong Li and Yuhan Bao and Ziyue Liu and Yucheng Wang}, year = {2026}, eprint = {2610.32909}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32909}, } @misc{fortin2026tacos, title = {{TACOS: Terrain-Aware COntact Supervision for Visual Footstep Planning}}, author = {Jean-Michel Fortin and William Larrivée-Hardy and Gabriel Jeanson and Olivier Gamache and Daniele De Martini and François Pomerleau and Philippe Giguère}, year = {2026}, eprint = {2610.37806}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37806}, } @misc{peng2026hug, title = {{HuG: Learning Humanoid Whole-Body Affordance-Aware Grasping with Active Perception}}, author = {Xuanbin Peng and Lai Wei and Yuze Zhai and Qingyuan Yu and Keyi Wang and Jianglong Ye and Xiaolong Wang}, year = {2026}, eprint = {2611.01659}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01659}, } @misc{ye2026energy, title = {{Energy-Based Policy Orchestration}}, author = {Weirui Ye and Yen-Jen Wang and Elvis Hsieh and Zhiyang Dou and Shibo Zhao and Pieter Abbeel and Yilun Du and Leslie Pack Kaelbling and Tomás Lozano-Pérez}, year = {2026}, eprint = {2611.02546}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02546}, } @misc{lim2026mapo, title = {{MAPO: Mixture of Experts with Alternating Policy Optimization for Universal Humanoid Motion Tracking}}, author = {Seonghyeon Lim and Hyeonwoo Lee and Mincheol Kim and Kimin Lee and Hyun Myung}, year = {2026}, eprint = {2611.02613}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02613}, } @misc{jiang2025wholebodyvla, title = {{WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control}}, author = {Haoran Jiang and Jin Chen and Qingwen Bu and Li Chen and Modi Shi and Yanjie Zhang and Delong Li and Chuanzhe Suo and Chuang Wang and Zhihui Peng and Hongyang Li}, year = {2025}, eprint = {2512.11047}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.11047}, } @misc{chen2024learning, title = {{Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies}}, author = {Zixuan Chen and Xialin He and Yen-Jen Wang and Qiayuan Liao and Yanjie Ze and Zhongyu Li and S. Shankar Sastry and Jiajun Wu and Koushil Sreenath and Saurabh Gupta and Xue Bin Peng}, year = {2024}, eprint = {2410.11825}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.11825}, } @misc{peng2018deepmimic, title = {{DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills}}, author = {Xue Bin Peng and Pieter Abbeel and Sergey Levine and Michiel van de Panne}, year = {2018}, eprint = {1804.02717}, archivePrefix = {arXiv}, primaryClass = {cs.GR}, url = {https://arxiv.org/abs/1804.02717}, } @misc{peng2022ase, title = {{ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters}}, author = {Xue Bin Peng and Yunrong Guo and Lina Halper and Sergey Levine and Sanja Fidler}, year = {2022}, eprint = {2205.01906}, archivePrefix = {arXiv}, primaryClass = {cs.GR}, url = {https://arxiv.org/abs/2205.01906}, } @misc{luo2023perpetual, title = {{Perpetual Humanoid Control for Real-time Simulated Avatars}}, author = {Zhengyi Luo and Jinkun Cao and Alexander Winkler and Kris Kitani and Weipeng Xu}, year = {2023}, eprint = {2305.06456}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2305.06456}, } @misc{xu2025intermimic, title = {{InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions}}, author = {Sirui Xu and Hung Yu Ling and Yu-Xiong Wang and Liang-Yan Gui}, year = {2025}, eprint = {2502.20390}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2502.20390}, } @misc{luo2025sonic, title = {{SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control}}, author = {Zhengyi Luo and Ye Yuan and Tingwu Wang and Chenran Li and Fernando Castañeda and Sirui Chen and Zi-Ang Cao and Jiefeng Li and David Minor and Qingwei Ben and Jinhyung Park and David Sami and Zi Wang and Xingye Da and Runyu Ding and Cyrus Hogg and Lina Song and Edy Lim and Eugene Jeong and Tairan He and Haoru Xue and Wenli Xiao and Simon Yuen and Jan Kautz and Yan Chang and Umar Iqbal and Linxi "Jim" Fan and Yuke Zhu}, year = {2025}, eprint = {2511.07820}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.07820}, } @misc{qi2026humanoid, title = {{Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking}}, author = {Zekun Qi and Xuchuan Chen and Dairu Liu and Chenghuai Lin and Yunrui Lian and Sikai Liang and Zhikai Zhang and Yu Guan and Jilong Wang and Wenyao Zhang and Xinqiang Yu and He Wang and Li Yi}, year = {2026}, eprint = {2606.03985}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.03985}, } @misc{wu2026sugar, title = {{SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework}}, author = {Tianshu Wu and Xiangqi Kong and Yue Chen and Qize Yu and Hang Ye and Jia Li and Yizhou Wang and Hao Dong}, year = {2026}, eprint = {2605.20373}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.20373}, } @misc{seo2023deep, title = {{Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation}}, author = {Mingyo Seo and Steve Han and Kyutae Sim and Seung Hyeon Bang and Carlos Gonzalez and Luis Sentis and Yuke Zhu}, year = {2023}, eprint = {2309.01952}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.01952}, } @misc{sleiman2026hlo, title = {{HLO-AMP: Hierarchical Loco-Manipulation from Object-Aware Motion Priors}}, author = {Jean-Pierre Sleiman and Bilal Hammoud and He Li and Jonathan Foster and Sylvain Bertrand and Jessica K. Hodgins and Farbod Farshidian}, year = {2026}, eprint = {2611.05113}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05113}, } @misc{dong2026coordinating, title = {{Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight}}, author = {Ju Dong and Xinyu Xiao and Yiming Zhou and Tianshuo Yang and Xuerong Liu and Lei Zhang and Jian Chen and Haocheng Zhao and Yu Fu and Yujie Wei and Diwen Zheng and Alois Christian Knoll and Angela P. Schoellig and Ping Luo and Jianwei Zhang}, year = {2026}, eprint = {2611.04839}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04839}, } @misc{schuck2026learning, title = {{Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL}}, author = {Martin Schuck and Maks Sorokin and Simone Manni and Duy Ta and Angela P. Schoellig and Marco Hutter and Simon Le Cleac'H and Jan Brüdigam}, year = {2026}, eprint = {2608.12063}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.12063}, } @misc{qu2026ressafe, title = {{ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids}}, author = {Gechen Qu and Tong Zhang and Bike Zhang and Yen-Jen Wang and Koushil Sreenath and Claire Tomlin and Jason Jangho Choi}, year = {2026}, eprint = {2609.15988}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.15988}, } @misc{chen2025gmt, title = {{GMT: General Motion Tracking for Humanoid Whole-Body Control}}, author = {Zixuan Chen and Mazeyu Ji and Xuxin Cheng and Xuanbin Peng and Xue Bin Peng and Xiaolong Wang}, year = {2025}, eprint = {2506.14770}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.14770}, } @misc{ze2025twist, title = {{TWIST: Teleoperated Whole-Body Imitation System}}, author = {Yanjie Ze and Zixuan Chen and João Pedro Araújo and Zi-ang Cao and Xue Bin Peng and Jiajun Wu and C. Karen Liu}, year = {2025}, eprint = {2505.02833}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.02833}, } @misc{xue2025unified, title = {{A Unified and General Humanoid Whole-Body Controller for Versatile Locomotion}}, author = {Yufei Xue and Wentao Dong and Minghuan Liu and Weinan Zhang and Jiangmiao Pang}, year = {2025}, eprint = {2502.03206}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.03206}, } @misc{li2025amo, title = {{AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control}}, author = {Jialong Li and Xuxin Cheng and Tianshu Huang and Shiqi Yang and Ri-Zhao Qiu and Xiaolong Wang}, year = {2025}, eprint = {2505.03738}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.03738}, } @misc{li2025bfm, title = {{BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning}}, author = {Yitang Li and Zhengyi Luo and Tonghe Zhang and Cunxi Dai and Anssi Kanervisto and Andrea Tirinzoni and Haoyang Weng and Kris Kitani and Mateusz Guzek and Ahmed Touati and Alessandro Lazaric and Matteo Pirotta and Guanya Shi}, year = {2025}, eprint = {2511.04131}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.04131}, } @misc{araujo2025retargeting, title = {{Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking}}, author = {Joao Pedro Araujo and Yanjie Ze and Pei Xu and Jiajun Wu and C. Karen Liu}, year = {2025}, eprint = {2510.02252}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.02252}, } @misc{yang2025omniretarget, title = {{OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction}}, author = {Lujie Yang and Xiaoyu Huang and Zhen Wu and Angjoo Kanazawa and Pieter Abbeel and Carmelo Sferrazza and C. Karen Liu and Rocky Duan and Guanya Shi}, year = {2025}, eprint = {2509.26633}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.26633}, } @misc{yin2025visualmimic, title = {{VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation}}, author = {Shaofeng Yin and Yanjie Ze and Hong-Xing Yu and C. Karen Liu and Jiajun Wu}, year = {2025}, eprint = {2509.20322}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.20322}, } @misc{zhao2025resmimic, title = {{ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning}}, author = {Siheng Zhao and Yanjie Ze and Yue Wang and C. Karen Liu and Pieter Abbeel and Guanya Shi and Rocky Duan}, year = {2025}, eprint = {2510.05070}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.05070}, } @misc{zhang2025falcon, title = {{FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation}}, author = {Yuanhang Zhang and Yifu Yuan and Prajwal Gurunath and Ishita Gupta and Shayegan Omidshafiei and Ali-akbar Agha-mohammadi and Marcell Vazquez-Chanlatte and Liam Pedersen and Tairan He and Guanya Shi}, year = {2025}, eprint = {2505.06776}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.06776}, } @misc{zhang2025hub, title = {{HuB: Learning Extreme Humanoid Balance}}, author = {Tong Zhang and Boyuan Zheng and Ruiqian Nai and Yingdong Hu and Yen-Jen Wang and Geng Chen and Fanqi Lin and Jiongye Li and Chuye Hong and Koushil Sreenath and Yang Gao}, year = {2025}, eprint = {2505.07294}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.07294}, } @misc{xie2025kungfubot, title = {{KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills}}, author = {Weiji Xie and Jinrui Han and Jiakun Zheng and Huanyu Li and Xinzhe Liu and Jiyuan Shi and Weinan Zhang and Chenjia Bai and Xuelong Li}, year = {2025}, eprint = {2506.12851}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.12851}, } @misc{wang2025beamdojo, title = {{BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds}}, author = {Huayi Wang and Zirui Wang and Junli Ren and Qingwei Ben and Tao Huang and Weinan Zhang and Jiangmiao Pang}, year = {2025}, eprint = {2502.10363}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.10363}, } @misc{ji2024exbody, title = {{ExBody2: Advanced Expressive Humanoid Whole-Body Control}}, author = {Mazeyu Ji and Xuanbin Peng and Fangchen Liu and Jialong Li and Ge Yang and Xuxin Cheng and Xiaolong Wang}, year = {2024}, eprint = {2412.13196}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.13196}, } @misc{kuang2025skillblender, title = {{SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending}}, author = {Yuxuan Kuang and Haoran Geng and Amine Elhafsi and Tan-Dzung Do and Pieter Abbeel and Jitendra Malik and Marco Pavone and Yue Wang}, year = {2025}, eprint = {2506.09366}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.09366}, } @misc{kalaria2025dreamcontrol, title = {{DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion}}, author = {Dvij Kalaria and Sudarshan S Harithas and Pushkal Katara and Sangkyung Kwak and Sarthak Bhagat and Shankar Sastry and Srinath Sridhar and Sai Vemprala and Ashish Kapoor and Jonathan Chung-Kuan Huang}, year = {2025}, eprint = {2509.14353}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.14353}, } @misc{wang2025physhsi, title = {{PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System}}, author = {Huayi Wang and Wentao Zhang and Runyi Yu and Tao Huang and Junli Ren and Feiyu Jia and Zirui Wang and Xiaojie Niu and Xiao Chen and Jiahe Chen and Qifeng Chen and Jingbo Wang and Jiangmiao Pang}, year = {2025}, eprint = {2510.11072}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.11072}, } @misc{weng2025hdmi, title = {{HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos}}, author = {Haoyang Weng and Yitang Li and Nikhil Sobanbabu and Zihan Wang and Zhengyi Luo and Tairan He and Deva Ramanan and Guanya Shi}, year = {2025}, eprint = {2509.16757}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.16757}, } @misc{jiang2024harmon, title = {{Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions}}, author = {Zhenyu Jiang and Yuqi Xie and Jinhan Li and Ye Yuan and Yifeng Zhu and Yuke Zhu}, year = {2024}, eprint = {2410.12773}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.12773}, } @misc{su2025hitter, title = {{HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning}}, author = {Zhi Su and Bike Zhang and Nima Rahmanian and Yuman Gao and Qiayuan Liao and Caitlin Regan and Koushil Sreenath and S. Shankar Sastry}, year = {2025}, eprint = {2508.21043}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.21043}, } @misc{lu2024mobile, title = {{Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control}}, author = {Chenhao Lu and Xuxin Cheng and Jialong Li and Shiqi Yang and Mazeyu Ji and Chengjing Yuan and Ge Yang and Sha Yi and Xiaolong Wang}, year = {2024}, eprint = {2412.07773}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.07773}, } @misc{zhuang2025embrace, title = {{Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions}}, author = {Ziwen Zhuang and Hang Zhao}, year = {2025}, eprint = {2502.01465}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.01465}, } @misc{zhang2024wococo, title = {{WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts}}, author = {Chong Zhang and Wenli Xiao and Tairan He and Guanya Shi}, year = {2024}, eprint = {2406.06005}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.06005}, } @misc{huang2025learning, title = {{Learning Humanoid Standing-up Control across Diverse Postures}}, author = {Tao Huang and Junli Ren and Huayi Wang and Zirui Wang and Qingwei Ben and Muning Wen and Xiao Chen and Jianan Li and Jiangmiao Pang}, year = {2025}, eprint = {2502.08378}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.08378}, } @misc{he2025learning, title = {{Learning Getting-Up Policies for Real-World Humanoid Robots}}, author = {Xialin He and Runpei Dong and Zixuan Chen and Saurabh Gupta}, year = {2025}, eprint = {2502.12152}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.12152}, } @misc{zhang2025unleashing, title = {{Unleashing Humanoid Reaching Potential via Real-world-Ready Skill Space}}, author = {Zhikai Zhang and Chao Chen and Han Xue and Jilong Wang and Sikai Liang and Yun Liu and Zongzhang Zhang and He Wang and Li Yi}, year = {2025}, eprint = {2505.10918}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.10918}, } @misc{zhuang2026deep, title = {{Deep Whole-body Parkour}}, author = {Ziwen Zhuang and Shaoting Zhu and Mengjie Zhao and Hang Zhao}, year = {2026}, eprint = {2601.07701}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2601.07701}, } @misc{zhu2026hiking, title = {{Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids}}, author = {Shaoting Zhu and Ziwen Zhuang and Mengjie Zhao and Kun-Ying Lee and Hang Zhao}, year = {2026}, eprint = {2601.07718}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2601.07718}, } @misc{wu2026perceptive, title = {{Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching}}, author = {Zhen Wu and Xiaoyu Huang and Lujie Yang and Yuanhang Zhang and Xi Chen and Pieter Abbeel and Rocky Duan and Angjoo Kanazawa and Carmelo Sferrazza and Guanya Shi and C. Karen Liu}, year = {2026}, eprint = {2602.15827}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.15827}, } @misc{wang2026omnixtreme, title = {{OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control}}, author = {Yunshen Wang and Shaohang Zhu and Peiyuan Zhi and Yuhan Li and Jiaxin Li and Yong-Lu Li and Yuchen Xiao and Xingxing Wang and Baoxiong Jia and Siyuan Huang}, year = {2026}, eprint = {2602.23843}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.23843}, } @misc{wang2026humanx, title = {{HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos}}, author = {Yinhuai Wang and Qihan Zhao and Yuen Fui Lau and Runyi Yu and Hok Wai Tsui and Qifeng Chen and Jingbo Wang and Jiangmiao Pang and Ping Tan}, year = {2026}, eprint = {2602.02473}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.02473}, } @misc{margolis2025softmimic, title = {{SoftMimic: Learning Compliant Whole-body Control from Examples}}, author = {Gabriel B. Margolis and Michelle Wang and Nolan Fey and Pulkit Agrawal}, year = {2025}, eprint = {2510.17792}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.17792}, } @misc{lu2025gentlehumanoid, title = {{GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interaction}}, author = {Qingzhou Lu and Yao Feng and Baiyu Shi and Michael Piseno and Zhenan Bao and C. Karen Liu}, year = {2025}, eprint = {2511.04679}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.04679}, } @misc{chen2025chip, title = {{CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation}}, author = {Sirui Chen and Zi-ang Cao and Zhengyi Luo and Fernando Castañeda and Chenran Li and Tingwu Wang and Ye Yuan and Linxi "Jim" Fan and C. Karen Liu and Yuke Zhu}, year = {2025}, eprint = {2512.14689}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.14689}, } @misc{sleiman2026zest, title = {{ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control}}, author = {Jean Pierre Sleiman and He Li and Alphonsus Adu-Bredu and Robin Deits and Arun Kumar and Kevin Bergamin and Mohak Bhardwaj and Scott Biddlestone and Nicola Burger and Matthew A. Estrada and Francesco Iacobelli and Twan Koolen and Alexander Lambert and Erica Lin and M. Eva Mungai and Zach Nobles and Shane Rozen-Levy and Yuyao Shi and Jiashun Wang and Jakob Welner and Fangzhou Yu and Mike Zhang and Alfred Rizzi and Jessica Hodgins and Sylvain Bertrand and Yeuhi Abe and Scott Kuindersma and Farbod Farshidian}, year = {2026}, eprint = {2602.00401}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.00401}, } @misc{bohlinger2024one, title = {{One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion}}, author = {Nico Bohlinger and Grzegorz Czechmanowski and Maciej Krupka and Piotr Kicki and Krzysztof Walas and Jan Peters and Davide Tateo}, year = {2024}, eprint = {2409.06366}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.06366}, } @misc{yuan2025survey, title = {{A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots}}, author = {Mingqi Yuan and Tao Yu and Wenqi Ge and Xiuyong Yao and Huijiang Wang and Jiayu Chen and Bo Li and Wei Zhang and Wenjun Zeng and Hua Chen and Xin Jin}, year = {2025}, eprint = {2506.20487}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.20487}, } @misc{gu2025humanoid, title = {{Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning}}, author = {Zhaoyuan Gu and Junheng Li and Wenlan Shen and Wenhao Yu and Zhaoming Xie and Stephen McCrory and Xianyi Cheng and Abdulaziz Shamsah and Robert Griffin and C. Karen Liu and Abderrahmane Kheddar and Xue Bin Peng and Yuke Zhu and Guanya Shi and Quan Nguyen and Gordon Cheng and Huijun Gao and Ye Zhao}, year = {2025}, eprint = {2501.02116}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2501.02116}, } @misc{hu2026perceptive, title = {{Perceptive Humanoid Motion from Simulation}}, author = {Siyuan Hu and Abulikemu Abuduweili and Yue Meng and Shipeng Liu and Quentin Leboutet and Chen Chen and Matthias Müller and Vladlen Koltun}, year = {2026}, eprint = {2611.06908}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.06908}, } @misc{zhao2026ctrl, title = {{Ctrl-F: Force as an Interface for Humanoid Loco-Manipulation}}, author = {Mengjie Zhao and Yuxin Chen and Yiyang Shao and Chuye Hong and Jiakang Chen and Koushil Sreenath and Masayoshi Tomizuka}, year = {2026}, eprint = {2611.05507}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05507}, } @misc{ding2025humanoid, title = {{Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration}}, author = {Pengxiang Ding and Jianfei Ma and Xinyang Tong and Binghong Zou and Xinxin Luo and Yiguo Fan and Ting Wang and Hongchao Lu and Panzhong Mo and Jinxin Liu and Yuefan Wang and Huaicheng Zhou and Wenshuo Feng and Jiacheng Liu and Siteng Huang and Donglin Wang}, year = {2025}, eprint = {2502.14795}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.14795}, } @misc{chen2025rhino, title = {{RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations}}, author = {Jingxiao Chen and Xinyao Li and Jiahang Cao and Zhengbang Zhu and Wentao Dong and Minghuan Liu and Ying Wen and Yong Yu and Liqing Zhang and Weinan Zhang}, year = {2025}, eprint = {2502.13134}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.13134}, } @misc{albaba2025nil, title = {{NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models}}, author = {Mert Albaba and Chenhao Li and Markos Diomataris and Omid Taheri and Andreas Krause and Michael Black}, year = {2025}, eprint = {2503.10626}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2503.10626}, } @misc{wang2023prompt, title = {{Prompt a Robot to Walk with Large Language Models}}, author = {Yen-Jen Wang and Bike Zhang and Jianyu Chen and Koushil Sreenath}, year = {2023}, eprint = {2309.09969}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.09969}, } @misc{wang2026counterfactual, title = {{Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation}}, author = {Zihan Wang and Zhen Wu and Pieter Abbeel and Rocky Duan and Jitendra Malik and Carmelo Sferrazza and C. Karen Liu and Guanya Shi and Angjoo Kanazawa}, year = {2026}, eprint = {2609.38172}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.38172}, } @misc{dong2026hero, title = {{HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping}}, author = {Runpei Dong and Ziyan Li and Arjun Gupta and Xialin He and Saurabh Gupta}, year = {2026}, eprint = {2602.16705}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.16705}, } @misc{girgin2026learning, title = {{Learning Contact Representation for Leg Odometry}}, author = {Emre Girgin and Cagri Kilic}, year = {2026}, eprint = {2606.05501}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.05501}, } @misc{maluleke2026social, title = {{Social Humanoid: Socially Responsive Human-Humanoid Interaction}}, author = {Vongani H. Maluleke and James Ni and Kie Horiuchi and Lea Wilken and Jiahui Lei and Evonne Ng and Roei Herzig and Jitendra Malik and Trevor Darrell and Angjoo Kanazawa}, year = {2026}, eprint = {2611.08407}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08407}, } @misc{lu2026hitch, title = {{HITCH: Teaching a Vision-Language Model to Operate a Humanoid through a Whole-Body Harness}}, author = {Qingzhou Lu and Chenxin Liu and Xinming Wang and Liu Cao and Yanjiang Guo and Mengdi Xu and Jianyu Chen}, year = {2026}, eprint = {2611.08039}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08039}, } @misc{shibata2026vlm, title = {{VLM-Guided Contact Retargeting and Generative Partner Modeling for Humanoid-Human Interaction}}, author = {Yuto Shibata and Kotaro Amaya and Kashu Yamazaki and Lalit Jayanti and Yoshimitsu Aoki and Mariko Isogawa and Katerina Fragkiadaki}, year = {2026}, eprint = {2610.28523}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28523}, } @misc{ye2026skillx, title = {{SkillX: Unified Multi-Skill Policy Learning for Humanoid Soccer}}, author = {Zhangchen Ye and Enxuan Ruan and Yifei Bao and Runhan Huang and Jiankun Yang and Jiakang Jin and Yixiao Huo and Pengyuan Wang and Yinan Han and Huaxing Huang and Wenhao Cui and Yiming Li and Xiaoyu Tian}, year = {2026}, eprint = {2609.06718}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.06718}, } @misc{sun2026solo, title = {{SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion}}, author = {Pihai Sun and Gang Han and Jingkai Sun and Jiahao Ma and Zeran Su and Zelin Tao and Peiran Liu and Shuai Shi and Wei Cui and Zifan Wang and Jialin Yu and Wen Zhao and Kangning Yin and Jiaxu Wang and Jiahang Cao and Lingfeng Zhang and Hao Cheng and Jian Tang and Qiang Zhang and Yijie Guo}, year = {2026}, eprint = {2608.26583}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.26583}, } @misc{kim2026humanoid, title = {{Humanoid Hanoi: Investigating Shared Whole-Body Control for Skill-Based Box Rearrangement}}, author = {Minku Kim and Kuan-Chia Chen and Aayam Shrestha and Li Fuxin and Stefan Lee and Alan Fern}, year = {2026}, eprint = {2602.13850}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.13850}, } @misc{li2026contactmimic, title = {{ContactMimic: Humanoid Object Interaction via Contact Control}}, author = {Xinyao Li and Xialin He and Runpei Dong and Saurabh Gupta}, year = {2026}, eprint = {2607.08742}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.08742}, } @misc{kim2026legs, title = {{LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World}}, author = {Hojune Kim and Timothy Chen and Jiankai Sun and Lars W. Osterberg and Qianzhong Chen and Ke Wang and Mac Schwager}, year = {2026}, eprint = {2606.01458}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.01458}, } @misc{xiong2026extremcontrol, title = {{ExtremControl: Low-Latency Humanoid Teleoperation with Scaled Velocity Feedforward}}, author = {Ziyan Xiong and Lixing Fang and Junyun Huang and Kashu Yamazaki and Hao Zhang and Chuang Gan}, year = {2026}, eprint = {2602.11321}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.11321}, } @misc{wang2026vlk, title = {{VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes}}, author = {Yen-Jen Wang and Jiaman Li and Sirui Chen and Takara E. Truong and Pei Xu and Pieter Abbeel and Rocky Duan and Koushil Sreenath and Angjoo Kanazawa and Carmelo Sferrazza and Guanya Shi and Karen Liu}, year = {2026}, eprint = {2606.30645}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.30645}, } @misc{lin2026humanoidmimicgen, title = {{HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning}}, author = {Kevin Lin and Ajay Mandlekar and Caelan Reed Garrett and Nikita Chernyadev and Yu Fang and Runyu Ding and Yuqi Xie and Justin Tran and Linxi Fan and Yuke Zhu}, year = {2026}, eprint = {2605.27724}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.27724}, } @misc{liu2026heft, title = {{HEFT: Heavy-Payload Full-size Humanoid Teleoperation with Privileged Motion Guidance and Windowed Payload Curriculum}}, author = {Chenxin Liu and Qingzhou Lu and Guangxiao Yang and Xuanyang Shi and Chenghan Yang and Yanjiang Guo and Jianyu Chen}, year = {2026}, eprint = {2607.02332}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.02332}, } @misc{morton2026constrained, title = {{Constrained Whole-Body Tracking for Humanoid Robots}}, author = {Daniel Morton and Pranit Mohnot and Marco Pavone}, year = {2026}, eprint = {2606.00374}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.00374}, } @misc{huang2026towards, title = {{Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking}}, author = {Tao Huang and Ruofei Liu and Xuchen Tang and Xinyin Zhang and Junli Ren and Huayi Wang and Feiyu Jia and Yukai Qi and Kangning Yin and Weishuai Zeng and Lipeng Chen and Xi Li and Ting Wu and Kailin Li and Ruoli Dai and Jingbo Wang and Lei Han and Jiangmiao Pang}, year = {2026}, eprint = {2608.20087}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.20087}, } @misc{xie2026textop, title = {{TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control}}, author = {Weiji Xie and Jiakun Zheng and Jinrui Han and Jiyuan Shi and Weinan Zhang and Chenjia Bai and Xuelong Li}, year = {2026}, eprint = {2602.07439}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.07439}, } @misc{cao2026texedo, title = {{TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation}}, author = {Jianuo Cao and Yuxin Chen and Yuzhen Song and Masayoshi Tomizuka and Chenran Li and Thomas Tian}, year = {2026}, eprint = {2606.22998}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22998}, } @misc{wu2026adapt, title = {{ADAPT: Agile Diffusion Action Priors for Robust and Steerable Online Text-Driven Humanoid Control}}, author = {Yan Wu and Chenhao Li and Kaifeng Zhao and Gen Li and Marco Hutter and Siyu Tang}, year = {2026}, eprint = {2609.00677}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.00677}, } @misc{xie2026fada, title = {{FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control}}, author = {Angchen Xie and Nikhil Sobanbabu and Ishayu Shikhare and Alan Wang and Max Simchowitz and Guanya Shi}, year = {2026}, eprint = {2606.28476}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.28476}, } @misc{hu2026eye, title = {{Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE}}, author = {Yuhang Hu and Junlin Lyu and Yuan Fang and Xiaoying Shen and Lechen Zhang and Jiong Lin and Judah Goldfeder and Steven Tian and Hod Lipson}, year = {2026}, eprint = {2610.19635}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.19635}, } @misc{taouil2026motiondisco, title = {{MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation}}, author = {Ilyass Taouil and Michal Ciebelski and Shafeef Omar and Haizhou Zhao and Angela Dai and Aaron M. Johnson and Majid Khadiv}, year = {2026}, eprint = {2606.06139}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.06139}, } @misc{yang2026zerowbc, title = {{ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data}}, author = {Haoran Yang and Jiacheng Bao and Yucheng Xin and Haoming Song and Yuyang Tian and Bin Zhao and Dong Wang and Xuelong Li}, year = {2026}, eprint = {2603.09170}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.09170}, } @misc{hu2026tac, title = {{TAC-LOCO: Unified Whole-Body Control for Quadrupedal TACtile-Informed LOCO-Manipulation}}, author = {Muqun Hu and Yuhao Zhou and Kabir Ray Malik and Chi Lin and Won Suk Lee and Yu She and Yan Gu}, year = {2026}, eprint = {2607.10132}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.10132}, } @misc{lin2026pro, title = {{Pro-HOI: Perceptive Root-guided Humanoid-Object Interaction}}, author = {Yuhang Lin and Jiyuan Shi and Dewei Wang and Jipeng Kong and Yong Liu and Chenjia Bai and Xuelong Li}, year = {2026}, eprint = {2603.01126}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.01126}, } @misc{yu2026omnicontact, title = {{OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation}}, author = {Runyi Yu and Xiaoyi Lin and Ji Ma and Yinhuai Wang and Koukou Luo and Jiahao Ji and Huayi Wang and Wenjia Wang and Runhan Zhang and Ping Tan and Ting Wu and Ruoli Dai and Qifeng Chen and Lei Han}, year = {2026}, eprint = {2606.26201}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26201}, } @misc{cui2026humanoid, title = {{Humanoid Badminton: Learning Dynamic Racket Skills from Limited Human Motion Data}}, author = {Jingzhi Cui and Zhexiong Wang and Bangjie Xu and Pengyu Zhao and Youyuan Li and Zhi Su and Peng Ren and Mengdi Xu and Chao Yu and Yi Wu and Luyang Wang and Zhongyu Li}, year = {2026}, eprint = {2609.31840}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.31840}, } @misc{zhang2026x, title = {{X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control}}, author = {Juntong Zhang and Chun Gu and Li Zhang}, year = {2026}, eprint = {2609.15213}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.15213}, } @misc{ren2026closing, title = {{Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation}}, author = {Peng Ren and Haoyang Ge and Jiang Zhao and Cong Huang and Yukun Shi and Pei Chi and Kai Chen}, year = {2026}, eprint = {2607.18016}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.18016}, } @misc{xiong2026swingbot, title = {{SwingBot: Learning Whole-Body Brachiation for Humanoid Robots}}, author = {Yujie Xiong and Peng Zhai and Taixian Hou and Quancheng Qian and Cunwang Liu and Kangmai Hu and Long Yang and Zhiyan Dong and Lihua Zhang}, year = {2026}, eprint = {2609.10283}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.10283}, } @misc{chen2026s, title = {{S2M-Trek: From Single to Multi-Sphere Transport via Per-Frame Deep Sets on a Wheel-Legged Robot}}, author = {Zong Chen and Xuebin Li and Jinpeng Xiao and Shaoyang Li and Ben Liu and Min Li and Zhouping Yin and Yiqun Li}, year = {2026}, eprint = {2606.01332}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.01332}, } @misc{zhong2026ft, title = {{FT-WBC: Learning Fault-Tolerant Whole-Body Control for Legged Loco-Manipulation}}, author = {Yudong Zhong and Pengfei Mai and Sikai Guo and Jiahang Cao and Zhihai Bi and Qiuyue Liu and Ziyan Feng and Jinni Zhou and Jun Ma}, year = {2026}, eprint = {2606.24466}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.24466}, } @misc{wang2026general, title = {{General Humanoid Whole-Body Control via Pretraining and Fast Adaptation}}, author = {Zepeng Wang and Jiangxing Wang and Shiqing Yao and Yu Zhang and Ziluo Ding and Ming Yang and Yuxuan Wang and Haobin Jiang and Chao Ma and Xiaochuan Shi and Zongqing Lu}, year = {2026}, eprint = {2602.11929}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.11929}, } @misc{shao2026playing, title = {{Playing Soccer Like Humans Do: Learning Versatile and Agile Humanoid Soccer via Latent Motion Priors}}, author = {Haoyu Shao and Yunshen Wang and Jingze Zhang and Shaohang Zhu and Yong-Lu Li and Tianzhu Zhang and Baoxiong Jia and Siyuan Huang}, year = {2026}, eprint = {2611.06564}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.06564}, } @misc{liu2026unleashing, title = {{Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors}}, author = {Youzhi Liu and Li Gao and Yifei Qian and Liu Liu and Yang Cai and Wenbin Tang}, year = {2026}, eprint = {2606.28237}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.28237}, } @misc{mishra2026morfic, title = {{MorFiC: Fixing Value Miscalibration for Zero-Shot Quadruped Transfer}}, author = {Prakhar Mishra and Amir Hossain Raj and Xuesu Xiao and Dinesh Manocha}, year = {2026}, eprint = {2603.14554}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.14554}, } @misc{danesh2026morphology, title = {{Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotion}}, author = {Mohamad H. Danesh and Chenhao Li and Amin Abyaneh and Anas Houssaini and Kirsty Ellis and Glen Berseth and Marco Hutter and Hsiu-Chin Lin}, year = {2026}, eprint = {2604.08780}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.08780}, } @misc{kordos2026locomposition, title = {{LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors}}, author = {Loukas Kordos and Leonard T. Franz and Simon Rappenecker and Oliver Hausdoerfer and Angela P. Schoellig and Pavel Kolev and Georg Martius}, year = {2026}, eprint = {2606.15896}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15896}, } @misc{chen2026physics, title = {{Physics-Guided Biomechanical Gait Adaptation for Humanoid Locomotion on Extreme Sloped Terrains}}, author = {Xuanyu Chen and Mohan Liu and Dengchen Mei and Zhihao Gu and Haitian Zhang and Kaimin Mao and Haiyue Zhu and Shijun Yan and Lin Wang}, year = {2026}, eprint = {2607.07830}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.07830}, } @misc{zhang2026rpl, title = {{RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains}}, author = {Yuanhang Zhang and Younggyo Seo and Juyue Chen and Yifu Yuan and Koushil Sreenath and Pieter Abbeel and Carmelo Sferrazza and Karen Liu and Rocky Duan and Guanya Shi}, year = {2026}, eprint = {2602.03002}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.03002}, } @misc{lee2026echo, title = {{Echo in the Steps: Learning Perceptive Humanoid Parkour with Gated Memory}}, author = {Ming-Ju Lee and Zizhuo Wang and Shaoting Zhu and Haozhe Lou and Hang Zhao and Yiming Li}, year = {2026}, eprint = {2609.28960}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.28960}, } @misc{zhang2026meshmimic, title = {{MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction}}, author = {Qiang Zhang and Jiahao Ma and Peiran Liu and Shuai Shi and Zeran Su and Zifan Wang and Jingkai Sun and Wei Cui and Jialin Yu and Gang Han and Wen Zhao and Pihai Sun and Kangning Yin and Jiaxu Wang and Jiahang Cao and Lingfeng Zhang and Hao Cheng and Xiaoshuai Hao and Yiding Ji and Junwei Liang and Jian Tang and Renjing Xu and Yijie Guo}, year = {2026}, eprint = {2602.15733}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.15733}, } @misc{wang2026perceptive, title = {{Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain}}, author = {Zifan Wang and Yizhao Li and Teli Ma and Qiang Zhang and Yudong Fan and Hao Xu and Shuo Yang and Junwei Liang}, year = {2026}, eprint = {2606.08059}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08059}, } @misc{crismariu2026march, title = {{MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds}}, author = {Codrin Crismariu and Ryan K. Cosner}, year = {2026}, eprint = {2606.10288}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.10288}, } @misc{chen2026cap, title = {{CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising}}, author = {Hongjin Chen and Zijun Xu and Shihao Ma and Yi Zhao and Xilai Liu and Ke Ma and Wei Zhang and Chunyang Xie and Pengfei Li and Jieru Zhao and Wenchao Ding}, year = {2026}, eprint = {2609.11553}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.11553}, } @misc{li2026robodreamer, title = {{RoboDreamer: Anticipatory Humanoid Locomotion with Predictive State-Space Models}}, author = {Zhe Li and Yangyang Wei and Xichen Yuan and Zhenzhe Zhang and Weihao Yuan and Shanghang Zhang and Jianfei Yang}, year = {2026}, eprint = {2609.07096}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.07096}, } @misc{lyu2026adapt, title = {{ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion}}, author = {Bofan Lyu and Jindou Jia and Kuangji Zuo and Yanshuo Lu and Shijia Han and Gen Li and Boyu Ma and Jingliang Li and Geng Li and Jianfei Yang}, year = {2026}, eprint = {2606.16542}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16542}, } @misc{aurand2026walk, title = {{Walk Like This: Stylized Locomotion for Physics-Based Characters through Example-Driven Diffusion}}, author = {Joshua Aurand and Agon Serifi and Sammy Christen and Ruben Grandia and Espen Knoop and Marco Hutter and Moritz Bächer}, year = {2026}, eprint = {2610.18147}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18147}, } @misc{chakraborty2026actuator, title = {{Actuator Dynamics Curricula for Narrow-Viability Tasks in Legged Robot Learning}}, author = {Kousheek Chakraborty and Chandan K. Rajendra and Ayham Alharbat and Abeje Y. Mersha}, year = {2026}, eprint = {2609.09492}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.09492}, } @misc{liu2026trajectory, title = {{Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain}}, author = {Rocky Liu and Tengyu Liu and Baoxiong Jia and Fangwei Zhong and Xinyi Tong and Hongzhao Xie and Siyuan Huang}, year = {2026}, eprint = {2608.16164}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2608.16164}, } @misc{tsuruhara2026shoes, title = {{SHOES: Sim-to-real Hardware-adaptation via On-policy Expansion of Skills for Legged Robots}}, author = {Kota Tsuruhara and Tsung-Yuan Chen and Kento Kawaharazuka}, year = {2026}, eprint = {2610.16457}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16457}, } @misc{tommaselli2026mind, title = {{Mind the Phase: Effective Rank and Representation Health in Legged Locomotion}}, author = {Felipe Tommaselli and Ricardo V. Godoy and Thiago H. Segreto and Juliano D. Negri and Marcelo Becker}, year = {2026}, eprint = {2609.06958}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.06958}, } @misc{huang2026push, title = {{Push the Limit: Learning High-Speed Sprinting and Aggressive Cornering on a Full-Scale Humanoid}}, author = {Huaxing Huang and Ruidong Li and Jinchao Han and Ziyang Dong and Wenhao Cui}, year = {2026}, eprint = {2610.14840}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.14840}, } @misc{wei2026dkwbc, title = {{DKWBC: Decoupling Motion Tracking and Balancing for Humanoid Whole-Body Control}}, author = {Dingkun Wei and Zehong Shen and Huaijin Pi and Xueyang Wang and Xing Zhu and Hujun Bao and Yujun Shen and Xiaowei Zhou}, year = {2026}, eprint = {2611.09605}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09605}, } @misc{wu2026sugarv, title = {{SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References}}, author = {Tianshu Wu and Tianxiang Gui and Yue Chen and Tingxu Liu and Ziye Peng and Guangjie Yang and Xiangqi Kong and Ye Shi and Jingya Wang and Hao Dong}, year = {2026}, eprint = {2611.09266}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09266}, } @misc{ha2018world, title = {{World Models}}, author = {David Ha and Jürgen Schmidhuber}, year = {2018}, eprint = {1803.10122}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1803.10122}, } @misc{hafner2023mastering, title = {{Mastering Diverse Domains through World Models}}, author = {Danijar Hafner and Jurgis Pasukonis and Jimmy Ba and Timothy Lillicrap}, year = {2023}, eprint = {2301.04104}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2301.04104}, } @misc{wu2022daydreamer, title = {{DayDreamer: World Models for Physical Robot Learning}}, author = {Philipp Wu and Alejandro Escontrela and Danijar Hafner and Ken Goldberg and Pieter Abbeel}, year = {2022}, eprint = {2206.14176}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2206.14176}, } @misc{yang2023learning, title = {{Learning Interactive Real-World Simulators}}, author = {Sherry Yang and Yilun Du and Kamyar Ghasemipour and Jonathan Tompson and Leslie Kaelbling and Dale Schuurmans and Pieter Abbeel}, year = {2023}, eprint = {2310.06114}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2310.06114}, } @misc{bruce2024genie, title = {{Genie: Generative Interactive Environments}}, author = {Jake Bruce and Michael Dennis and Ashley Edwards and Jack Parker-Holder and Yuge Shi and Edward Hughes and Matthew Lai and Aditi Mavalankar and Richie Steigerwald and Chris Apps and Yusuf Aytar and Sarah Bechtle and Feryal Behbahani and Stephanie Chan and Nicolas Heess and Lucy Gonzalez and Simon Osindero and Sherjil Ozair and Scott Reed and Jingwei Zhang and Konrad Zolna and Jeff Clune and Nando de Freitas and Satinder Singh and Tim Rocktäschel}, year = {2024}, eprint = {2402.15391}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2402.15391}, } @misc{nvidia2025cosmos, title = {{Cosmos World Foundation Model Platform for Physical AI}}, author = {NVIDIA and : and Niket Agarwal and Arslan Ali and Maciej Bala and Yogesh Balaji and Erik Barker and Tiffany Cai and Prithvijit Chattopadhyay and Yongxin Chen and Yin Cui and Yifan Ding and Daniel Dworakowski and Jiaojiao Fan and Michele Fenzi and Francesco Ferroni and Sanja Fidler and Dieter Fox and Songwei Ge and Yunhao Ge and Jinwei Gu and Siddharth Gururani and Ethan He and Jiahui Huang and Jacob Huffman and Pooya Jannaty and Jingyi Jin and Seung Wook Kim and Gergely Klár and Grace Lam and Shiyi Lan and Laura Leal-Taixe and Anqi Li and Zhaoshuo Li and Chen-Hsuan Lin and Tsung-Yi Lin and Huan Ling and Ming-Yu Liu and Xian Liu and Alice Luo and Qianli Ma and Hanzi Mao and Kaichun Mo and Arsalan Mousavian and Seungjun Nah and Sriharsha Niverty and David Page and Despoina Paschalidou and Zeeshan Patel and Lindsey Pavao and others}, year = {2025}, eprint = {2501.03575}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2501.03575}, } @misc{assran2025v, title = {{V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning}}, author = {Mido Assran and Adrien Bardes and David Fan and Quentin Garrido and Russell Howes and Mojtaba and Komeili and Matthew Muckley and Ammar Rizvi and Claire Roberts and Koustuv Sinha and Artem Zholus and Sergio Arnaud and Abha Gejji and Ada Martin and Francois Robert Hogan and Daniel Dugas and Piotr Bojanowski and Vasil Khalidov and Patrick Labatut and Francisco Massa and Marc Szafraniec and Kapil Krishnakumar and Yong Li and Xiaodong Ma and Sarath Chandar and Franziska Meier and Yann LeCun and Michael Rabbat and Nicolas Ballas}, year = {2025}, eprint = {2506.09985}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2506.09985}, } @misc{hafner2019dream, title = {{Dream to Control: Learning Behaviors by Latent Imagination}}, author = {Danijar Hafner and Timothy Lillicrap and Jimmy Ba and Mohammad Norouzi}, year = {2019}, eprint = {1912.01603}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1912.01603}, } @misc{hansen2023td, title = {{TD-MPC2: Scalable, Robust World Models for Continuous Control}}, author = {Nicklas Hansen and Hao Su and Xiaolong Wang}, year = {2023}, eprint = {2310.16828}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2310.16828}, } @misc{zhou2024dino, title = {{DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning}}, author = {Gaoyue Zhou and Hengkai Pan and Yann LeCun and Lerrel Pinto}, year = {2024}, eprint = {2411.04983}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2411.04983}, } @misc{liu2026ropedia, title = {{Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience}}, author = {Tianqi Liu and Hanfei Zhao and Qifeng Liang and Hui En Pang and Jiarui Xu and Sayang Mu and Penghao Qiu and YingSheng Zhang and Jun Wang and Ziang Cao and Mingze Sun and Yukang Cao and Fangzhou Hong and Zhaoxi Chen and Ziwei Liu}, year = {2026}, eprint = {2610.26855}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.26855}, } @misc{mei2026robotic, title = {{Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions}}, author = {Zhiting Mei and Tenny Yin and Ola Shorinwa and Apurva Badithela and Zhonghe Zheng and Joseph Bruno and Madison Bland and Lihan Zha and Asher Hancock and Jaime Fernández Fisac and Philip Dames and Anirudha Majumdar}, year = {2026}, eprint = {2601.07823}, archivePrefix = {arXiv}, primaryClass = {eess.SY}, url = {https://arxiv.org/abs/2601.07823}, } @misc{hafner2018learning, title = {{Learning Latent Dynamics for Planning from Pixels}}, author = {Danijar Hafner and Timothy Lillicrap and Ian Fischer and Ruben Villegas and David Ha and Honglak Lee and James Davidson}, year = {2018}, eprint = {1811.04551}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1811.04551}, } @misc{hafner2020mastering, title = {{Mastering Atari with Discrete World Models}}, author = {Danijar Hafner and Timothy Lillicrap and Mohammad Norouzi and Jimmy Ba}, year = {2020}, eprint = {2010.02193}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2010.02193}, } @misc{micheli2022transformers, title = {{Transformers are Sample-Efficient World Models}}, author = {Vincent Micheli and Eloi Alonso and François Fleuret}, year = {2022}, eprint = {2209.00588}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2209.00588}, } @misc{du2023learning, title = {{Learning Universal Policies via Text-Guided Video Generation}}, author = {Yilun Du and Mengjiao Yang and Bo Dai and Hanjun Dai and Ofir Nachum and Joshua B. Tenenbaum and Dale Schuurmans and Pieter Abbeel}, year = {2023}, eprint = {2302.00111}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2302.00111}, } @misc{hansen2022temporal, title = {{Temporal Difference Learning for Model Predictive Control}}, author = {Nicklas Hansen and Xiaolong Wang and Hao Su}, year = {2022}, eprint = {2203.04955}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2203.04955}, } @misc{ding2026cw, title = {{CW-WAM: A Structured Contact-Wrench World Action Model for Force-Sensitive Manipulation}}, author = {Houzhu Ding and Xinda Qi and Luqi Wang and Ming Yang}, year = {2026}, eprint = {2610.30117}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30117}, } @misc{wu2023unleashing, title = {{Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation}}, author = {Hongtao Wu and Ya Jing and Chilam Cheang and Guangzeng Chen and Jiafeng Xu and Xinghang Li and Minghuan Liu and Hang Li and Tao Kong}, year = {2023}, eprint = {2312.13139}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.13139}, } @misc{hu2024video, title = {{Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations}}, author = {Yucheng Hu and Yanjiang Guo and Pengchao Wang and Xiaoyu Chen and Yen-Jen Wang and Jianke Zhang and Koushil Sreenath and Chaochao Lu and Jianyu Chen}, year = {2024}, eprint = {2412.14803}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2412.14803}, } @misc{li2025unified, title = {{Unified Video Action Model}}, author = {Shuang Li and Yihuai Gao and Dorsa Sadigh and Shuran Song}, year = {2025}, eprint = {2503.00200}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.00200}, } @misc{cen2025worldvla, title = {{WorldVLA: Towards Autoregressive Action World Model}}, author = {Jun Cen and Chaohui Yu and Hangjie Yuan and Yuming Jiang and Siteng Huang and Jiayan Guo and Xin Li and Yibing Song and Hao Luo and Fan Wang and Deli Zhao and Hao Chen}, year = {2025}, eprint = {2506.21539}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.21539}, } @misc{liao2025genie, title = {{Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation}}, author = {Yue Liao and Pengfei Zhou and Siyuan Huang and Donglin Yang and Shengcong Chen and Yuxin Jiang and Yue Hu and Jingbin Cai and Si Liu and Jianlan Luo and Liliang Chen and Shuicheng Yan and Maoqing Yao and Guanghui Ren}, year = {2025}, eprint = {2508.05635}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.05635}, } @misc{tian2026uniflowwam, title = {{UniFlowWAM: A Unified World-Action Model with Visual Semantics and 4D Geometry}}, author = {Jialin Tian and Zhuofan Li and Xinkai Wang and Bokai Lin and Chenyi Wang and Xinyu Zhan and Cewu Lu and Lixin Yang}, year = {2026}, eprint = {2610.30991}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30991}, } @misc{sidorov2026greenwam, title = {{GreenWAM: A World Foundation Model for Robotics}}, author = {Gennady Sidorov and Valerii Kornilov and Denis Grankin and Polina Fedotova and Aleksey Postnikov}, year = {2026}, eprint = {2610.18774}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18774}, } @misc{jang2026self, title = {{Self-Distilling Future Video Representations for World Action Models}}, author = {Huiwon Jang and Suhyeok Jang and Hyeonmo Kang and Seungku Kim and Jinwoo Shin and Sihyun Yu}, year = {2026}, eprint = {2610.30320}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30320}, } @misc{liu2026agentic, title = {{Agentic World Action Models}}, author = {Zhuoyang Liu and Dantong Niu and Botong Zhang and Boning Shao and Jing Wang and Ruijie Zheng and Yuvan Sharma and Runyu Lu and Jiaming Liu and Renrui Zhang and Roei Herzig and Yutong Bai and Ken Goldberg and Danfei Xu and Yuke Zhu and Guanzhi Wang and Linxi "Jim" Fan and Trevor Darrell}, year = {2026}, eprint = {2610.30136}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30136}, } @misc{lv2026skeleton, title = {{Skeleton-Grounded Latent Action Model for Robot World Models}}, author = {Qi Lv and Jiayi Lin and Yuxin Jiang and Jianzong Wang and Xiang Deng and Mike Shou Zheng}, year = {2026}, eprint = {2610.31474}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31474}, } @misc{zhu2026rynnunify, title = {{RynnUnify: Towards Unified Embodied Brain}}, author = {Minghao Zhu and Bohan Hou and Kun Xiang and Zixuan Wang and Yinzhou Tang and Yifei Yang and Zhikai Wang and Tianyi Zhang and Kehan Li and Haoyu Zhao and Siteng Huang and Leigang Qu and Sicong Leng and Dongchi Huang and Mingxiu Chen and Shijian Lu and Yue Wang and Xiaodan Liang and Zhenyu Zeng and Deli Zhao and Chengju Liu and Jianfei Yang and Xin Li}, year = {2026}, eprint = {2610.32965}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32965}, } @misc{jang2025dreamgen, title = {{DreamGen: Unlocking Generalization in Robot Learning through Video World Models}}, author = {Joel Jang and Seonghyeon Ye and Zongyu Lin and Jiannan Xiang and Johan Bjorck and Yu Fang and Fengyuan Hu and Spencer Huang and Kaushil Kundalia and Yen-Chen Lin and Loic Magne and Ajay Mandlekar and Avnish Narayan and You Liang Tan and Guanzhi Wang and Jing Wang and Qi Wang and Yinzhen Xu and Xiaohui Zeng and Kaiyuan Zheng and Ruijie Zheng and Ming-Yu Liu and Luke Zettlemoyer and Dieter Fox and Jan Kautz and Scott Reed and Yuke Zhu and Linxi Fan}, year = {2025}, eprint = {2505.12705}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.12705}, } @misc{xing2026physical, title = {{Physical Canvas: A Vision Tactile World Model For Robot Policy Evaluation And Learning}}, author = {Zebin Xing and Yuhang Zheng and Yupeng Zheng and Yichen Zhang and Zichen Li and Shangqing Zhou and Yujie Zang and Yuchen Liu and Zhongpu Xia and Haoran Li and Qichao Zhang}, year = {2026}, eprint = {2610.28613}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28613}, } @misc{zou2026pica, title = {{PICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models}}, author = {Yude Zou and Yifei Yao and Guanbo Jiao and Jianming Ma and Guanjie Zheng and Xing Gao}, year = {2026}, eprint = {2610.26813}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.26813}, } @misc{zhang2026oswam, title = {{OSWAM: An Effective World Action Model with One-Step Action Generation}}, author = {Guowen Zhang and Liyi Chen and Xu Hu and Pengfei Wang and Jingfan Chen and Chenhang He and Lei Zhang}, year = {2026}, eprint = {2610.35850}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.35850}, } @misc{scardecchia2026video, title = {{Video World Models Need Predictable Latents}}, author = {Mattia Scardecchia and Sherry Yang}, year = {2026}, eprint = {2610.34663}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2610.34663}, } @misc{lee2026dexplicit, title = {{DeXplicit: Making Physical State Explicit in Dexterous Manipulation World Models}}, author = {Adam Lee and Mutian Xu and Yukang Cao and Shulin Tian and Ziwei Liu}, year = {2026}, eprint = {2610.30781}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.30781}, } @misc{bateman2026training, title = {{Training Controllable World Models via Action Influence Maximization}}, author = {Samuel M. Bateman and Tenny Yin and Chongyi Zheng and Lei Huang and Brian Wang and Benjamin Eysenbach and Jaime Fernández Fisac and Dhruv Shah}, year = {2026}, eprint = {2610.27387}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27387}, } @misc{geng2026trajwam, title = {{TrajWAM: An Efficient Trajectory-Guided World Action Model for Dynamic Robotic Manipulation}}, author = {Haohan Geng and Sha Zhang and Weishuo Sun and Guanting Ye and Wenhao Yu and Yuang Xie and Qicheng Zeng and Peng Ye and Jiajun Deng and Jianmin Ji}, year = {2026}, eprint = {2610.25763}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25763}, } @misc{liu2026gawm, title = {{GAWM: A Compact Latent World-Action Model for Multi-Task Robot Manipulation}}, author = {Yang Liu and Xiaoli Liu and Liuzhao Li and Yuduo Song and Muyuan Liu and Xiang Gao}, year = {2026}, eprint = {2610.37091}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37091}, } @misc{collins2026tapestry, title = {{TAPESTRY: A Single Backbone for Video Generation and Robot Control}}, author = {Jeremy A. Collins and Seungjae Lee and Rachanon Wachakorn and Krishnan Srinivasan and Animesh Garg and Vitor Campagnolo Guizilini and Paarth Shah}, year = {2026}, eprint = {2610.36823}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36823}, } @misc{zhao2026rynnworld, title = {{RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions}}, author = {Haoyu Zhao and Yinzhou Tang and Zixuan Wang and Minghao Zhu and Dongchi Huang and Xingyue Zhao and Qin Zhao and Kehan Li and Siteng Huang and Xin Li and Zhenyu Zeng and Mingxiu Chen and Deli Zhao and Zhongyu Li}, year = {2026}, eprint = {2610.36791}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36791}, } @misc{luo2026rollback, title = {{Rollback: Experience Backtracking in World Models for Policy Improvement}}, author = {Jiayi Luo and Yang Zhang and Liliang Chen and Nan Wang and Chen Gao and Boxiang Qiu and Zhuoxuan Li and Baorui Peng and Chuankang Li and Yuxiang Yan and Si Liu and Qingyun Sun and Shuicheng Yan and Maoqing Yao and Jianxin Li and Guanghui Ren}, year = {2026}, eprint = {2610.36068}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36068}, } @misc{hu2026trace, title = {{Trace-WAM: Learning to Act via 3D Motion Prediction for World Action Models}}, author = {Xu Hu and Changjie Wu and Linzhe Shi and Hang Zhang and Chen Yang and Lingjun Zhang and Guowen Zhang and Mu Xu and Junran Peng and Qing Li and Zhaoxiang Zhang}, year = {2026}, eprint = {2610.36840}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36840}, } @misc{kim2026adapting, title = {{Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction}}, author = {Taeyoung Kim and Junyoung Sung and Heeseung Kwon and Minseop Kim and Jinwoo Shin}, year = {2026}, eprint = {2610.36624}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.36624}, } @misc{mittal2026calibrated, title = {{Calibrated for Which Policy? Conformal Uncertainty for Fixed World Models Under Intervention}}, author = {Ayush Mittal and Dhruv Gupta}, year = {2026}, eprint = {2610.35877}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2610.35877}, } @misc{yoo2026phystrace, title = {{PhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models}}, author = {Taekoan Yoo and Wonkyung Jung and Kyunghun Kim and Kyeongbo Kong}, year = {2026}, eprint = {2610.31429}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2610.31429}, } @misc{chen2026lawam, title = {{LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies}}, author = {Jialei Chen and Kai Wang and Kang Chen and Shuaihang Chen and Feng Gao and Wenhao Tang and Zhiyuan Li and Weilin Liu and Zhuyu Yao and Boxun Li and Yuanbo Xu and Chao Yu}, year = {2026}, eprint = {2606.15768}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15768}, } @misc{lu2026worldflow, title = {{WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining}}, author = {Yuhao Lu and Jiongxu Chen and Hexiang Wei and Jiajin Wu and Juelin Li and Mingjian Liang and Fan Yang and Zhuowei Liang and Zihao Liu and Zhennan Wang and Sheng Wang and Lin Shao}, year = {2026}, eprint = {2610.39278}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.39278}, } @misc{zhou2026hierarchical, title = {{Hierarchical World Models with Implicit Dynamics}}, author = {Gaoyue Zhou and Yvonne Wu and Zichen Jeff Cui and Nicolas Ballas and Mido Assran and Lerrel Pinto and Yann LeCun}, year = {2026}, eprint = {2610.42146}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.42146}, } @misc{cen2026worldbridge, title = {{WorldBridge: Bridging Video and Action for Task Generalization in World Action Models}}, author = {Jun Cen and Yubo Guo and Hao Li and Liangkai Li and Yaoxu Lyu and Meng Wei and Zeqi Xiao and Sizhe Yang and Yuqiang Yang and Yifan Ye and Shanghang Zhang and Duo Zheng}, year = {2026}, eprint = {2610.40748}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40748}, } @misc{ye2026world, title = {{World Action Models are Zero-shot Policies}}, author = {Seonghyeon Ye and Yunhao Ge and Kaiyuan Zheng and Shenyuan Gao and Sihyun Yu and George Kurian and Suneel Indupuru and You Liang Tan and Chuning Zhu and Jiannan Xiang and Ayaan Malik and Kyungmin Lee and William Liang and Nadun Ranawaka and Jiasheng Gu and Yinzhen Xu and Guanzhi Wang and Fengyuan Hu and Avnish Narayan and Johan Bjorck and Jing Wang and Gwanghyun Kim and Dantong Niu and Ruijie Zheng and Yuqi Xie and Jimmy Wu and Qi Wang and Ryan Julian and Danfei Xu and Yilun Du and Yevgen Chebotar and Scott Reed and Jan Kautz and Yuke Zhu and Linxi "Jim" Fan and Joel Jang}, year = {2026}, eprint = {2602.15922}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.15922}, } @misc{song2026chunk, title = {{Chunk-wise Model-based Policy Optimization}}, author = {Weixi Song and Donglin Wang and Yong-Lu Li}, year = {2026}, eprint = {2610.14564}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.14564}, } @misc{rathbun2026targeting, title = {{Targeting World Models to Compromise Robot Learning Pipelines}}, author = {Ethan Rathbun and Ahmed Agha and Saaduddin Mahmud and Christopher Amato and Alina Oprea and Eugene Bagdasarian}, year = {2026}, eprint = {2606.09499}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.09499}, } @misc{feng2026seeing, title = {{Seeing and Imagining as One: Unified Video Generation and 4D Perception for Embodied World Modeling}}, author = {Haitang Feng and Zhuoman Liu and Zhennan Wang and Sheng Wang and Juelin Li and Chengzhi Zhao and Hexiang Wei and Lin Shao}, year = {2026}, eprint = {2610.39232}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.39232}, } @misc{nie2026opennwm, title = {{OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining}}, author = {Dujun Nie and Ruiqi Song and Zixuan Wang and Hanqing Wang and Yifan Han and Baiyong Ding and Wenzhao Zheng and Hangbin Wu and Long Chen}, year = {2026}, eprint = {2611.01844}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01844}, } @misc{pandya2026pico, title = {{pico-WAM: Evaluating Counterfactual Prediction and Planning Error in a Compact World Action Model}}, author = {Keivalya Pandya}, year = {2026}, eprint = {2611.01039}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01039}, } @misc{zhu2026xiaomi, title = {{Xiaomi Auto World Model 2.0: Causal World Models for Real-World Driving and Embodied Intelligence}}, author = {Zhenxin Zhu and Zhijian Huang and Cheng Chi and Yuru Wang and Jianhua Wu and Jiayi Guan and Yonggang Li and Mingfei Tu and JiaKui Hu and Tao Xu and Xianqi Wang and Hao Li and Yuechuan Pu and Qizeng Jia and Ruiling Yang and Hongxiao Yu and Xuhan Sheng and Jian Mao and Ruiqiang Zhang and Yu Zhu and Guang Chen and Hangjun Ye and Bing Wang}, year = {2026}, eprint = {2611.01677}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2611.01677}, } @misc{shen2026world, title = {{World Action Models: A Survey}}, author = {Qiuhong Shen and Shihua Zhang and Yue Liao and Qi Li and Zhenxiong Tan and Shizun Wang and Shuicheng Yan and Xinchao Wang}, year = {2026}, eprint = {2606.20781}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.20781}, } @misc{kim2026dreamx, title = {{DreamX: Video Diffusion Model is a Universal Latent Action Learner}}, author = {Jisoo Kim and Chaehyun Kim and Junsu Kim and Jiho Park and Seongchan Kim and Eunbeen Hong and Soowon Son and Fu-En Yang and Seungryong Kim}, year = {2026}, eprint = {2611.05377}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2611.05377}, } @misc{davies2026primesim, title = {{PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations}}, author = {Travis Davies and Wentao Ma and Lihao Guo and Tengfei Ma and Xiaowen Chang and Jiafeng Xu and Shilong Wang and Yiqi Deng and Shaowen He and Xiaoqi Li and Qian Zhu and Ran Cheng and Hao Dong}, year = {2026}, eprint = {2611.04870}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04870}, } @misc{nvidia2026cosmos, title = {{Cosmos 3: Omnimodal World Models for Physical AI}}, author = {NVIDIA and : and Aditi and Niket Agarwal and Arslan Ali and Jon Allen and Martin Antolini and Adeline Aubame and Alisson Azzolini and Junjie Bai and Maciej Bala and Yogesh Balaji and Josh Bapst and Aarti Basant and Mukesh Beladiya and Mohammad Qazim Bhat and Zaid Pervaiz Bhat and Dan Blick and Vanni Brighella and Han Cai and Tiffany Cai and Eric Cameracci and Jiaxin Cao and Yulong Cao and Mark Carlson and Carlos Casanova and Ting-Yun Chang and Yan Chang and Yu-Wei Chao and Prithvijit Chattopadhyay and Roshan Chaudhari and Chieh-Yun Chen and Junyu Chen and Ke Chen and Qizhi Chen and Wenkai Chen and Xiaotong Chen and Yu Chen and An-Chieh Cheng and Click Cheng and Xiu Chia and Jeana Choi and Chaeyeon Chung and Wenyan Cong and Yin Cui and Magdalena Dadela and Nalin Dadhich and Wenliang Dai and Joyjit Daw and Alperen Degirmenci and others}, year = {2026}, eprint = {2606.02800}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.02800}, } @misc{nvidia2025world, title = {{World Simulation with Video Foundation Models for Physical AI}}, author = {NVIDIA and : and Arslan Ali and Junjie Bai and Maciej Bala and Yogesh Balaji and Aaron Blakeman and Tiffany Cai and Jiaxin Cao and Tianshi Cao and Elizabeth Cha and Yu-Wei Chao and Prithvijit Chattopadhyay and Mike Chen and Yongxin Chen and Yu Chen and Shuai Cheng and Yin Cui and Jenna Diamond and Yifan Ding and Jiaojiao Fan and Linxi Fan and Liang Feng and Francesco Ferroni and Sanja Fidler and Xiao Fu and Ruiyuan Gao and Yunhao Ge and Jinwei Gu and Aryaman Gupta and Siddharth Gururani and Imad El Hanafi and Ali Hassani and Zekun Hao and Jacob Huffman and Joel Jang and Pooya Jannaty and Jan Kautz and Grace Lam and Xuan Li and Zhaoshuo Li and Maosheng Liao and Chen-Hsuan Lin and Tsung-Yi Lin and Yen-Chen Lin and Huan Ling and Ming-Yu Liu and Xian Liu and Yifan Lu and Alice Luo and others}, year = {2025}, eprint = {2511.00062}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2511.00062}, } @misc{gao2026dreamdojo, title = {{DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos}}, author = {Shenyuan Gao and William Liang and Kaiyuan Zheng and Ayaan Malik and Seonghyeon Ye and Sihyun Yu and Wei-Cheng Tseng and Yuzhu Dong and Kaichun Mo and Chen-Hsuan Lin and Qianli Ma and Seungjun Nah and Loic Magne and Jiannan Xiang and Yuqi Xie and Ruijie Zheng and Dantong Niu and You Liang Tan and K. R. Zentner and George Kurian and Suneel Indupuru and Pooya Jannaty and Jinwei Gu and Jun Zhang and Jitendra Malik and Pieter Abbeel and Ming-Yu Liu and Yuke Zhu and Joel Jang and Linxi "Jim" Fan}, year = {2026}, eprint = {2602.06949}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.06949}, } @misc{li2026causal, title = {{Causal World Modeling for Robot Control}}, author = {Lin Li and Qihang Zhang and Yiming Luo and Shuai Yang and Ruilin Wang and Fei Han and Mingrui Yu and Zelin Gao and Nan Xue and Xing Zhu and Yujun Shen and Yinghao Xu}, year = {2026}, eprint = {2601.21998}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2601.21998}, } @misc{wang2026openwam, title = {{OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining}}, author = {Yuran Wang and Siqiao Huang and Mingleyang Li and Chenhao Zhang and Jiaqi Liang and Weiyang Jin and Yue Chen and Xuemin Chi and Donghao Zhou and Qize Yu and Yu-Kai Wang and Yuhan Rui and Shenzhe Yao and Zhen Yuan and Zhenhao Shen and Kefei Zhu and Zijie Zhu and Ning Gao and Xiaowei Chi and Guanqi He and Shanghang Zhang and Hao Dong and Lin Shao and Hang Zhao}, year = {2026}, eprint = {2609.07398}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.07398}, } @misc{yuan2026fast, title = {{Fast-WAM: Do World Action Models Need Test-time Future Imagination?}}, author = {Tianyuan Yuan and Zibin Dong and Yicheng Liu and Hang Zhao}, year = {2026}, eprint = {2603.16666}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2603.16666}, } @misc{ye2026gigaworld, title = {{GigaWorld-Policy: An Efficient Action-Centered World--Action Model}}, author = {Angen Ye and Boyuan Wang and Chaojun Ni and Guan Huang and Guosheng Zhao and Hao Li and Hengtao Li and Jie Li and Jindi Lv and Jingyu Liu and Min Cao and Peng Li and Qiuping Deng and Wenjun Mei and Xiaofeng Wang and Xinze Chen and Xinyu Zhou and Yang Wang and Yifan Chang and Yifan Li and Yukun Zhou and Yun Ye and Zhichao Liu and Zheng Zhu}, year = {2026}, eprint = {2603.17240}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2603.17240}, } @misc{chen2026abot, title = {{ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment}}, author = {Yuzhi Chen and Ronghan Chen and Dongjie Huo and Yandan Yang and Dekang Qi and Haoyun Liu and Tong Lin and Shuang Zeng and Junjin Xiao and Xinyuan Chang and Feng Xiong and Xing Wei and Zhiheng Ma and Mu Xu}, year = {2026}, eprint = {2603.23376}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2603.23376}, } @misc{zhou2026zero, title = {{Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization}}, author = {Jiaming Zhou and Qihang Zhang and Gangwei Xu and Cunxin Fan and Yujie Zhao and Ruilin Wang and Yiming Luo and Shuai Yang and Xing Zhu and Yujun Shen and Junwei Liang and Yinghao Xu}, year = {2026}, eprint = {2608.26103}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.26103}, } @misc{team2026motubrain, title = {{Motubrain: An Advanced World Action Model for Robot Control}}, author = {Motubrain Team and Chendong Xiang and Fan Bao and Haitian Liu and Hengkai Tan and Hongzhe Bi and James Li and Jiabao Liu and Jingrui Pang and Kiro Jing and Louis Liu and Mengchen Cai and Rongxu Cui and Ruowen Zhao and Runqing Wang and Shuhe Huang and Yao Feng and Yinze Rong and Zeyuan Wang and Jun Zhu}, year = {2026}, eprint = {2604.27792}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.27792}, } @misc{luo2026being, title = {{Being-H0.7: A Latent World-Action Model from Egocentric Videos}}, author = {Hao Luo and Wanpeng Zhang and Yicheng Feng and Sipeng Zheng and Haiweng Xu and Chaoyi Xu and Ziheng Xi and Yuhui Fu and Zongqing Lu}, year = {2026}, eprint = {2605.00078}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.00078}, } @misc{li2026wall, title = {{WALL-WM: Carving World Action Modeling at the Event Joints}}, author = {Shalfun Li and Victor Yao and Charles Yang and Truth Qu and Regis Cheng and Ryan Yu and Howard Lu and Newton Von and Vincent Chen and Yohann Tang and Maeve Zhang and Ellie Ma and Gody Li and Starrick Liu and Sage Yang and Lorien Shu and J. W. Gao and Ethan Chen and Colin Ye and Yu Sun and Elise Mon and PS Zhang and Neo Li and Lily Li and James Wang and Ping Yang and Chris Pan and Lucy Liang and Hang Su and Roy Gan and Hao Wang and Qian Wang}, year = {2026}, eprint = {2606.01955}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.01955}, } @misc{miao2026internw, title = {{InternW0-$Δ$: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data}}, author = {Xingyu Miao and Zizun Li and Baole Fang and Kaiwen Song and Tenghui Wang and Hanxue Zhang and Yating Wang and Xudong Li and Yuping He and Xueyuan Wei and Chao Gao and Xijie Yang and Yingxiang Xu and Kerui Ren and Wenqi Guo and Jianjun Zhou and Xinzhe Wang and Weiguang Zhao and Ni Yang and Zetao Cai and Yufei Xue and Hengjie Li and Zeyu He and Yuanzhen Zhou and Rong Fu and Jianyang Zhang and Siwei Cui and Fuxian Huang and Yunsong Zhou and Xing Gao and Yifei Yao and Qiaojun Yu and Kailin Li and Ming Zhou and Mu Huang and Xinyue Li and Wenze Cui and Bingqi Jiang and Xueyue Zhu and Junting Dong and Haoyu Guo and Tao Lu and Mulin Yu and Bowen Zhou and Bin Zhao and Tianfan Xue and Weinan Zhang and Chunhua Shen}, year = {2026}, eprint = {2609.31394}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.31394}, } @misc{guo2026video, title = {{Video Prediction Policy 2: Predict Better, Act Better}}, author = {Yanjiang Guo and Haodong Yan and Zhide Zhong and Zhongru Zhang and Qingyuan Yang and Qingzhou Lu and Xiaoyu Chen and Yen-Jen Wang and Shuying Deng and Chenghan Yang and Puzhen Yuan and Chenxin Liu and Tun Ban and Xiang Zhu and Yichen Liu and Kun Feng and Haoang Li and Jianyu Chen}, year = {2026}, eprint = {2610.10270}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.10270}, } @misc{zholus2026robojepa, title = {{RoboJEPA: Scaling Robotic Latent World Models}}, author = {Artem Zholus and Nicolas Beltran-Velez and Jianhao Yuan and Sarath Chandar and Tushar Nagarajan and Daniel Severo and Koustuv Sinha and Michal Drozdzal and Adriana Romero Soriano and Jeannette Bohg and Nicolas Ballas and Mahmoud Assran}, year = {2026}, eprint = {2610.10515}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2610.10515}, } @misc{zheng2025flare, title = {{FLARE: Robot Learning with Implicit World Modeling}}, author = {Ruijie Zheng and Jing Wang and Scott Reed and Johan Bjorck and Yu Fang and Fengyuan Hu and Joel Jang and Kaushil Kundalia and Zongyu Lin and Loic Magne and Avnish Narayan and You Liang Tan and Guanzhi Wang and Qi Wang and Jiannan Xiang and Yinzhen Xu and Seonghyeon Ye and Jan Kautz and Furong Huang and Yuke Zhu and Linxi Fan}, year = {2025}, eprint = {2505.15659}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.15659}, } @misc{zhang2026qwen, title = {{Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation}}, author = {Jie Zhang and Xiaoyue Chen and Anzhe Chen and Dayiheng Liu and Deqing Li and Gengze Zhou and Hale Yin and Haoqi Yuan and Haoyang Li and Jiahao Li and Jiazhao Zhang and Jingren Zhou and Kaiyuan Gao and Kun Yan and Lihan Jiang and Ningyuan Tang and Pei Lin and Qihang Peng and Shengming Yin and Tianhe Wu and Tianyi Yan and Xiao Xu and Yan Shu and Yanran Zhang and Ye Wang and Yi Wang and Yilei Chen and Yixian Xu and Yiyang Huang and Yuxiang Chen and Zekai Zhang and Zhendong Wang and Zixing Lei and Zhixuan Liang and Zihao Liu and Zikai Zhou and Chenxu Lv and Xiong-Hui Chen and Chenfei Wu}, year = {2026}, eprint = {2606.17030}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.17030}, } @misc{li2026xiaomi, title = {{Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model}}, author = {Xinghang Li and Jun Guo and Qiwei Li and Long Qian and Hang Lai and Yueze Wang and Hongyu Yan and Jiahang Cao and Xi Chen and Jingen Qu and Jiaxi Song and Nan Sun and Hanye Zhao and Futeng Liu and Wanli Peng and Heyun Wang and Yunhong Wang and Caoyu Xia and Jack Zhao and Diyun Xiang and Hangjun Ye and Heng Qu and Huaping Liu and Jason Li}, year = {2026}, eprint = {2607.11643}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.11643}, } @misc{zhang2026physisforcing, title = {{PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation}}, author = {Peiwen Zhang and Yufan Deng and Shangkun Sun and Juncheng Ma and Duomin Wang and Jonas Du and Zilin Pan and Ye Huang and Hao Liang and Songyan Huang and Ruihua Zhang and Enze Xie and Ming-Yu Liu and Daquan Zhou}, year = {2026}, eprint = {2606.28128}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.28128}, } @misc{team2025evaluating, title = {{Evaluating Gemini Robotics Policies in a Veo World Simulator}}, author = {Gemini Robotics Team and Krzysztof Choromanski and Coline Devin and Yilun Du and Debidatta Dwibedi and Ruiqi Gao and Abhishek Jindal and Thomas Kipf and Sean Kirmani and Isabel Leal and Fangchen Liu and Anirudha Majumdar and Andrew Marmon and Carolina Parada and Yulia Rubanova and Dhruv Shah and Vikas Sindhwani and Jie Tan and Fei Xia and Ted Xiao and Sherry Yang and Wenhao Yu and Allan Zhou}, year = {2025}, eprint = {2512.10675}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.10675}, } @misc{tseng2025scalable, title = {{Scalable Policy Evaluation with Video World Models}}, author = {Wei-Cheng Tseng and Jinwei Gu and Qinsheng Zhang and Hanzi Mao and Ming-Yu Liu and Florian Shkurti and Lin Yen-Chen}, year = {2025}, eprint = {2511.11520}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.11520}, } @misc{zhang2026do, title = {{Do World Action Models Generalize Better than VLAs? A Robustness Study}}, author = {Zhanguang Zhang and Zhiyuan Li and Behnam Rahmati and Rui Heng Yang and Yintao Ma and Amir Rasouli and Sajjad Pakdamansavoji and Yangzheng Wu and Lingfeng Zhang and Tongtong Cao and Feng Wen and Xinyu Wang and Xingyue Quan and Yingxue Zhang}, year = {2026}, eprint = {2603.22078}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.22078}, } @misc{lu2026world, title = {{World-Action Models for Robot Learning and Control: A Survey}}, author = {Zuxing Lu and Hongjia Zhai and Guanzhi Wang and Huajian Zeng and Jiaqi Yang and Jingyu Liu and Lei Cheng and Yuantai Zhang and Yuheng Qiu and Zezhou Cheng and Ivan Laptev and Danfei Xu and Benjamin Riviere and Giuseppe Loianno and Eric Xing and Xingxing Zuo}, year = {2026}, eprint = {2609.16074}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.16074}, } @misc{zhang2026from, title = {{From World Models to World Action Models: A Concise Tutorial for Robotics}}, author = {Xiaoxiong Zhang and Xiong Zeng and Wei Zhang}, year = {2026}, eprint = {2607.00836}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.00836}, } @misc{lu2025gwm, title = {{GWM: Towards Scalable Gaussian World Models for Robotic Manipulation}}, author = {Guanxing Lu and Baoxiong Jia and Puhao Li and Yixin Chen and Ziwei Wang and Yansong Tang and Siyuan Huang}, year = {2025}, eprint = {2508.17600}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.17600}, } @misc{huang2025particleformer, title = {{ParticleFormer: A 3D Point Cloud World Model for Multi-Object, Multi-Material Robotic Manipulation}}, author = {Suning Huang and Qianzhong Chen and Xiaohan Zhang and Jiankai Sun and Mac Schwager}, year = {2025}, eprint = {2506.23126}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.23126}, } @misc{wang2026st, title = {{ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts}}, author = {Mingxin Wang and Bin Hu and Bin Qian and Kaitao Jiang and Haoning Wu and Feng Yan and Bowen Jing and Ruiyang Hao and Enyi Wang and Kangning Niu and Yandan Yang and Mu Xu and Yan Wang and Houde Liu and Tianlun Li}, year = {2026}, eprint = {2607.28993}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.28993}, } @misc{qiu2026ge, title = {{GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation}}, author = {Boxiang Qiu and Liliang Chen and Yue Liao and Nan Wang and Lintao Wang and Jiayi Luo and Wenzhi Zhao and Shengcong Chen and Di Chen and Ye Li and Chen Gao and Shuicheng Yan and Si Liu and Maoqing Yao and Guanghui Ren}, year = {2026}, eprint = {2605.27491}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.27491}, } @misc{hansen2024hierarchical, title = {{Hierarchical World Models as Visual Whole-Body Humanoid Controllers}}, author = {Nicklas Hansen and Jyothir S and Vlad Sobal and Yann LeCun and Xiaolong Wang and Hao Su}, year = {2024}, eprint = {2405.18418}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2405.18418}, } @misc{nvidia2026interactive, title = {{Interactive World Simulation with Cosmos for Physical AI}}, author = {NVIDIA and : and Anis Ahmad and Jon Allen and Malik Aqeel Anwar and Jesse Archer and Maciej Bala and Piotr Barejko and Aarti Basant and Dan Blick and Taras Bolzhelarskyi and Henry Che and Jin Chen and Yukang Chen and Tae Eun Choe and Yuzhu Dong and Nat Duca and Liang Feng and Francesco Ferroni and Xiao Fu and Mohit Gambhir and Vivek Goel and Rony Goldenthal and Aryaman Gupta and Ali Hassani and Nathan Hayes-Roth and Yong He and Michael Honke and Shengyu Huang and Wei Huang and DeLesley Hutchins and Suneel Indupuru and Pooya Jannaty and Jingyi Jin and Janmesh Kalra and Ashna Khetan and Xin Kong and Aleksandr Korovko and Hui Kuang and Zhengfei Kuang and George Kurian and Jean-Francois Lafleche and Jayjun Lee and Justin Leung and William Lew and Xiang Li and Zhaoshuo Li and Chen-Hsuan Lin and Ming-Yu Liu and Xiangyu Lu and others}, year = {2026}, eprint = {2611.06627}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2611.06627}, } @misc{liu2026reactworld, title = {{ReactWorld: Structuring Interaction Responses for Embodied Video Generation}}, author = {Hanwei Liu and Huijia Zhang and Hanzhang Wang and Guangyu Liu and Hanbei Zhan and Linjie Hu and Bin Xiao and Xuan Zhou and Dong Zhang}, year = {2026}, eprint = {2611.06120}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2611.06120}, } @misc{qu2026jev, title = {{Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model}}, author = {Yansong Qu and Jiancong Chen and Samuel Labi}, year = {2026}, eprint = {2611.05448}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05448}, } @misc{vasilev2026does, title = {{Does LeWorldModel Preserve Local Action Geometry?}}, author = {Vasil Vasilev and Siddharth Nayak}, year = {2026}, eprint = {2610.31716}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2610.31716}, } @misc{chen2025large, title = {{Large Video Planner Enables Generalizable Robot Control}}, author = {Boyuan Chen and Tianyuan Zhang and Haoran Geng and Caiyi Zhang and Peihao Li and Kiwhan Song and William T. Freeman and Jitendra Malik and Pieter Abbeel and Russ Tedrake and Vincent Sitzmann and Yilun Du}, year = {2025}, eprint = {2512.15840}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.15840}, } @misc{zhang2026imagewam, title = {{ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?}}, author = {Yuyang Zhang and Wenyao Zhang and Zekun Qi and He Zhang and Haitao Lin and Jingbo Zhang and Yao Mu and Xiaokang Yang and Wenjun Zeng and Xin Jin}, year = {2026}, eprint = {2606.19531}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.19531}, } @misc{li2026light, title = {{Light-WAM: Efficient World Action Models with State-Fusion Action Decoding}}, author = {Ziang Li and Dongzhou Cheng and Yibin Wang and Shiyue Wang and Xiaoyang Xu and Lingxuan Weng and Juan Wang and Jiaqi Wang}, year = {2026}, eprint = {2606.08242}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.08242}, } @misc{lee2026scalable, title = {{$μ_0$: A Scalable 3D Interaction-Trace World Model}}, author = {Seungjae Lee and Yoonkyo Jung and Jusuk Lee and Jonghun Shin and Amir Hossein Shahidzadeh and Yao-Chih Lee and H. Jin Kim and Jia-Bin Huang and Furong Huang}, year = {2026}, eprint = {2606.13769}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13769}, } @misc{seo2026stressdream, title = {{StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement}}, author = {Junwon Seo and Sushant Veer and Ran Tian and Wenhao Ding and Apoorva Sharma and Karen Leung and Edward Schmerling and Marco Pavone and Andrea Bajcsy}, year = {2026}, eprint = {2606.00267}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.00267}, } @misc{yeom2026what, title = {{What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction}}, author = {Jewon Yeom and Hanseul Kim and Jeongjae Park and Sungmok Jung and Jaejin Lee and Taesup Kim}, year = {2026}, eprint = {2606.07687}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.07687}, } @misc{clemente2026la, title = {{La-JEPA: Compact Robot Policies with Latent World Modeling}}, author = {Mateo Clémente and George Z. Xue and Amin Abyaneh and Liheng Ma and Rui Heng Yang and Tongtong Cao and Zhanguang Zhang and Yingxue Zhang}, year = {2026}, eprint = {2611.08156}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08156}, } @misc{ren2026gpwm, title = {{GPWM: Modeling the World as 3D Particle Motion}}, author = {Robert Ren and Matthew Bronars and He Zhu and Yikai Tang and Jianing Zhang and Sergey Zakharov and Pavel Tokmakov and Katerina Fragkiadaki}, year = {2026}, eprint = {2611.08338}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08338}, } @misc{yu2026box, title = {{Box-WAM: Box Trajectories as Compact State Representations for World Action Models}}, author = {Qinxi Yu and Wenzhou Ding and Gloria X. Wang and Albert J. Zhai and Shenlong Wang}, year = {2026}, eprint = {2610.17526}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17526}, } @misc{bardhan2026depthworld, title = {{DepthWorld: 3D World Model for Robot Manipulation}}, author = {Jai Bardhan and Josef Sivic and Vladimir Petrik}, year = {2026}, eprint = {2610.08780}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.08780}, } @misc{chen2026anyworld, title = {{AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization}}, author = {Cheng Chen and Jerry Bai and Jiacheng Wei and Boyu Chen and Xiaoji Zheng and Fan Wu and Minghao Yang and Tianrun Chen and Ruibo Li and Xiaoyu Yue and Xiaoyang Guo and Yixiao Ge and Guosheng Lin and Fayao Liu}, year = {2026}, eprint = {2608.29242}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.29242}, } @misc{jiang2026memoryvam, title = {{MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation}}, author = {Yuxin Jiang and Chang Yu and Yunuo Chen and Xiang Feng and Yin Yang and Nishank Gite and Chenfanfu Jiang}, year = {2026}, eprint = {2606.20679}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.20679}, } @misc{fu2026novaplan, title = {{NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning}}, author = {Jiahui Fu and Junyu Nan and Lingfeng Sun and Hongyu Li and Jianing Qian and Benjamin Yang and Yilun Du and Jennifer L. Barry and Kris Kitani and George Konidaris}, year = {2026}, eprint = {2602.20119}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.20119}, } @misc{yin2026physcore, title = {{PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics}}, author = {Haocheng Yin and Shuohan Tao and Yongsheng Chen and Lu Gan}, year = {2026}, eprint = {2607.20653}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.20653}, } @misc{li2026egowam, title = {{EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data}}, author = {Baoyu Li and Xinchen Yin and Mengying Lin and Yixin Zhang and Danfei Xu}, year = {2026}, eprint = {2607.08436}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.08436}, } @misc{yin2026playworld, title = {{PlayWorld: Learning Robot World Models from Autonomous Play}}, author = {Tenny Yin and Zhiting Mei and Zhonghe Zheng and Miyu Yamane and David Wang and Jade Sceats and Samuel M. Bateman and Lihan Zha and Apurva Badithela and Ola Shorinwa and Anirudha Majumdar}, year = {2026}, eprint = {2603.09030}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.09030}, } @misc{zhou2026wm, title = {{$τ_0$-WM: A Unified Video-Action World Model for Robotic Manipulation}}, author = {Pengfei Zhou and Shengcong Chen and Di Chen and Jiaxu Wang and Rongjun Jin and Bingwen Zhu and Yike Pan and Songen Gu and Kuanning Wang and Shufeng Nan and Xingyu Qiu and Chenhao Qiu and Pu Yang and Yunuo Cai and Jianxiong Gao and Yifan Li and Yanwei Fu and Xiangyu Yue and Zhi Chen and Jianlan Luo}, year = {2026}, eprint = {2606.01027}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.01027}, } @misc{jiang2026wovr, title = {{WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL}}, author = {Zhennan Jiang and Shangqing Zhou and Yutong Jiang and Zefang Huang and Mingjie Wei and Yuhui Chen and Tianxing Zhou and Zhen Guo and Hao Lin and Quanlu Zhang and Yu Wang and Haoran Li and Dongbin Zhao and Chao Yu}, year = {2026}, eprint = {2602.13977}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.13977}, } @misc{long2026scaling, title = {{Scaling World Model for Hierarchical Manipulation Policies}}, author = {Qian Long and Yueze Wang and Jiaxi Song and Junbo Zhang and Peiyan Li and Wenxuan Wang and Yuqi Wang and Haoyang Li and Shaoxuan Xie and Guocai Yao and Hanbo Zhang and Xinlong Wang and Zhongyuan Wang and Xuguang Lan and Huaping Liu and Xinghang Li}, year = {2026}, eprint = {2602.10983}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.10983}, } @misc{peng2026fact, title = {{FACT: Failure-Aware Causal Training for World-Action Models}}, author = {Quanquan Peng and Yutong Liang and Rui Yan and Nicklas Hansen and Xiaolong Wang}, year = {2026}, eprint = {2608.10232}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.10232}, } @misc{amigo2026coupled, title = {{Coupled Local and Global World Models for Efficient First Order RL}}, author = {Joseph Amigo and Rooholla Khorrambakht and Nicolas Mansard and Ludovic Righetti}, year = {2026}, eprint = {2602.06219}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.06219}, } @misc{zhang2026hierarchical, title = {{Hierarchical Planning with Latent World Models}}, author = {Wancong Zhang and Basile Terver and Artem Zholus and Soham Chitnis and Harsh Sutaria and Mido Assran and Randall Balestriero and Amir Bar and Yann LeCun and Nicolas Ballas}, year = {2026}, eprint = {2604.03208}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2604.03208}, } @misc{kim2026robot, title = {{Robot-Factored World Models via Robot Rendering}}, author = {Byungjun Kim and Taeksoo Kim and Hyunsoo Cha and Hanbyul Joo}, year = {2026}, eprint = {2607.22535}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.22535}, } @misc{ajith2026strips, title = {{STRIPS-WM: Learning Grounded Propositional STRIPS-style World Models from Images}}, author = {Abhiroop Ajith and Constantinos Chamzas}, year = {2026}, eprint = {2606.06832}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.06832}, } @misc{wu2026learning, title = {{Learning Robotic World Models with Semantic and Visual Feedback}}, author = {Hao Wu and Yuqi Li and Yizhou Zhao and Kun Wang and Xiao Luo and Yu Cheng and Bo An and Yingli Tian and Laszlo A. Jeni and Ming-Hsuan Yang}, year = {2026}, eprint = {2611.07850}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.07850}, } @misc{zhang2026w, title = {{W2A: Distilling World Priors into Action Models for Real-Time Robotic Control}}, author = {Xiaopeng Zhang and Yongjin Mu and Yueyang Weng and Chengzhi Zhao and Yanjie Li}, year = {2026}, eprint = {2611.02600}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02600}, } @misc{he2026fawam, title = {{FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation}}, author = {Haotian He and Zeyu Yan and Qipeng Liu and Ning Guo and Wenzhao Lian}, year = {2026}, eprint = {2606.08555}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08555}, } @misc{yu2026maskwam, title = {{MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models}}, author = {Hanyang Yu and Haitao Lin and Jingbo Zhang and Wenyao Zhang and Chenghao Gu and Heng Li and Ping Tan}, year = {2026}, eprint = {2606.13515}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.13515}, } @misc{weng2026ord, title = {{ORD-WM: Learning Object-Centric Rigid Dynamics for 3D World Modeling in Robotic Manipulation}}, author = {Yueyang Weng and Xiaopeng Zhang and Yuxi Ou and Yongjin Mu and Chengzhi Zhao and Yanjie Li}, year = {2026}, eprint = {2610.23156}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23156}, } @misc{mishra2026understanding, title = {{Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio}}, author = {Utkarsh A. Mishra and Yongxin Chen and Danfei Xu and Yang Liu and Xi Chen and Jiayuan Mao}, year = {2026}, eprint = {2607.08127}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2607.08127}, } @misc{feng2026wam, title = {{WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time}}, author = {Yusen Feng and Bingchen Han and Jiangran Lyu and Kai Liu and Yixin Zheng and Yuxuan Wan and Weiheng Liu and Sun Han and Ruiqin Li and Yulong Zhang and Fangfu Liu and Xuesong Shi and Libin Liu and Yizhou Wang and Zhizheng Zhang and He Wang}, year = {2026}, eprint = {2607.06988}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.06988}, } @misc{he2026skip, title = {{SKIP: Sparse Keyframe Interpolation Paradigm for Efficient Embodied World Models}}, author = {Ziheng He and Yixiang Chen and Ning Yang and Zhanqian Wu and Qisen Ma and Yuan Xu and Jiabing Yang and Peiyan Li and Xiangnan Wu and Xiaofeng Wang and Zheng Zhu and Jing Liu and Nianfeng Liu and Yan Huang}, year = {2026}, eprint = {2606.00664}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.00664}, } @misc{yu2026sensitivity, title = {{Sensitivity Shaping for Latent Modeling}}, author = {Hongzhan Yu and Chenghao Li and Ruipeng Zhang and Henrik Christensen and Sicun Gao}, year = {2026}, eprint = {2606.14585}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14585}, } @misc{beddow2026adaptive, title = {{Adaptive World-Models for Anomaly Recognition (AWARE): A Framework for Robot Dynamics Prediction and Introspection}}, author = {Luke Beddow and George Mavroghenis and Rodrigo Chacon Quesada and Kamil Dreczkowski and Cong Sun and Jiankai Wang and Oscar Kwong-Fai Pang and Antoine Cully}, year = {2026}, eprint = {2610.32742}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32742}, } @misc{kim2025how, title = {{How Well Do Latent World Models Understand Partially Observable Safety Constraints?}}, author = {Matthew Kim and Kensuke Nakamura and Andrea Bajcsy}, year = {2025}, eprint = {2510.06492}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.06492}, } @misc{zhao2026c, title = {{C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache}}, author = {Weisen Zhao and Lam Nguyen and Zhicong Lu and Yuzhang Shang}, year = {2026}, eprint = {2606.08962}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2606.08962}, } @misc{jo2026future, title = {{Future Representation Distillation for Imagination-free World Action Models}}, author = {Jaehyeong Jo and Sangwon Jang and Sihyun Yu and Seonghyeon Ye and Yekyung Nah and Hojung Jung and Kimin Lee and Sung Ju Hwang}, year = {2026}, eprint = {2611.04527}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04527}, } @misc{chen2026objectworld, title = {{ObjectWorld: Scaling Object-Centric World Models with A Large-Scale 3D Full-Object Flow Dataset}}, author = {Haonan Chen and Sicheng Isabella Lu and Haitian Li and Jiajin Wu and Hexiang Wei and Jiawei Zhang and Xin Fei and Yiwen Hou and Chenrui Tie and Chongkai Gao and Sheng Wang and Lin Shao}, year = {2026}, eprint = {2611.11085}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.11085}, } @misc{ahn2022do, title = {{Do As I Can, Not As I Say: Grounding Language in Robotic Affordances}}, author = {Michael Ahn and Anthony Brohan and Noah Brown and Yevgen Chebotar and Omar Cortes and Byron David and Chelsea Finn and Chuyuan Fu and Keerthana Gopalakrishnan and Karol Hausman and Alex Herzog and Daniel Ho and Jasmine Hsu and Julian Ibarz and Brian Ichter and Alex Irpan and Eric Jang and Rosario Jauregui Ruano and Kyle Jeffrey and Sally Jesmonth and Nikhil J Joshi and Ryan Julian and Dmitry Kalashnikov and Yuheng Kuang and Kuang-Huei Lee and Sergey Levine and Yao Lu and Linda Luu and Carolina Parada and Peter Pastor and Jornell Quiambao and Kanishka Rao and Jarek Rettinghouse and Diego Reyes and Pierre Sermanet and Nicolas Sievers and Clayton Tan and Alexander Toshev and Vincent Vanhoucke and Fei Xia and Ted Xiao and Peng Xu and Sichun Xu and Mengyuan Yan and Andy Zeng}, year = {2022}, eprint = {2204.01691}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2204.01691}, } @misc{liang2022code, title = {{Code as Policies: Language Model Programs for Embodied Control}}, author = {Jacky Liang and Wenlong Huang and Fei Xia and Peng Xu and Karol Hausman and Brian Ichter and Pete Florence and Andy Zeng}, year = {2022}, eprint = {2209.07753}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2209.07753}, } @misc{huang2022inner, title = {{Inner Monologue: Embodied Reasoning through Planning with Language Models}}, author = {Wenlong Huang and Fei Xia and Ted Xiao and Harris Chan and Jacky Liang and Pete Florence and Andy Zeng and Jonathan Tompson and Igor Mordatch and Yevgen Chebotar and Pierre Sermanet and Noah Brown and Tomas Jackson and Linda Luu and Sergey Levine and Karol Hausman and Brian Ichter}, year = {2022}, eprint = {2207.05608}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2207.05608}, } @misc{anderson2017vision, title = {{Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments}}, author = {Peter Anderson and Qi Wu and Damien Teney and Jake Bruce and Mark Johnson and Niko Sünderhauf and Ian Reid and Stephen Gould and Anton van den Hengel}, year = {2017}, eprint = {1711.07280}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/1711.07280}, } @misc{huang2022visual, title = {{Visual Language Maps for Robot Navigation}}, author = {Chenguang Huang and Oier Mees and Andy Zeng and Wolfram Burgard}, year = {2022}, eprint = {2210.05714}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2210.05714}, } @misc{sridhar2023nomad, title = {{NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration}}, author = {Ajay Sridhar and Dhruv Shah and Catherine Glossop and Sergey Levine}, year = {2023}, eprint = {2310.07896}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2310.07896}, } @misc{liu2024ok, title = {{OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics}}, author = {Peiqi Liu and Yaswanth Orru and Jay Vakil and Chris Paxton and Nur Muhammad Mahi Shafiullah and Lerrel Pinto}, year = {2024}, eprint = {2401.12202}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2401.12202}, } @misc{wang2026cracking, title = {{Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System}}, author = {Zixuan Wang and Jia-Ning Li and Yinzhou Tang and Yanzhao Yu and Biao Wu and Meng Fang and Xin Li and Yiwu Zhong}, year = {2026}, eprint = {2610.19600}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.19600}, } @misc{gong2026hierarchical, title = {{Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance}}, author = {Zhefei Gong and Hefeifei Jiang and Zehao Wang and Jiachen Li}, year = {2026}, eprint = {2610.20607}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.20607}, } @misc{shah2023vint, title = {{ViNT: A Foundation Model for Visual Navigation}}, author = {Dhruv Shah and Ajay Sridhar and Nitish Dashora and Kyle Stachowicz and Kevin Black and Noriaki Hirose and Sergey Levine}, year = {2023}, eprint = {2306.14846}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2306.14846}, } @misc{shah2022gnm, title = {{GNM: A General Navigation Model to Drive Any Robot}}, author = {Dhruv Shah and Ajay Sridhar and Arjun Bhorkar and Noriaki Hirose and Sergey Levine}, year = {2022}, eprint = {2210.03370}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2210.03370}, } @misc{yokoyama2023vlfm, title = {{VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation}}, author = {Naoki Yokoyama and Sehoon Ha and Dhruv Batra and Jiuguang Wang and Bernadette Bucher}, year = {2023}, eprint = {2312.03275}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2312.03275}, } @misc{zhang2024navid, title = {{NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation}}, author = {Jiazhao Zhang and Kunyu Wang and Rongtao Xu and Gengze Zhou and Yicong Hong and Xiaomeng Fang and Qi Wu and Zhizheng Zhang and He Wang}, year = {2024}, eprint = {2402.15852}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2402.15852}, } @misc{zhang2024uni, title = {{Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks}}, author = {Jiazhao Zhang and Kunyu Wang and Shaoan Wang and Minghan Li and Haoran Liu and Songlin Wei and Zhongyuan Wang and Zhizheng Zhang and He Wang}, year = {2024}, eprint = {2412.06224}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.06224}, } @misc{macenski2020marathon, title = {{The Marathon 2: A Navigation System}}, author = {Steve Macenski and Francisco Martín and Ruffin White and Jonatan Ginés Clavero}, year = {2020}, eprint = {2003.00368}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2003.00368}, } @misc{cheng2024navila, title = {{NaVILA: Legged Robot Vision-Language-Action Model for Navigation}}, author = {An-Chieh Cheng and Yandong Ji and Zhaojing Yang and Zaitian Gongye and Xueyan Zou and Jan Kautz and Erdem Bıyık and Hongxu Yin and Sifei Liu and Xiaolong Wang}, year = {2024}, eprint = {2412.04453}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.04453}, } @misc{krantz2020beyond, title = {{Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments}}, author = {Jacob Krantz and Erik Wijmans and Arjun Majumdar and Dhruv Batra and Stefan Lee}, year = {2020}, eprint = {2004.02857}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2004.02857}, } @misc{shah2022lm, title = {{LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action}}, author = {Dhruv Shah and Blazej Osinski and Brian Ichter and Sergey Levine}, year = {2022}, eprint = {2207.04429}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2207.04429}, } @misc{chaplot2020object, title = {{Object Goal Navigation using Goal-Oriented Semantic Exploration}}, author = {Devendra Singh Chaplot and Dhiraj Gandhi and Abhinav Gupta and Ruslan Salakhutdinov}, year = {2020}, eprint = {2007.00643}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2007.00643}, } @misc{chaplot2020learning, title = {{Learning to Explore using Active Neural SLAM}}, author = {Devendra Singh Chaplot and Dhiraj Gandhi and Saurabh Gupta and Abhinav Gupta and Ruslan Salakhutdinov}, year = {2020}, eprint = {2004.05155}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2004.05155}, } @misc{gadre2022cows, title = {{CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation}}, author = {Samir Yitzhak Gadre and Mitchell Wortsman and Gabriel Ilharco and Ludwig Schmidt and Shuran Song}, year = {2022}, eprint = {2203.10421}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2203.10421}, } @misc{ramrakhya2023pirlnav, title = {{PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav}}, author = {Ram Ramrakhya and Dhruv Batra and Erik Wijmans and Abhishek Das}, year = {2023}, eprint = {2301.07302}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2301.07302}, } @misc{yang2026scalenav, title = {{ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation}}, author = {Yihui Yang and Yuanhong Yu and Jiawei Wang and Zhongrui Yu and Jia Shi and Kun Zhan and Ruizhen Hu and Xiaowei Zhou and Yu Liu and Sida Peng}, year = {2026}, eprint = {2610.25690}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25690}, } @misc{zhou2023navgpt, title = {{NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models}}, author = {Gengze Zhou and Yicong Hong and Qi Wu}, year = {2023}, eprint = {2305.16986}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2305.16986}, } @misc{an2023etpnav, title = {{ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments}}, author = {Dong An and Hanqing Wang and Wenguan Wang and Zun Wang and Yan Huang and Keji He and Liang Wang}, year = {2023}, eprint = {2304.03047}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2304.03047}, } @misc{xu2026tarsphere, title = {{TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments}}, author = {Yicheng Xu and Zhikai Xu and Ziyuan Chen and Yuhang Dong and Tao Zhang and Zhucun Xue and Yong Liu and Jiangning Zhang}, year = {2026}, eprint = {2610.30043}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.30043}, } @misc{feng2026embodiedworld, title = {{EmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models}}, author = {X. Feng and J. Tang and Z. Lin and L. Chen and S. Shao and Q. Lu and K. Huang}, year = {2026}, eprint = {2610.25959}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2610.25959}, } @misc{zhou2026injepa, title = {{InJePA: Intention-First Latent Planning with Coupled JEPA World Models for Visual Navigation}}, author = {Siming Zhou and Bowen Ma and Ruiran Du and Pengcheng Zheng and Sheng Zheng and Dongshen Han and Zhijie Li and Wei Dong and Fan Mo and Chaoning Zhang}, year = {2026}, eprint = {2610.23896}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23896}, } @misc{wang2026havana, title = {{HAVANA: A Hierarchical Video-Action Model for Vision-Language Navigation}}, author = {Dongzhihan Wang and Yi Du and Chen Wang and Xiuxian Li and Liang Xu}, year = {2026}, eprint = {2610.24122}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.24122}, } @misc{zhou2026moon, title = {{MOON: Learning When to Forget and How to Move On in Vision-and-Language Navigation}}, author = {Jingmeng Zhou and Seson Sun and Binyao Xu and Lingming Zhang and Hanshi Wang and Fudong Ge and Weiming Hu and Jin Gao and Zhipeng Zhang}, year = {2026}, eprint = {2610.33546}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.33546}, } @misc{yu2026one, title = {{One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation}}, author = {Zhuoyuan Yu and Yuxing Long and Du Wang and Junyang Wang and Hongwei Fan and Hao Dong}, year = {2026}, eprint = {2610.33794}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.33794}, } @misc{chen2026see, title = {{See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space}}, author = {Jiawei Chen and Yinxi Wang and Zihan Yang and Meijun Gao and Yaowei Liu and Shuming Zhang and Zecheng Li and Xiangju Mi and Yuxuan Liu and Runzhong Huang and Tianlin Li and Xun Zhang and Zhengyang Wang and Xu Miao and Tong Yang}, year = {2026}, eprint = {2610.31762}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31762}, } @misc{chen2026gaussian, title = {{Gaussian Episodic Memory for Long-Term Spatiotemporal Reasoning}}, author = {Ling-Chia Chen and Abdelrhman Werby and Kaan Aytekin and Kai O. Arras}, year = {2026}, eprint = {2610.33158}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.33158}, } @misc{bae2026benchmarking, title = {{Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation}}, author = {Hyunwoong Bae and Jisu Han and Jiyeon Choi and Dohoon Kim and Taesup Moon}, year = {2026}, eprint = {2610.34674}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34674}, } @misc{liu2026sidewalkbench, title = {{SidewalkBench: Benchmarking Visual Navigation on Urban Sidewalks}}, author = {Zhizheng Liu and Honglin He and Vivek Alumootil and Akshat Pandya and Brad Squicciarini and Wayne Wu and Bolei Zhou}, year = {2026}, eprint = {2606.16953}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16953}, } @misc{sahak2026oscar, title = {{OSCAR: Obstacle Survival Curves for Adaptive Robot Navigation}}, author = {Hshmat Sahak and Aoran Jiao and Nicholas Rhinehart and Tim Barfoot}, year = {2026}, eprint = {2606.00990}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.00990}, } @misc{liu2026openflyv, title = {{OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation}}, author = {Junli Liu and Zhongrui You and Chenhui Li and Zhen Li and Yuyang Tian and Qizhen Chen and Delin Qu and Haoming Song and Dong Wang and Xuelong Li and Zhigang Wang and Bin Zhao}, year = {2026}, eprint = {2610.39287}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39287}, } @misc{patel2026waytrace, title = {{WayTrace: A Map-to-Language-to-Trace Hierarchy for Embodied Urban Navigation}}, author = {Manthan Patel and Jonas Frey and Pascal Roth and Marco Hutter and Cesar Cadena}, year = {2026}, eprint = {2611.05129}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05129}, } @misc{lee2026aero, title = {{Aero-VPA: Few-Step Flow-Matching Control over Non-Reconstructive JEPA Latents for Agile Flight on Edge Hardware}}, author = {Yeonseok Lee}, year = {2026}, eprint = {2611.04392}, archivePrefix = {arXiv}, primaryClass = {cs.LO}, url = {https://arxiv.org/abs/2611.04392}, } @misc{shi2026from, title = {{From Region Arrival to Instance-Level Grounding in Vision-and-Language Navigation}}, author = {Xiangyu Shi and Ruoxi Yang and Wei Tao and Jiwen Zhang and Yanyuan Qiao and Qi Wu}, year = {2026}, eprint = {2607.03792}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.03792}, } @misc{kohaut2026driving, title = {{Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility}}, author = {Simon Kohaut and Felix Divo and Julius Hahnewald and Benedict Flade and Julian Eggert and Kristian Kersting and Devendra Singh Dhami}, year = {2026}, eprint = {2606.15251}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15251}, } @misc{deng2026collaborative, title = {{Collaborative Planning for UAV-UGV Teams under Operational Constraints via Masked Error-bounded Neuro-Symbolic Diffusion}}, author = {Zihao Deng and Qianhuang Li and Maggie Wigness and John Rogers and Donghyun Kim and Hao Zhang}, year = {2026}, eprint = {2610.18850}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18850}, } @misc{lee2026odorspaces, title = {{OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments}}, author = {Changyeon Lee and Kelin Yu and Zheng Wei and Shuna Ni and Ruohan Gao}, year = {2026}, eprint = {2611.05738}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05738}, } @misc{cai2025navdp, title = {{NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance}}, author = {Wenzhe Cai and Jiaqi Peng and Yuqiang Yang and Yujian Zhang and Meng Wei and Hanqing Wang and Yilun Chen and Tai Wang and Jiangmiao Pang}, year = {2025}, eprint = {2505.08712}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.08712}, } @misc{choi2024canvas, title = {{CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction}}, author = {Suhwan Choi and Yongjun Cho and Minchan Kim and Jaeyoon Jung and Myunchul Joe and Yubeen Park and Minseo Kim and Sungwoong Kim and Sungjae Lee and Hwiseong Park and Jiwan Chung and Youngjae Yu}, year = {2024}, eprint = {2410.01273}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.01273}, } @misc{honerkamp2024language, title = {{Language-Grounded Dynamic Scene Graphs for Interactive Object Search with Mobile Manipulation}}, author = {Daniel Honerkamp and Martin Büchner and Fabien Despinoy and Tim Welschehold and Abhinav Valada}, year = {2024}, eprint = {2403.08605}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.08605}, } @misc{seong2025costnav, title = {{CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents}}, author = {Haebin Seong and Sungmin Kim and Yongjun Cho and Myunchul Joe and Geunwoo Kim and Yubeen Park and Sunhoo Kim and Samwoo Seong and Yoonshik Kim and Suhwan Choi and Jaeyoon Jung and Jiyong Youn and Jinmyung Kwak and Sunghee Ahn and Jaemin Lee and Younggil Do and Seungyeop Yi and Woojin Cheong and Minhyeok Oh and Minchan Kim and Seongjae Kang and Youngjae Yu and Yunsung Lee}, year = {2025}, eprint = {2511.20216}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2511.20216}, } @misc{lei2025robomemory, title = {{RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systems}}, author = {Mingcong Lei and Honghao Cai and Yuyuan Yang and Yimou Wu and Jinke Ren and Zezhou Cui and Liangchen Tan and Junkun Hong and Gehan Hu and Shuangyu Zhu and Shaohan Jiang and Ge Wang and Junyuan Tan and Zhenglin Wan and Zheng Li and Zhen Li and Shuguang Cui and Yiming Zhao and Yatong Han}, year = {2025}, eprint = {2508.01415}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.01415}, } @misc{liu2026cofl, title = {{CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation}}, author = {Haokun Liu and Zhaoqi Ma and Yicheng Chen and Wentao Zhang and Masaki Kitagawa and Zicen Xiong and Jinjie Li and Moju Zhao}, year = {2026}, eprint = {2607.02222}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.02222}, } @misc{liao2026g, title = {{G2-Nav: Grounded and Guarded Vision-Language Costmaps for Robot Social Navigation}}, author = {Yuwen Liao and Yihang Lan and Yizhuo Yang and Ruimeng Liu and Xinhang Xu and Shenghai Yuan and Lihua Xie}, year = {2026}, eprint = {2607.16956}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.16956}, } @misc{llontop2026messynav, title = {{MessyNav: Zero-Shot Navigation via Manipulation in Messy Environments}}, author = {Kenneth Llontop and Cherie Ho and Dylan Zhou and Anuva Banwasi and Priya Sundaresan and Carlota Parés-Morlans and Jeannette Bohg}, year = {2026}, eprint = {2611.07417}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.07417}, } @misc{banwasi2026messymem, title = {{MessyMem: Learning-from-Doing Memory for Mobile Manipulation}}, author = {Anuva Banwasi and William Muckelroy and Priya Sundaresan and Linfeng Zhao and Jeannette Bohg and Cherie Ho}, year = {2026}, eprint = {2609.15976}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.15976}, } @misc{li2026safe, title = {{Safe Task Planning with Long-Term Graph Memory for Embodied Agents}}, author = {Siyuan Li and Taiyan Lang and Aoqi Yan and Jia Yu and Feifan Liu and Yihan Du and Yu Zheng and Xun Wang and Peng Liu}, year = {2026}, eprint = {2609.08444}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.08444}, } @misc{tsoi2026stars, title = {{STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction}}, author = {Nathan Tsoi and Michael J. Munje and Tejas Oberoi and Rishab Maheshwari and Pengen Zheng and Tanush Chauhan and Peter Stone and Joydeep Biswas}, year = {2026}, eprint = {2609.40245}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.40245}, } @misc{liu2026incom, title = {{InCoM: Intent-Driven Perception and Structured Coordination for Mobile Manipulation}}, author = {Jiahao Liu and Cui Wenbo and Zhongpu Xia and Yongliang Wang and Haoran Li and Dongbin Zhao}, year = {2026}, eprint = {2602.23024}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.23024}, } @misc{lee2026agentic, title = {{An Agentic Framework for Proactive Robots with Procedural Assistance Memory}}, author = {Dohyun Lee and Minho Park and Jeonghoon Park and Dongyoon Hwang and Junha Hyung and Sungwon Hwang and Byungkun Lee and Jaegul Choo}, year = {2026}, eprint = {2610.21211}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.21211}, } @misc{qiu2026look, title = {{Look Before You Move: Agent-Interface-Aligned Supervision for Open-World Mobile Manipulation}}, author = {Ronghe Qiu and Teli Ma and Jiaming Zhou and Zeying Gong and Yiting He and Qiang Huang and Junwei Liang}, year = {2026}, eprint = {2610.15572}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.15572}, } @misc{phoompho2026task, title = {{Task-Aware Environment Augmentation for Reliable Navigation via Shielded Conditional Diffusion}}, author = {Bharawee Phoompho and Gokul Puthumanaillam and Yan Miao and Ruben Hernandez and Tim Bretl and Sayan Mitra and Melkior Ornik}, year = {2026}, eprint = {2606.15154}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15154}, } @misc{bai2026robots, title = {{Robots as Tokens: Unified Diffusion Transformer for Coordinated Multi-Robot Trajectory Generation}}, author = {Ruofei Bai and Jie Chen and Yuxin Cai and Jun Li and Wei-Yun Yau and Lihua Xie}, year = {2026}, eprint = {2606.15550}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.15550}, } @misc{wang2026cosmo, title = {{CoSMO: Conformal Semantic Mapping for Open-World Safe Robot Navigation}}, author = {Shuqi Wang and Yiwei Zheng and Pingrui Zhang and Yue Gao and Xiang Yin}, year = {2026}, eprint = {2610.18321}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18321}, } @misc{yang2026x, title = {{X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching}}, author = {Tianyu Yang and Yiming Zeng and Wenzhe Cai and Yuqiang Yang and Jiaqi Peng and Hui Cheng and Jiangmiao Pang and Tai Wang}, year = {2026}, eprint = {2607.28560}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.28560}, } @misc{wang2026coopuq, title = {{CoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative Forecasting}}, author = {Zehao Wang and Jianpeng Yao and Yuping Wang and Yiping Li and Jiaqi Li and Zhixu Li and Kanghoon Lee and Jinfeng Wang and Cong Liu and Zhaowei Tan and Jinkyoo Park and Jiachen Li}, year = {2026}, eprint = {2610.26852}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26852}, } @misc{suganda2026adaptive, title = {{Adaptive Risk-Certified Event-Triggered Replanning for Dynamic Navigation}}, author = {Richie R. Suganda and Bin Hu}, year = {2026}, eprint = {2610.09302}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.09302}, } @misc{huber2026cool, title = {{COOL: Curiosity-Driven Object Ownership Learning for Personalized Robotic Assistance}}, author = {Samira Huber and Ruben Hammele and Sören Pirk}, year = {2026}, eprint = {2610.09358}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.09358}, } @misc{hong2026seeing, title = {{Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes}}, author = {Seong-Eun Hong and JuYeong Hwang and Jinhyun Kim and Hanyoung Jang and HyeongYeop Kang}, year = {2026}, eprint = {2611.07730}, archivePrefix = {arXiv}, primaryClass = {cs.GR}, url = {https://arxiv.org/abs/2611.07730}, } @misc{peng2025pigeon, title = {{PIGEON: VLM-Driven Object Navigation via Points of Interest Selection}}, author = {Cheng Peng and Zhenzhe Zhang and Xiaobao Wei and Yanhao Zhang and Heng Wang and Pengwei Wang and Zhongyuan Wang and Cheng Chi and Shanghang Zhang and Jing Liu}, year = {2025}, eprint = {2511.13207}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.13207}, } @misc{ji2026navigating, title = {{Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems}}, author = {Jiabao Ji and Yongchao Chen and Yang Zhang and Ramana Rao Kompella and Chuchu Fan and Gaowen Liu and Shiyu Chang}, year = {2026}, eprint = {2604.21138}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.21138}, } @misc{subedi2026lcla, title = {{LCLA: Language-Conditioned Latent Alignment for Vision-Language Navigation}}, author = {Nitesh Subedi and Adam Haroon and Samuel Tetteh and Prajwal Koirala and Cody Fleming and Soumik Sarkar}, year = {2026}, eprint = {2602.07629}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.07629}, } @misc{li2026one, title = {{One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation}}, author = {Zerui Li and Hongpei Zheng and Fangguo Zhao and Aidan Chan and Jian Zhou and Sihao Lin and Shijie Li and Qi Wu}, year = {2026}, eprint = {2602.15400}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.15400}, } @misc{wang2026pathpainter, title = {{PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation}}, author = {Yijin Wang and Yuru Tian and Xijie Huang and Weiqi Gai and Mo Zhu and Xin Zhou and Yuze Wu and Fei Gao}, year = {2026}, eprint = {2605.07496}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.07496}, } @misc{hirose2026asyncvla, title = {{AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge}}, author = {Noriaki Hirose and Catherine Glossop and Dhruv Shah and Sergey Levine}, year = {2026}, eprint = {2602.13476}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.13476}, } @misc{he2026from, title = {{From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation}}, author = {Honglin He and Zhizheng Liu and Yukai Ma and Bolei Zhou}, year = {2026}, eprint = {2606.12603}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12603}, } @misc{shin2026pathlift, title = {{PathLift: Depth-Conditioned Metric Lifting for Visual-Navigation Priors}}, author = {Gwanjun Shin and Hyeongseok Suh and Hongmo Jung and Jongwoo Lim}, year = {2026}, eprint = {2610.16103}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16103}, } @misc{cai2026intentnav, title = {{IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations}}, author = {Yuxin Cai and Zongtai Li and Maonan Wang and Muyi Bao and Haokun Zhu and Ruofei Bai and Ding Zhao and Zirui Li and Wenshan Wang and Wei-Yun Yau and Ji Zhang and Chen Lv}, year = {2026}, eprint = {2606.08029}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08029}, } @misc{yang2026wam, title = {{WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation}}, author = {Ning Yang and Yan Huang and Kaiwen Peng and Ziheng He and Kai Wang and Cui Miao and Kailin Lyu and Guo Li and Xiaofeng Wang and Zheng Zhu and Jing Liu and Nianfeng Liu}, year = {2026}, eprint = {2606.04907}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.04907}, } @misc{liang2026glst, title = {{GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation}}, author = {Yousef Liang and Ryan Ardalan and Yarden Goraly and Chenhao Zhu and Yue Yin and Jonas Frey and Claire Tomlin and Marco Pavone and Shankar Sastry}, year = {2026}, eprint = {2610.17927}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17927}, } @misc{he2025schr, title = {{Schrödinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation}}, author = {Yu He and Da Huang and Zhenyang Liu and Zixiao Gu and Qiang Sun and Guangnan Ye and Yanwei Fu and Yu-Gang Jiang}, year = {2025}, eprint = {2512.21201}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.21201}, } @misc{nukapotula2026evoplan, title = {{EvoPlan: Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees}}, author = {Bhavya Sai Nukapotula and Samin Moosavi and Haoze Wang and Luke Duncan and Diya Shakkottai and Varun Murali and Srinivas Shakkottai}, year = {2026}, eprint = {2607.06724}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.06724}, } @misc{feng2026future, title = {{Future-Aware Flow Planning for Safe UAV Target Following}}, author = {Boning Feng and Haoran Zhang and Xiaowen Bi and Yanzhen Zhang and Xiaodan Shi}, year = {2026}, eprint = {2609.10166}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.10166}, } @misc{feng2026training, title = {{Training Generalist Navigation Policies via Action Self-Distillation}}, author = {Bowen Feng and Keqin Wang and Yulong Yang and Amogh Joshi and Christine Allen-Blanchette and Dhruv Shah and Felix Heide}, year = {2026}, eprint = {2610.17593}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17593}, } @misc{bianco2026learning, title = {{Learning Visuomotor Quadrotor Flight Through Dynamic Narrow Gaps via Differentiable Simulation}}, author = {Riccardo Bianco and Yunfan Ren and Jiaxu Xing and Davide Scaramuzza}, year = {2026}, eprint = {2610.37557}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37557}, } @misc{rodriguez2026acrorl, title = {{AcroRL: Learning Aggressive Quadrotor Inversion using Bidirectional Thrust}}, author = {Gabriel Rodriguez and Henri Sayag and Abhishek Rathod and John Stecklein and Siddharth Saha and Christopher Barngrover and Wennie Tabib}, year = {2026}, eprint = {2605.24301}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.24301}, } @misc{messikommer2026approximate, title = {{Approximate Imitation Learning for Event-based Quadrotor Flight in Cluttered Environments}}, author = {Nico Messikommer and Jiaxu Xing and Leonard Bauersfeld and Marco Cannici and Elie Aljalbout and Davide Scaramuzza}, year = {2026}, eprint = {2603.07578}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.07578}, } @misc{chen2026cpnav, title = {{CPNav: Calibrated Vision-Language Navigation for Object-Goal Search in Unseen Environments}}, author = {Qizhao Chen and Yuanhong Zeng and Shoh Nishino and Anushri Dixit}, year = {2026}, eprint = {2611.10366}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10366}, } @misc{liang2026mosu, title = {{MOSU2: Long-range Navigation System with Multi-modal Scene Understanding}}, author = {Jing Liang and Zhenyu Hou and Senthurbavan Kirubaharan and Md Safwan Mondal and Ashok Gudivada and Xuesu Xiao and Dinesh Manocha}, year = {2026}, eprint = {2611.11148}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.11148}, } @misc{campos2020orb, title = {{ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM}}, author = {Carlos Campos and Richard Elvira and Juan J. Gómez Rodríguez and José M. M. Montiel and Juan D. Tardós}, year = {2020}, eprint = {2007.11898}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2007.11898}, } @misc{shan2020lio, title = {{LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping}}, author = {Tixiao Shan and Brendan Englot and Drew Meyers and Wei Wang and Carlo Ratti and Daniela Rus}, year = {2020}, eprint = {2007.00258}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2007.00258}, } @misc{xu2021fast, title = {{FAST-LIO2: Fast Direct LiDAR-inertial Odometry}}, author = {Wei Xu and Yixi Cai and Dongjiao He and Jiarong Lin and Fu Zhang}, year = {2021}, eprint = {2107.06829}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2107.06829}, } @misc{teed2021droid, title = {{DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras}}, author = {Zachary Teed and Jia Deng}, year = {2021}, eprint = {2108.10869}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2108.10869}, } @misc{matsuki2023gaussian, title = {{Gaussian Splatting SLAM}}, author = {Hidenobu Matsuki and Riku Murai and Paul H. J. Kelly and Andrew J. Davison}, year = {2023}, eprint = {2312.06741}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2312.06741}, } @misc{wang2023dust, title = {{DUSt3R: Geometric 3D Vision Made Easy}}, author = {Shuzhe Wang and Vincent Leroy and Yohann Cabon and Boris Chidlovskii and Jerome Revaud}, year = {2023}, eprint = {2312.14132}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2312.14132}, } @misc{wang2025vggt, title = {{VGGT: Visual Geometry Grounded Transformer}}, author = {Jianyuan Wang and Minghao Chen and Nikita Karaev and Andrea Vedaldi and Christian Rupprecht and David Novotny}, year = {2025}, eprint = {2503.11651}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2503.11651}, } @misc{wen2023foundationpose, title = {{FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects}}, author = {Bowen Wen and Wei Yang and Jan Kautz and Stan Birchfield}, year = {2023}, eprint = {2312.08344}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2312.08344}, } @misc{yang2024depth, title = {{Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}}, author = {Lihe Yang and Bingyi Kang and Zilong Huang and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao}, year = {2024}, eprint = {2401.10891}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2401.10891}, } @misc{gu2023conceptgraphs, title = {{ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning}}, author = {Qiao Gu and Alihusein Kuwajerwala and Sacha Morin and Krishna Murthy Jatavallabhula and Bipasha Sen and Aditya Agarwal and Corban Rivera and William Paul and Kirsty Ellis and Rama Chellappa and Chuang Gan and Celso Miguel de Melo and Joshua B. Tenenbaum and Antonio Torralba and Florian Shkurti and Liam Paull}, year = {2023}, eprint = {2309.16650}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.16650}, } @misc{kirillov2023segment, title = {{Segment Anything}}, author = {Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick}, year = {2023}, eprint = {2304.02643}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2304.02643}, } @misc{ravi2024sam, title = {{SAM 2: Segment Anything in Images and Videos}}, author = {Nikhila Ravi and Valentin Gabeur and Yuan-Ting Hu and Ronghang Hu and Chaitanya Ryali and Tengyu Ma and Haitham Khedr and Roman Rädle and Chloe Rolland and Laura Gustafson and Eric Mintun and Junting Pan and Kalyan Vasudev Alwala and Nicolas Carion and Chao-Yuan Wu and Ross Girshick and Piotr Dollár and Christoph Feichtenhofer}, year = {2024}, eprint = {2408.00714}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2408.00714}, } @misc{liu2023grounding, title = {{Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection}}, author = {Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Qing Jiang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang}, year = {2023}, eprint = {2303.05499}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2303.05499}, } @misc{wen2025foundationstereo, title = {{FoundationStereo: Zero-Shot Stereo Matching}}, author = {Bowen Wen and Matthew Trepte and Joseph Aribido and Jan Kautz and Orazio Gallo and Stan Birchfield}, year = {2025}, eprint = {2501.09898}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2501.09898}, } @misc{liu2026sparv, title = {{SpaRV: Sparse Radiance Voxels for Scalable Geometrically Consistent LiDAR-Visual Mapping and Rendering}}, author = {Jianheng Liu and Yunfei Wan and Fangming Cheng and Xiangyu Hong and Zuhao Zou and Haotian Li and Longji Yin and Chunran Zheng and Jiarong Lin and Fu Zhang}, year = {2026}, eprint = {2610.25665}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25665}, } @misc{jiang2026vision, title = {{Vision as Proprioception: Estimating Humanoid Robot Pose from Video}}, author = {Jiaxi Jiang and Matthias Heyrman and René Zurbrügg and Marco Hutter and Christian Holz}, year = {2026}, eprint = {2610.25288}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25288}, } @misc{jiang2026which, title = {{Which Depth Estimator for Jetson AGX Orin? A 2026 Benchmark of Monocular and Stereo Methods}}, author = {Leaf Jiang}, year = {2026}, eprint = {2610.27199}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27199}, } @misc{oquab2023dinov, title = {{DINOv2: Learning Robust Visual Features without Supervision}}, author = {Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski}, year = {2023}, eprint = {2304.07193}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2304.07193}, } @misc{karaev2023cotracker, title = {{CoTracker: It is Better to Track Together}}, author = {Nikita Karaev and Ignacio Rocco and Benjamin Graham and Natalia Neverova and Andrea Vedaldi and Christian Rupprecht}, year = {2023}, eprint = {2307.07635}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2307.07635}, } @misc{leroy2024grounding, title = {{Grounding Image Matching in 3D with MASt3R}}, author = {Vincent Leroy and Yohann Cabon and Jérôme Revaud}, year = {2024}, eprint = {2406.09756}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2406.09756}, } @misc{zheng2024fast, title = {{FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry}}, author = {Chunran Zheng and Wei Xu and Zuhao Zou and Tong Hua and Chongjian Yuan and Dongjiao He and Bingyang Zhou and Zheng Liu and Jiarong Lin and Fangcheng Zhu and Yunfan Ren and Rong Wang and Fanle Meng and Fu Zhang}, year = {2024}, eprint = {2408.14035}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2408.14035}, } @misc{yang2024depth, title = {{Depth Anything V2}}, author = {Lihe Yang and Bingyi Kang and Zilong Huang and Zhen Zhao and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao}, year = {2024}, eprint = {2406.09414}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2406.09414}, } @misc{wen2023bundlesdf, title = {{BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects}}, author = {Bowen Wen and Jonathan Tremblay and Valts Blukis and Stephen Tyree and Thomas Muller and Alex Evans and Dieter Fox and Jan Kautz and Stan Birchfield}, year = {2023}, eprint = {2303.14158}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2303.14158}, } @misc{wang2026ace, title = {{ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models}}, author = {Yinhe Wang and Tao Tao and Zexin He and Shuang Luo and Wei Mao and Yao Mu and Feng Pan and Hanming Deng and Lewei Lu and Zhi Hou and Xingang Pan and Dahua Lin and Dacheng Tao and Xiaogang Wang}, year = {2026}, eprint = {2610.27040}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27040}, } @misc{carion2025sam, title = {{SAM 3: Segment Anything with Concepts}}, author = {Nicolas Carion and Laura Gustafson and Yuan-Ting Hu and Shoubhik Debnath and Ronghang Hu and Didac Suris and Chaitanya Ryali and Kalyan Vasudev Alwala and Haitham Khedr and Andrew Huang and Jie Lei and Tengyu Ma and Baishan Guo and Arpit Kalla and Markus Marks and Joseph Greer and Meng Wang and Peize Sun and Roman Rädle and Triantafyllos Afouras and Effrosyni Mavroudi and Katherine Xu and Tsung-Han Wu and Yu Zhou and Liliane Momeni and Rishi Hazra and Shuangrui Ding and Sagar Vaze and Francois Porcher and Feng Li and Siyuan Li and Aishwarya Kamath and Ho Kei Cheng and Piotr Dollár and Nikhila Ravi and Kate Saenko and Pengchuan Zhang and Christoph Feichtenhofer}, year = {2025}, eprint = {2511.16719}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2511.16719}, } @misc{choi2026openvio, title = {{OpenVIO: A Versatile Open-Source Visual-Inertial Odometry System}}, author = {Seungwon Choi}, year = {2026}, eprint = {2610.41671}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41671}, } @misc{tao2026anchor, title = {{Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping}}, author = {Peilin Tao and Chong Cheng and Yuansen Du and Caiwei Song and Zhengqing Chen and Xiaoyang Guo and Wei Yin and Weiqiang Ren and Qian Zhang and Hainan Cui and Shuhan Shen}, year = {2026}, eprint = {2606.05035}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.05035}, } @misc{hwang2026anchorhec, title = {{AnchorHEC: Targetless Hand-Eye Calibration of Wrist and Fixed Cameras}}, author = {Guebin Hwang and Taeyeop Lee and Yeonseo Lee and Hyosup Shin and Sungho Jo}, year = {2026}, eprint = {2611.02884}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02884}, } @misc{rosinol2019kimera, title = {{Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping}}, author = {Antoni Rosinol and Marcus Abate and Yun Chang and Luca Carlone}, year = {2019}, eprint = {1910.02490}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1910.02490}, } @misc{zou2026mosaicimu, title = {{MosaicIMU: Composing Carrier Experts for Generalizable Neural Inertial Odometry}}, author = {Junye Zou and Huiyi Yan and Xinning Xu and Xiaolei Li and Pengkun Zhou and Jinhui Zhang and Ziyang Meng}, year = {2026}, eprint = {2606.09355}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.09355}, } @misc{buchner2026articulated, title = {{Articulated 3D Scene Graphs for Open-World Mobile Manipulation}}, author = {Martin Büchner and Adrian Röfer and Tim Engelbracht and Tim Welschehold and Zuria Bauer and Hermann Blum and Marc Pollefeys and Abhinav Valada}, year = {2026}, eprint = {2602.16356}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.16356}, } @misc{wang2026corematch, title = {{CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching}}, author = {Robert J. Wang and Charles Ling and Boyu Wang}, year = {2026}, eprint = {2611.03932}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03932}, } @misc{shafiullah2022clip, title = {{CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory}}, author = {Nur Muhammad Mahi Shafiullah and Chris Paxton and Lerrel Pinto and Soumith Chintala and Arthur Szlam}, year = {2022}, eprint = {2210.05663}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2210.05663}, } @misc{cai2024spatialbot, title = {{SpatialBot: Precise Spatial Understanding with Vision Language Models}}, author = {Wenxiao Cai and Iaroslav Ponomarenko and Jianhao Yuan and Xiaoqi Li and Wankou Yang and Hao Dong and Bo Zhao}, year = {2024}, eprint = {2406.13642}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2406.13642}, } @misc{zhou2025roborefer, title = {{RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics}}, author = {Enshen Zhou and Jingkun An and Cheng Chi and Yi Han and Shanyu Rong and Chi Zhang and Pengwei Wang and Zhongyuan Wang and Tiejun Huang and Lu Sheng and Shanghang Zhang}, year = {2025}, eprint = {2506.04308}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.04308}, } @misc{zhou2025towards, title = {{Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics}}, author = {Enshen Zhou and Yibo Li and Jingkun An and Jiayuan Zhang and Shanyu Rong and Mengzhen Liu and Yi Han and Yuheng Ji and Huajie Tan and Jiawei He and Pengwei Wang and Zhongyuan Wang and Cheng Chi and Lu Sheng and Shanghang Zhang}, year = {2025}, eprint = {2512.13660}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2512.13660}, } @misc{hu2026functional, title = {{Functional-SLAM: Interaction-Aware Mapping with Online Functional Scene Graphs}}, author = {Xinggang Hu and Chenyangguang Zhang and Zihan Zhu and Ruida Zhang and Xiangkui Zhang and Xiangyang Ji}, year = {2026}, eprint = {2609.07497}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.07497}, } @misc{gao2026cyclops, title = {{Cyclops: LiDAR as a Camera That Dreams in Color}}, author = {Wei Gao and Jian Shu and Mingle Zhao and Maani Ghaffari and David Kong and Chengzhong Xu and Hui Kong}, year = {2026}, eprint = {2608.16264}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.16264}, } @misc{schwaiger2026resireg, title = {{ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks}}, author = {Simon Schwaiger and David Seyser and Alessandro Scherl and Wilfried Wöber and Gerald Steinbauer-Wagner}, year = {2026}, eprint = {2606.19088}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.19088}, } @misc{peng2026freeloc, title = {{FreeLoc: Online Floorplan Localization via Diffusion-Aided Pose Refinement}}, author = {Haocheng Peng and Boyang Zhou and Jiarui Hu and Xiyue Guo and Ziyang Zhang and Boming Zhao and Yifan Gao and Xiao Li and Hujun Bao and Zhaopeng Cui}, year = {2026}, eprint = {2610.05011}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.05011}, } @misc{siva2026what, title = {{What Objects Enable, Not What They Are: Functional Latent Spaces for Affordance Reasoning}}, author = {Rohan Siva and Neel P. Bhatt and Yunhao Yang and Seoyoung Lee and Nishant Gadde and Christian Ellis and Alvaro Velasquez and Zhangyang Wang and Ufuk Topcu}, year = {2026}, eprint = {2606.05533}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2606.05533}, } @misc{liu2026optigeo, title = {{OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes}}, author = {Muxin Liu and Tianbo Liu and Jing Xia and Xiaoyang Lyu and Xiaoshan Wu and Bo Wang and Peng Dai and Zhongrui Wang and Shaoshuai Shi and Xiaojuan Qi}, year = {2026}, eprint = {2608.29881}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2608.29881}, } @misc{naveen2026language, title = {{Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language}}, author = {Aryan Naveen and Jason Xinyu Liu and Luca Carlone and Andreea Bobu}, year = {2026}, eprint = {2606.08666}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08666}, } @misc{zhao2026aurora, title = {{AURORA: Active Uncertainty-Driven Re-Orientation for In-Hand Reconstruction}}, author = {Feiyu Zhao and Yuetong Li and Chenxi Xiao}, year = {2026}, eprint = {2609.08493}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.08493}, } @misc{cao2026fast, title = {{Fast and Accurate Hand Estimation in Pixels, Interaction and World Space}}, author = {Jinkun Cao}, year = {2026}, eprint = {2611.07711}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2611.07711}, } @misc{wei2026g, title = {{G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation}}, author = {Yufei Wei and Shuhao Ye and Chenxiao Hu and Yiyuan Pan and Dongyu Feng and Rong Xiong and Yue Wang and Yanmei Jiao}, year = {2026}, eprint = {2606.08284}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.08284}, } @misc{shin2026learning, title = {{Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups}}, author = {Jaeho Shin and Maani Ghaffari and Yulun Tian}, year = {2026}, eprint = {2607.08735}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.08735}, } @misc{kim2026ginio, title = {{GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry}}, author = {Chankyo Kim and Minghan Zhu and Tzu-Yuan Lin and Avantika Rattan and Maani Ghaffari}, year = {2026}, eprint = {2609.25338}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.25338}, } @misc{sun2026lime, title = {{LIME: Learning Intent-aware Camera Motion from Egocentric Video}}, author = {Boyang Sun and Jiajie Li and Yung-Hsu Yang and Chenyangguang Zhang and Tim Engelbracht and Sunghwan Hong and Cesar Cadena and Marc Pollefeys and Hermann Blum}, year = {2026}, eprint = {2607.02417}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.02417}, } @misc{omama2026latematch, title = {{LateMatch: Breaking the Interaction Bottleneck via Cacheable Matching for Efficient Visual Localization}}, author = {Mohammad Omama and Aeyan Ashraf and Sandeep Chinchali}, year = {2026}, eprint = {2610.25358}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.25358}, } @misc{jung2026romo, title = {{RoMo-GS: Efficient Online 3D Gaussian Splatting for Robot Mapping via Exposure-Integrated Motion Blur}}, author = {Sangwoo Jung and Di Deng and Jiahui Fu and Laura Herlant and Ayoung Kim and Yafei Hu}, year = {2026}, eprint = {2610.24605}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.24605}, } @misc{sun2026voxafford, title = {{VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection}}, author = {Haowen Sun and Shaolong Zhang and Mingyang Li and Chengzhong Ma and Xinzhe Chen and Qiongjie Cui and Xingyu Chen and Zeyang Liu and Xuguang Lan}, year = {2026}, eprint = {2605.01365}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2605.01365}, } @misc{chen2026prose, title = {{PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models}}, author = {Zhiang Chen and Nahyuk Lee and Boyang Sun and Taein Kwon and Marc Pollefeys and Zuria Bauer and Sunghwan Hong}, year = {2026}, eprint = {2606.16569}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2606.16569}, } @misc{sundaralingam2023curobo, title = {{cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation}}, author = {Balakumar Sundaralingam and Siva Kumar Sastry Hari and Adam Fishman and Caelan Garrett and Karl Van Wyk and Valts Blukis and Alexander Millane and Helen Oleynikova and Ankur Handa and Fabio Ramos and Nathan Ratliff and Dieter Fox}, year = {2023}, eprint = {2310.17274}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2310.17274}, } @misc{fishman2022motion, title = {{Motion Policy Networks}}, author = {Adam Fishman and Adithyavairan Murali and Clemens Eppner and Bryan Peele and Byron Boots and Dieter Fox}, year = {2022}, eprint = {2210.12209}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2210.12209}, } @misc{janner2022planning, title = {{Planning with Diffusion for Flexible Behavior Synthesis}}, author = {Michael Janner and Yilun Du and Joshua B. Tenenbaum and Sergey Levine}, year = {2022}, eprint = {2205.09991}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2205.09991}, } @misc{ames2019control, title = {{Control Barrier Functions: Theory and Applications}}, author = {Aaron D. Ames and Samuel Coogan and Magnus Egerstedt and Gennaro Notomista and Koushil Sreenath and Paulo Tabuada}, year = {2019}, eprint = {1903.11199}, archivePrefix = {arXiv}, primaryClass = {eess.SY}, url = {https://arxiv.org/abs/1903.11199}, } @misc{brunke2021safe, title = {{Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning}}, author = {Lukas Brunke and Melissa Greeff and Adam W. Hall and Zhaocong Yuan and Siqi Zhou and Jacopo Panerati and Angela P. Schoellig}, year = {2021}, eprint = {2108.06266}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2108.06266}, } @misc{yuan2021safe, title = {{safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics}}, author = {Zhaocong Yuan and Adam W. Hall and Siqi Zhou and Lukas Brunke and Melissa Greeff and Jacopo Panerati and Angela P. Schoellig}, year = {2021}, eprint = {2109.06325}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2109.06325}, } @misc{mastalli2019crocoddyl, title = {{Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control}}, author = {Carlos Mastalli and Rohan Budhiraja and Wolfgang Merkt and Guilhem Saurel and Bilal Hammoud and Maximilien Naveau and Justin Carpentier and Ludovic Righetti and Sethu Vijayakumar and Nicolas Mansard}, year = {2019}, eprint = {1909.04947}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1909.04947}, } @misc{verschueren2019acados, title = {{acados: a modular open-source framework for fast embedded optimal control}}, author = {Robin Verschueren and Gianluca Frison and Dimitris Kouzoupis and Jonathan Frey and Niels van Duijkeren and Andrea Zanelli and Branimir Novoselnik and Thivaharan Albin and Rien Quirynen and Moritz Diehl}, year = {2019}, eprint = {1910.13753}, archivePrefix = {arXiv}, primaryClass = {math.OC}, url = {https://arxiv.org/abs/1910.13753}, } @misc{skerlj2026sub, title = {{Sub-Millisecond Reflexes for Continuous Physical Human-Robot Interaction}}, author = {Jon Škerlj and Sami Haddadin}, year = {2026}, eprint = {2610.21913}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.21913}, } @misc{wu2026prismplan, title = {{PrismPlan: A Shared GPU Substrate for Motion Planning Across Paradigms}}, author = {Hong Wu and ChaoXuan Liu and ShuJie Wang}, year = {2026}, eprint = {2610.23884}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.23884}, } @misc{howell2022predictive, title = {{Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo}}, author = {Taylor Howell and Nimrod Gileadi and Saran Tunyasuvunakool and Kevin Zakka and Tom Erez and Yuval Tassa}, year = {2022}, eprint = {2212.00541}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2212.00541}, } @misc{viljoen2026cusadi, title = {{CusADi2: Latency-Optimized Batch Computation of Robot Kinematics, Jacobians, and Hessians on the GPU}}, author = {John Viljoen and Lasse Peters and Masayoshi Tomizuka and Negar Mehr}, year = {2026}, eprint = {2610.25476}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25476}, } @misc{stellato2017osqp, title = {{OSQP: An Operator Splitting Solver for Quadratic Programs}}, author = {Bartolomeo Stellato and Goran Banjac and Paul Goulart and Alberto Bemporad and Stephen Boyd}, year = {2017}, eprint = {1711.08013}, archivePrefix = {arXiv}, primaryClass = {math.OC}, url = {https://arxiv.org/abs/1711.08013}, } @misc{thomason2023motions, title = {{Motions in Microseconds via Vectorized Sampling-Based Planning}}, author = {Wil Thomason and Zachary Kingston and Lydia E. Kavraki}, year = {2023}, eprint = {2309.14545}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.14545}, } @misc{ratliff2018riemannian, title = {{Riemannian Motion Policies}}, author = {Nathan D. Ratliff and Jan Issac and Daniel Kappler and Stan Birchfield and Dieter Fox}, year = {2018}, eprint = {1801.02854}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1801.02854}, } @misc{bansal2017hamilton, title = {{Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances}}, author = {Somil Bansal and Mo Chen and Sylvia Herbert and Claire J. Tomlin}, year = {2017}, eprint = {1709.07523}, archivePrefix = {arXiv}, primaryClass = {eess.SY}, url = {https://arxiv.org/abs/1709.07523}, } @misc{berscheid2021jerk, title = {{Jerk-limited Real-time Trajectory Generation with Arbitrary Target States}}, author = {Lars Berscheid and Torsten Kröger}, year = {2021}, eprint = {2105.04830}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2105.04830}, } @misc{lee2026keeping, title = {{Keeping Contact: Task-Adaptive Friction Margins for Bimanual Non-Prehensile Manipulation}}, author = {Qian Ying Lee and Lin Yang and Domenico Campolo}, year = {2026}, eprint = {2610.36961}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36961}, } @misc{wang2026generalist, title = {{A generalist policy for muscle-driven control across individual musculoskeletal models}}, author = {Bozhao Wang and Yinglei Zhu and Zhengqing Li and Zhiyuan Zhang and Weiming Kang and Yiheng He and XinJun Liu and Senhao Hou and Huichan Zhao and Xiaoqiang Tang}, year = {2026}, eprint = {2610.36535}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36535}, } @misc{son2026tam, title = {{TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation}}, author = {Dongwon Son and Florian Shkurti and Jason Lee and Naman Shah and Beomjoon Kim and Dieter Fox}, year = {2026}, eprint = {2606.06218}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.06218}, } @misc{walter2026ram, title = {{RAM: Reachability Across Morphologies}}, author = {Tim Walter and Xinyu Chen and Jonathan Külz and Matthias Althoff}, year = {2026}, eprint = {2606.09108}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.09108}, } @misc{liu2026policyik, title = {{PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning}}, author = {Yuhan Liu and Xinqi Liu and Zixuan Dong and Keith W. Ross and Shenji Wan}, year = {2026}, eprint = {2611.05372}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05372}, } @misc{oshin2026scalable, title = {{Scalable Deep Unfolding of Conic Optimizers}}, author = {Alex Oshin and Rahul Vodeb Ghosh and Evangelos A. Theodorou}, year = {2026}, eprint = {2606.13825}, archivePrefix = {arXiv}, primaryClass = {math.OC}, url = {https://arxiv.org/abs/2606.13825}, } @misc{sundaralingam2026curobov, title = {{cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots}}, author = {Balakumar Sundaralingam and Adithyavairavan Murali and Stan Birchfield}, year = {2026}, eprint = {2603.05493}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.05493}, } @misc{kim2025pyroki, title = {{PyRoki: A Modular Toolkit for Robot Kinematic Optimization}}, author = {Chung Min Kim and Brent Yi and Hongsuk Choi and Yi Ma and Ken Goldberg and Angjoo Kanazawa}, year = {2025}, eprint = {2505.03728}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.03728}, } @misc{johannsmeier2026pakt, title = {{PAKT: Physically-Aligned Kinesthetic Teaching for Reinforcement Learning}}, author = {Lars Johannsmeier and Yashraj Narang}, year = {2026}, eprint = {2609.25630}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.25630}, } @misc{jang2026safe, title = {{Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics}}, author = {Seunghwan Jang and Jeongyong Yang and Siddharth Ancha and SooJean Han}, year = {2026}, eprint = {2610.03132}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.03132}, } @misc{garcia2026exploring, title = {{Exploring the Intrinsic Geometry of Diffusion Models with Constrained Inverse Kinematics}}, author = {Miguel Angel Rogel Garcia and Phone Thiha Kyaw and Jonathan Kelly}, year = {2026}, eprint = {2606.26408}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26408}, } @misc{krishna2026lemca, title = {{LEMCA: LLM-Guided Synthesis of Efficient Mode-Switching Control Architectures}}, author = {Arjun Krishna and Vincent Pacelli and Dinesh Jayaraman}, year = {2026}, eprint = {2609.21319}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.21319}, } @misc{lee2026prism, title = {{PRISM: Polynomial Representations for Interaction-Structured Motor Control}}, author = {Seung Hyun Lee and Stella X. Yu}, year = {2026}, eprint = {2607.23473}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.23473}, } @misc{yang2026tdc, title = {{TDC: Sim-to-Real Transferable Directional Compliance for Contact-Rich Manipulation}}, author = {Yifei Yang and Anzhe Chen and Zhenjie Zhu and Kechun Xu and Yunxuan Mao and Yufei Wei and Lu Chen and Rong Xiong and Yue Wang}, year = {2026}, eprint = {2602.14174}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.14174}, } @misc{sun2026m, title = {{M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation}}, author = {Xingpeng Sun and Zherong Pan and Kai Cheng and Xindi Tang and Syed Talha Bukhari and Aniket Bera}, year = {2026}, eprint = {2609.18669}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.18669}, } @misc{feng2026gradient, title = {{Gradient-Free Neural Hamilton-Jacobi Reachability for Scalable Safety-Critical Control}}, author = {Zeyuan Feng and Ali Fuat Sahin and Santiago Thorup and Somil Bansal}, year = {2026}, eprint = {2609.14087}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.14087}, } @misc{derajic2026vertexcbf, title = {{VertexCBF: Improving Neural Control Barrier Functions via Vertex-Restricted Control Search}}, author = {Bojan Derajić and Sebastian Bernhard and Wolfgang Hönig}, year = {2026}, eprint = {2609.12831}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.12831}, } @misc{chauhan2026barrierformer, title = {{BarrierFormer: Transformer-Guided Predictive Barrier Enforcement for Safe Robot Control}}, author = {Anandsingh Chauhan and Kunal Garg}, year = {2026}, eprint = {2609.23896}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.23896}, } @misc{yoon2026learning, title = {{Learning Unions of Convex Sets via Invertible Latent Decomposition for Path Planning}}, author = {Taerim Yoon and Dongho Kang and Kisang Park and Junha Cha and Stelian Coros and Sungjoon Choi}, year = {2026}, eprint = {2606.12027}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12027}, } @misc{musavi2026when, title = {{When Should a Robot Replan? Regret-Guided Update Scheduling in Time-Varying MDPs}}, author = {Negin Musavi and Gokul Puthumanaillam and Ruben Hernandez and William Schafer and Melkior Ornik}, year = {2026}, eprint = {2606.16972}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16972}, } @misc{liu2026limits, title = {{On the Limits of Sampling-Based Reachability: Geometry, Dynamics, and Sample Complexity}}, author = {Jixian Liu and Ihab Tabbara and Hussein Sibai and Enrique Mallada}, year = {2026}, eprint = {2607.18606}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.18606}, } @misc{schoch2026optimal, title = {{Optimal Control with Learned Critics under Unmodeled State Dependencies}}, author = {Philipp Schoch and Markus Ryll}, year = {2026}, eprint = {2610.05359}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.05359}, } @misc{caron2026koopman, title = {{Koopman DCM: Unstable Eigenfunctions as Data-driven Representations for Legged Balancing}}, author = {Stéphane Caron}, year = {2026}, eprint = {2607.18760}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.18760}, } @misc{chen2026reachability, title = {{$λ$-Reachability: Geometric-Horizon Safety Bellman Equations for Humanoid Safety}}, author = {Rui Chen and Shangtao Li and Yifan Sun and Changliu Liu}, year = {2026}, eprint = {2606.16022}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16022}, } @misc{xing2026mpc, title = {{MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins}}, author = {Roy Xing and Seyoung Ree and Brian Plancher}, year = {2026}, eprint = {2606.26392}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.26392}, } @misc{trisovic2026vigor, title = {{VIGOR-MPC: Vision-Guided Objective Regulation MPC}}, author = {Jelena Trisovic and Rahel Rickenbach and Marek Landert and Panagiotis Minos and Melanie N. Zeilinger}, year = {2026}, eprint = {2610.20333}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.20333}, } @misc{garrett2026sampling, title = {{Sampling-based Model Predictive Control as Sequential Monte Carlo Inference}}, author = {Austin Garrett and Muyang Yan and Zachary Kingston}, year = {2026}, eprint = {2611.10877}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10877}, } @misc{schulman2017proximal, title = {{Proximal Policy Optimization Algorithms}}, author = {John Schulman and Filip Wolski and Prafulla Dhariwal and Alec Radford and Oleg Klimov}, year = {2017}, eprint = {1707.06347}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1707.06347}, } @misc{haarnoja2018soft, title = {{Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor}}, author = {Tuomas Haarnoja and Aurick Zhou and Pieter Abbeel and Sergey Levine}, year = {2018}, eprint = {1801.01290}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1801.01290}, } @misc{ross2010reduction, title = {{A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning}}, author = {Stephane Ross and Geoffrey J. Gordon and J. Andrew Bagnell}, year = {2010}, eprint = {1011.0686}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1011.0686}, } @misc{ball2023efficient, title = {{Efficient Online Reinforcement Learning with Offline Data}}, author = {Philip J. Ball and Laura Smith and Ilya Kostrikov and Sergey Levine}, year = {2023}, eprint = {2302.02948}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2302.02948}, } @misc{luo2024serl, title = {{SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning}}, author = {Jianlan Luo and Zheyuan Hu and Charles Xu and You Liang Tan and Jacob Berg and Archit Sharma and Stefan Schaal and Chelsea Finn and Abhishek Gupta and Sergey Levine}, year = {2024}, eprint = {2401.16013}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2401.16013}, } @misc{luo2024precise, title = {{Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning}}, author = {Jianlan Luo and Charles Xu and Jeffrey Wu and Sergey Levine}, year = {2024}, eprint = {2410.21845}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.21845}, } @misc{mandlekar2021what, title = {{What Matters in Learning from Offline Human Demonstrations for Robot Manipulation}}, author = {Ajay Mandlekar and Danfei Xu and Josiah Wong and Soroush Nasiriany and Chen Wang and Rohun Kulkarni and Li Fei-Fei and Silvio Savarese and Yuke Zhu and Roberto Martín-Martín}, year = {2021}, eprint = {2108.03298}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2108.03298}, } @misc{kostrikov2021offline, title = {{Offline Reinforcement Learning with Implicit Q-Learning}}, author = {Ilya Kostrikov and Ashvin Nair and Sergey Levine}, year = {2021}, eprint = {2110.06169}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2110.06169}, } @misc{shafiullah2022behavior, title = {{Behavior Transformers: Cloning $k$ modes with one stone}}, author = {Nur Muhammad Mahi Shafiullah and Zichen Jeff Cui and Ariuntuya Altanzaya and Lerrel Pinto}, year = {2022}, eprint = {2206.11251}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2206.11251}, } @misc{ren2024diffusion, title = {{Diffusion Policy Policy Optimization}}, author = {Allen Z. Ren and Justin Lidard and Lars L. Ankile and Anthony Simeonov and Pulkit Agrawal and Anirudha Majumdar and Benjamin Burchfiel and Hongkai Dai and Max Simchowitz}, year = {2024}, eprint = {2409.00588}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.00588}, } @misc{kumar2020conservative, title = {{Conservative Q-Learning for Offline Reinforcement Learning}}, author = {Aviral Kumar and Aurick Zhou and George Tucker and Sergey Levine}, year = {2020}, eprint = {2006.04779}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2006.04779}, } @misc{chen2021decision, title = {{Decision Transformer: Reinforcement Learning via Sequence Modeling}}, author = {Lili Chen and Kevin Lu and Aravind Rajeswaran and Kimin Lee and Aditya Grover and Michael Laskin and Pieter Abbeel and Aravind Srinivas and Igor Mordatch}, year = {2021}, eprint = {2106.01345}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2106.01345}, } @misc{fujimoto2018addressing, title = {{Addressing Function Approximation Error in Actor-Critic Methods}}, author = {Scott Fujimoto and Herke van Hoof and David Meger}, year = {2018}, eprint = {1802.09477}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/1802.09477}, } @misc{ho2016generative, title = {{Generative Adversarial Imitation Learning}}, author = {Jonathan Ho and Stefano Ermon}, year = {2016}, eprint = {1606.03476}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1606.03476}, } @misc{florence2021implicit, title = {{Implicit Behavioral Cloning}}, author = {Pete Florence and Corey Lynch and Andy Zeng and Oscar Ramirez and Ayzaan Wahid and Laura Downs and Adrian Wong and Johnny Lee and Igor Mordatch and Jonathan Tompson}, year = {2021}, eprint = {2109.00137}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2109.00137}, } @misc{nair2020awac, title = {{AWAC: Accelerating Online Reinforcement Learning with Offline Datasets}}, author = {Ashvin Nair and Abhishek Gupta and Murtaza Dalal and Sergey Levine}, year = {2020}, eprint = {2006.09359}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2006.09359}, } @misc{kalashnikov2018qt, title = {{QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation}}, author = {Dmitry Kalashnikov and Alex Irpan and Peter Pastor and Julian Ibarz and Alexander Herzog and Eric Jang and Deirdre Quillen and Ethan Holly and Mrinal Kalakrishnan and Vincent Vanhoucke and Sergey Levine}, year = {2018}, eprint = {1806.10293}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1806.10293}, } @misc{yarats2021mastering, title = {{Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning}}, author = {Denis Yarats and Rob Fergus and Alessandro Lazaric and Lerrel Pinto}, year = {2021}, eprint = {2107.09645}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2107.09645}, } @misc{wagenmaker2025steering, title = {{Steering Your Diffusion Policy with Latent Space Reinforcement Learning}}, author = {Andrew Wagenmaker and Mitsuhiko Nakamoto and Yunchu Zhang and Seohong Park and Waleed Yagoub and Anusha Nagabandi and Abhishek Gupta and Sergey Levine}, year = {2025}, eprint = {2506.15799}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.15799}, } @misc{park2025flow, title = {{Flow Q-Learning}}, author = {Seohong Park and Qiyang Li and Sergey Levine}, year = {2025}, eprint = {2502.02538}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2502.02538}, } @misc{li2025simplevla, title = {{SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning}}, author = {Haozhan Li and Yuxin Zuo and Jiale Yu and Yuhao Zhang and Zhaohui Yang and Kaiyan Zhang and Xuekai Zhu and Yuchen Zhang and Tianxing Chen and Ganqu Cui and Dehui Wang and Dingxiang Luo and Yuchen Fan and Youbang Sun and Jia Zeng and Jiangmiao Pang and Shanghang Zhang and Yu Wang and Yao Mu and Bowen Zhou and Ning Ding}, year = {2025}, eprint = {2509.09674}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2509.09674}, } @misc{nakamoto2023cal, title = {{Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning}}, author = {Mitsuhiko Nakamoto and Yuexiang Zhai and Anikait Singh and Max Sobol Mark and Yi Ma and Chelsea Finn and Aviral Kumar and Sergey Levine}, year = {2023}, eprint = {2303.05479}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2303.05479}, } @misc{chebotar2023q, title = {{Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions}}, author = {Yevgen Chebotar and Quan Vuong and Alex Irpan and Karol Hausman and Fei Xia and Yao Lu and Aviral Kumar and Tianhe Yu and Alexander Herzog and Karl Pertsch and Keerthana Gopalakrishnan and Julian Ibarz and Ofir Nachum and Sumedh Sontakke and Grecia Salazar and Huong T Tran and Jodilyn Peralta and Clayton Tan and Deeksha Manjunath and Jaspiar Singht and Brianna Zitkovich and Tomas Jackson and Kanishka Rao and Chelsea Finn and Sergey Levine}, year = {2023}, eprint = {2309.10150}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.10150}, } @misc{zang2025rlinf, title = {{RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models}}, author = {Hongzhi Zang and Mingjie Wei and Si Xu and Yongji Wu and Zhen Guo and Yuanqing Wang and Hao Lin and Peihong Wang and Liangzhi Shi and Yuqing Xie and Zhexuan Xu and Zhihao Liu and Kang Chen and Wenhao Tang and Quanlu Zhang and Weinan Zhang and Chao Yu and Yu Wang}, year = {2025}, eprint = {2510.06710}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.06710}, } @misc{yu2026learning, title = {{Learning from Fleet Experience: Collective Experience Learning Across 96 Robots}}, author = {Chao Yu and Shu'ang Yu and Hao Lin and Hongzhi Zang and Yuxiang Yan and Chenxi Jiang and Zhen Guo and Chuankang Li and Yihao Chen and Xin Xu and Xu Fu and Jiakai Zhou and Liangzhi Shi and Hongyi Ren and Yiwei Liu and Jing Wu and Yuanqing Wang and Chen Wu and Bo Dai and Chunyu Yang and Hongliang Huang and Shuoyu Yue and Weiqi Yin and Yinuo Chen and Ruihua Chen and Chunyang Zhu and Han Xiao and Yanghao Li and Ruipu Wu and Zhikai Cai and Xiu Chen and Xu Tan and Si Liu and Yuchen Yan and Jialin Zhang and Wen Zeng and Yiming Zhou and Zixiao Huang and Xinlei Chen and Guanghui Ren and Quanlu Zhang and Boxun Li and Maoqing Yao and Yu Wang}, year = {2026}, eprint = {2610.25736}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25736}, } @misc{kim2026accrue, title = {{ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models}}, author = {Changyeon Kim and Kimin Lee and Yashraj Narang and Yijie Guo}, year = {2026}, eprint = {2610.18596}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18596}, } @misc{liu2026agenticroborl, title = {{AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics}}, author = {Xinxin Liu and Bingxin Xu and Wenrui Bao and Ming Li and Wentao Bao and Chen Chen and Yuzhang Shang}, year = {2026}, eprint = {2610.28589}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28589}, } @misc{zhang2026scaling, title = {{Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds}}, author = {Kuan Zhang and Yukun Chen and Zhihao Yang and Yue Su and Xiangnan Wu and Zirong Chen and Run Luo and Jinkun Hou and Tao Tan and Yinhe Zheng and Yiming Li}, year = {2026}, eprint = {2610.28698}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2610.28698}, } @misc{luo2026toward, title = {{Toward Recursive Self-Improvement in Physical AI}}, author = {Meng Luo and Zechen Bai and Shanqing Xu and Yanlin Li and Kaixin Li and Mengchen Qian and Weifeng Lu and Ran Zhang and Yingtian Zou and Ziyang Luo and Wei Chen and Hongzhan Lin}, year = {2026}, eprint = {2610.29677}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29677}, } @misc{li2026where, title = {{Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy}}, author = {Zekai Li and Jiayi Yu and Jinlu Zhang and Luyang Niu and Zekun Qi and Jun Zheng and Xuchuan Chen and Dairu Liu and Yintianrun Zhang and He Wang and Li Yi}, year = {2026}, eprint = {2610.26848}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26848}, } @misc{lu2026tilde, title = {{TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models}}, author = {Yuxiang Lu and Yantong Liu and Jinghua Hou and Xueli Sun and Ruihua Han and Zhe Liu and Hengshuang Zhao}, year = {2026}, eprint = {2610.25376}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25376}, } @misc{zhang2026egoforesight, title = {{EgoForesight: Effectively Scaling Policy Learning with Noisy Egocentric Actions}}, author = {Chubin Zhang and Changyuan Wang and Yirui Wang and Ao Li and Shilin Ma and Yue Su and Cai Zhou and Xiuwei Xu and Tianle Zhang and Yansong Tang}, year = {2026}, eprint = {2610.31845}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31845}, } @misc{gu2026training, title = {{Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation}}, author = {Chun Gu and Xiaofei Wei and Yiming Chen and Bozhou Zhang and Juntong Zhang and Xiatian Zhu and Li Zhang}, year = {2026}, eprint = {2610.29264}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29264}, } @misc{park2026discodemo, title = {{DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning}}, author = {Minho Park and Kinam Kim and Donghu Kim and Byungkun Lee and Dongyoon Hwang and Yongjae Shin and Junha Hyung and Hojoon Lee and Jaegul Choo}, year = {2026}, eprint = {2610.32093}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32093}, } @misc{yu2026hidra, title = {{HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning}}, author = {Fanqi Yu and Matteo Tiezzi and Cigdem Beyan and Tommaso Apicella and Vittorio Murino}, year = {2026}, eprint = {2610.36374}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36374}, } @misc{luu2026progress, title = {{Progress-Guided Preference Generation for Aligning Generative Control Policies}}, author = {Tung M. Luu and Tri Ton and Duc M. Nguyen and Xuan Thanh Nguyen and Nguyen Gia Binh and Quang Tan Nguyen and Vu Duong and Daniel Sonntag and Duy M. H. Nguyen and Vien Anh Ngo and Chang D. Yoo}, year = {2026}, eprint = {2610.25692}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2610.25692}, } @misc{lee2026flexible, title = {{Flexible Language-Guided Representation Editing for Adaptive Robot Behavior}}, author = {Audrey Lee and Nathaniel Dennler and Ilia Sucholutsky and Andreea Bobu}, year = {2026}, eprint = {2610.28893}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28893}, } @misc{xu2026curaeval, title = {{CuraEval: Evaluating Demonstration Curation on Mixed-Skill Robot Data}}, author = {Jiuyi Xu and Meida Chen and Yang Ye and Yangming Shi}, year = {2026}, eprint = {2610.38221}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38221}, } @misc{han2026recursive, title = {{Recursive Self-Improvement in Physical AI: Mechanisms, Evidence, and Evaluation}}, author = {Xiaofeng Han and Kaize Luo and Zenghuang Fu and Zichong Zhu and Zhe Feng and Changwei Wang and Rongtao Xu and Weiliang Meng and Xiaopeng Zhang}, year = {2026}, eprint = {2610.38266}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.38266}, } @misc{yi2026flow, title = {{Flow Policy Gradients for Robot Control}}, author = {Brent Yi and Hongsuk Choi and Himanshu Gaurav Singh and Xiaoyu Huang and Takara E. Truong and Carmelo Sferrazza and Yi Ma and Rocky Duan and Pieter Abbeel and Guanya Shi and Karen Liu and Angjoo Kanazawa}, year = {2026}, eprint = {2602.02481}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.02481}, } @misc{xu2026rl, title = {{RL Token: Bootstrapping Online RL with Vision-Language-Action Models}}, author = {Charles Xu and Jost Tobias Springenberg and Michael Equi and Ali Amin and Adnan Esmail and Sergey Levine and Liyiming Ke}, year = {2026}, eprint = {2604.23073}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2604.23073}, } @misc{murray2026flowdagger, title = {{FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space}}, author = {Michael Murray and Daphne Chen and Simran Bagaria and Dean Fortier and Tess Hellebrekers and Galen Mullins and Harshavardhan Gajarla and Oier Mees and Maya Cakmak and Andrey Kolobov}, year = {2026}, eprint = {2607.08877}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.08877}, } @misc{kim2026diffusion, title = {{Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction}}, author = {Seonsoo Kim and Seongil Hong and Jun-Gill Kang}, year = {2026}, eprint = {2607.19919}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.19919}, } @misc{memmel2026d, title = {{D\&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models}}, author = {Marius Memmel and Shawn Yin and Urvi Rutia and Angad Wadhwa and Eldon Li and Gavin Angeloff and Ankit Goyal and Jesse Zhang and Dieter Fox and Fabio Ramos and Anqi Li and Abhishek Gupta}, year = {2026}, eprint = {2611.03622}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03622}, } @misc{park2026when, title = {{When Robots Outweigh Objects: How Inertia Mismatch Shapes Robot Policy Learning}}, author = {Younghyo Park and Antonia Bronars and Pulkit Agrawal}, year = {2026}, eprint = {2611.03501}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03501}, } @misc{sun2026beyond, title = {{Beyond Validation Loss: Coverage and Reliability Dynamics in Robot Policy Pretraining}}, author = {Zhanyi Sun and Max Simchowitz and Shuran Song}, year = {2026}, eprint = {2611.01565}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2611.01565}, } @misc{bauer2026behavior, title = {{Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data}}, author = {Erik Bauer and Jakob Thumm and Christopher Agia and Rohan Sinha and Chen Xu and Haruki Nishimura and Jeannette Bohg and Marco Pavone and Masha Itkina}, year = {2026}, eprint = {2611.00405}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.00405}, } @misc{xu2026gsbr, title = {{GSBR: Geometric Support Behavior Regularization for Online RL}}, author = {Charles Xu and Jacob Berg and Liyiming Ke and Sergey Levine}, year = {2026}, eprint = {2611.05295}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05295}, } @misc{arora2026scocat, title = {{SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking}}, author = {Aman Arora and Ricard Marsal I Castan and Matteo El-Hariry and Miguel Olivares-Mendez}, year = {2026}, eprint = {2609.06061}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.06061}, } @misc{xue2026control, title = {{Control-Ready Uncertainty for Trajectory Diffusion}}, author = {Zhiwei Xue and Jia Yue Kam and Jinhang Qiu and Yifeng Cheng and Ege Gursoy and Jiaming Wang and Vincent Bonnet and Harold Soh}, year = {2026}, eprint = {2610.12431}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.12431}, } @misc{sukhija2025tarc, title = {{TARC: Time-Adaptive Robotic Control}}, author = {Arnav Sukhija and Lenart Treven and Jin Cheng and Florian Dörfler and Stelian Coros and Andreas Krause}, year = {2025}, eprint = {2510.23176}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.23176}, } @misc{he2026fedguide, title = {{FedGuide: Diffusion Prior Alignment and Value Baseline Guidance for Heterogeneous Federated Reinforcement Learning}}, author = {Zhilin He and Gauri Joshi}, year = {2026}, eprint = {2609.18964}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2609.18964}, } @misc{ai2025towards, title = {{Towards Embodiment Scaling Laws in Robot Locomotion}}, author = {Bo Ai and Liu Dai and Nico Bohlinger and Dichen Li and Tongzhou Mu and Zhanxin Wu and K. Fay and Henrik I. Christensen and Jan Peters and Hao Su}, year = {2025}, eprint = {2505.05753}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.05753}, } @misc{jegal2026llms, title = {{LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation}}, author = {Hong Je-Gal and Jinwoo Kim and Chanbin Yi and Hyun-Suk Lee}, year = {2026}, eprint = {2611.04974}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04974}, } @misc{kim2026race, title = {{RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection}}, author = {Changyeon Kim and Yekyung Nah and Kimin Lee}, year = {2026}, eprint = {2611.05838}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05838}, } @misc{hsu2026ela, title = {{ELA: End-to-End Latent Action Policy Learning from Video Demonstrations}}, author = {Cheng-Chun Hsu and Peter Stone}, year = {2026}, eprint = {2611.05571}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05571}, } @misc{mccarthy2024towards, title = {{Towards Generalist Robot Learning from Internet Video: A Survey}}, author = {Robert McCarthy and Daniel C. H. Tan and Dominik Schmidt and Fernando Acero and Nathan Herr and Yilun Du and Thomas G. Thuruthel and Zhibin Li}, year = {2024}, eprint = {2404.19664}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2404.19664}, } @misc{maddukuri2025sim, title = {{Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation}}, author = {Abhiram Maddukuri and Zhenyu Jiang and Lawrence Yunliang Chen and Soroush Nasiriany and Yuqi Xie and Yu Fang and Wenqi Huang and Zu Wang and Zhenjia Xu and Nikita Chernyadev and Scott Reed and Ken Goldberg and Ajay Mandlekar and Linxi Fan and Yuke Zhu}, year = {2025}, eprint = {2503.24361}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.24361}, } @misc{liu2023llm, title = {{LLM+P: Empowering Large Language Models with Optimal Planning Proficiency}}, author = {Bo Liu and Yuqian Jiang and Xiaohan Zhang and Qiang Liu and Shiqi Zhang and Joydeep Biswas and Peter Stone}, year = {2023}, eprint = {2304.11477}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2304.11477}, } @misc{song2022llm, title = {{LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models}}, author = {Chan Hee Song and Jiaman Wu and Clayton Washington and Brian M. Sadler and Wei-Lun Chao and Yu Su}, year = {2022}, eprint = {2212.04088}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2212.04088}, } @misc{chen2026topreward, title = {{TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics}}, author = {Shirui Chen and Cole Harrison and Ying-Chun Lee and Angela Jin Yang and Zhongzheng Ren and Lillian J. Ratliff and Jiafei Duan and Dieter Fox and Ranjay Krishna}, year = {2026}, eprint = {2602.19313}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.19313}, } @misc{han2026online, title = {{Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observation}}, author = {Tyler Han and Bat Nemekhbold and Siyang Shen and Rohan Baijal and Richard Ebock and Harine Ravichandiran and Sanghun Jung and Kevin Huang and Byron Boots}, year = {2026}, eprint = {2602.24121}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.24121}, } @misc{laprevotte2026learning, title = {{Learning to Be Different: Component Specialization for Compositional Diffusion Policies}}, author = {Alec Laprevotte and Haonan Chen and Xiaoshen Han and Yilun Du}, year = {2026}, eprint = {2610.27194}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27194}, } @misc{ciftci2026where, title = {{Where Small Mistakes Matter: Quantifying State Criticality for Imitation Learning}}, author = {Yusuf Umut Ciftci and Joonwon Kang and Ajay Suresha Sathya and Somil Bansal}, year = {2026}, eprint = {2610.17709}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2610.17709}, } @misc{liu2026mirror, title = {{MIRROR: Reflecting Hidden Symmetries from Offline Robot Interaction Data}}, author = {Shiqi Liu and Yihang Yao and Peide Huang and Mengdi Xu and Ding Zhao}, year = {2026}, eprint = {2610.17422}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17422}, } @misc{zhang2026balanced, title = {{A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control}}, author = {Octi Zhang and Mateo Guaman Castro and Patrick Yin and Ignacio Dagnino and Abhishek Gupta and Rosario Scalise and Byron Boots}, year = {2026}, eprint = {2610.12465}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.12465}, } @misc{li2026robofft, title = {{RoboFFT: Finetuning generative robot policy via online reinforcement learning with forward process}}, author = {Yu Li and Shenghe Hu and Yuhan Wang and Yaoxiang Pu and Haotong Zhang and Yuanpei Chen and Yaodong Yang}, year = {2026}, eprint = {2609.32236}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.32236}, } @misc{niu2026hire, title = {{HiRE: Hindsight Reward Editing for Policy Finetuning}}, author = {Haoyi Niu and Zhengtao Han and Yufeng Ji and Zhongyu Li and Koushil Sreenath}, year = {2026}, eprint = {2609.27068}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.27068}, } @misc{wu2026r, title = {{$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning}}, author = {Lehong Wu and Yuxiao Qu and Zheyuan Hu and Ivan Zhang and Limin Wei and Zackory Erickson and Aviral Kumar}, year = {2026}, eprint = {2608.26053}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.26053}, } @misc{li2026trace, title = {{TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation}}, author = {Zihao Li and Ranpeng Qiu and Yincong Chen and Guoqiang Ren and Weiming Zhi}, year = {2026}, eprint = {2606.14551}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14551}, } @misc{cao2026unified, title = {{Unified Motion-Action Modeling for Heterogeneous Robot Learning}}, author = {Yunhao Cao and Shitong Liu and Chao Feng and Meryl Zhang and Xuanchen Lu and Andrew Owens and Kuan Fang}, year = {2026}, eprint = {2606.16917}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16917}, } @misc{wang2026learning, title = {{Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies}}, author = {Yi Wang and Xinchen Li and Pengwei Xie and Pu Yang and Buqing Nie and Yunuo Cai and Qinglin Zhang and Chendi Qu and Jeffrey Wu and Jianheng Song and Xinlin Ren and Jingshun Huang and Mingjie Pan and Siyuan Feng and Zhi Chen and Jianlan Luo}, year = {2026}, eprint = {2605.00416}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.00416}, } @misc{du2026memory, title = {{Memory Anchors for Continual Robot Learning}}, author = {Maximilian Du and Zhanyi Sun and Chen Xu and Paarth Shah and Masha Itkina and Shuran Song}, year = {2026}, eprint = {2608.26545}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.26545}, } @misc{deng2026uniintervene, title = {{UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning}}, author = {Haoyuan Deng and Yitong Gao and Yudong Lin and Haichao Liu and Zhenyu Wu and Ziwei Wang}, year = {2026}, eprint = {2606.12372}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12372}, } @misc{xia2026robo, title = {{Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning}}, author = {Wenke Xia and Pei Ren and Wenbo Yu and Yizhuo Zhang and Jifan Li and Yixue Zhang and Yinuo Zhao and Qingyang Gao and Jianlong Fu and Jian Tang and Ji-Rong Wen and Zhengping Che and Di Hu}, year = {2026}, eprint = {2607.09866}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.09866}, } @misc{yu2026generative, title = {{Generative Flow on Symbolic Abstractions for Embodiment Capability Discovery}}, author = {Youwei Yu and Lantao Liu}, year = {2026}, eprint = {2610.17174}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17174}, } @misc{xiao2026enpire, title = {{ENPIRE: Agentic Robot Policy Self-Improvement in the Real World}}, author = {Wenli Xiao and Jia Xie and Tonghe Zhang and Haotian Lin and Letian "Max" Fu and Haoru Xue and Jalen Lu and Yi Yang and Cunxi Dai and Zi Wang and Jimmy Wu and Guanzhi Wang and S. Shankar Sastry and Ken Goldberg and Linxi "Jim" Fan and Yuke Zhu and Guanya Shi}, year = {2026}, eprint = {2606.19980}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2606.19980}, } @misc{wang2026discretertc, title = {{DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors}}, author = {Pengcheng Wang and Kaiwen Hong and Chensheng Peng and Katherine Driggs-Campbell and Masayoshi Tomizuka and Chenfeng Xu and Chen Tang}, year = {2026}, eprint = {2604.25050}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.25050}, } @misc{hao2026far, title = {{FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement}}, author = {Haoran Hao and Shahram Najam Syed and Jeffrey Ichnowski and Jeff Schneider}, year = {2026}, eprint = {2607.01111}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.01111}, } @misc{liu2026egoengine, title = {{EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations}}, author = {Yangcen Liu and Shuo Cheng and Xinchen Yin and Woo Chul Shin and Alfred Cueva and Yiran Yang and Zhenyang Chen and Chuye Zhang and Danfei Xu}, year = {2026}, eprint = {2606.12604}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12604}, } @misc{rolland2026robot, title = {{Robot-WATCHDOG : failure detection through object-centric graph representation}}, author = {Quentin Rolland and Fabrice Mayran de Chamisso and Jean-Baptiste Mouret}, year = {2026}, eprint = {2610.13403}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.13403}, } @misc{zhou2026unified, title = {{Unified Condition-Action Modeling for Accurate One-Step Action Generation}}, author = {Xinyu Zhou and Zikun Cai and Kuangji Zuo and Gen Li and Boyu Ma and Yanshuo Lu and Yutong Song and Mingqi Yuan and Jiayu Chen and Jianfei Yang}, year = {2026}, eprint = {2608.16153}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.16153}, } @misc{li2026recover, title = {{Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures}}, author = {Bowen Li and Mayank Mishra and Y. Isabel Liu and Stone Tao and Nishanth Kumar and Alexander G. Gray and Ruwan Wickramarachchi and Jonathan Francis and Sebastian Scherer and Tom Silver}, year = {2026}, eprint = {2606.18328}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.18328}, } @misc{wei2026ambient, title = {{Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics}}, author = {Adam Wei and Nicholas Pfaff and Thomas Cohn and Arif Kerem Dayı and Constantinos Daskalakis and Giannis Daras and Russ Tedrake}, year = {2026}, eprint = {2606.12365}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.12365}, } @misc{yu2026warp, title = {{WARP-RM: A Warp-Augmented Relative Progress Reward Model for Data Curation}}, author = {Justin Yu and Andrew Goldberg and Kavish Kondap and Karim El-Refai and Ethan Ransing and Qianzhong Chen and Mac Schwager and Fred Shentu and Philipp Wu and Ken Goldberg}, year = {2026}, eprint = {2606.28320}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.28320}, } @misc{lee2025learning, title = {{Learning Robust Visuomotor Policies via Dynamics Alignment}}, author = {Dohyeok Lee and Jung Min Lee and Munkyung Kim and Seokhun Ju and Jin Woo Koo and Kyungjae Lee and Dohyeong Kim and Taehyun Cho and Tapomayukh Bhattacharjee and Jungwoo Lee}, year = {2025}, eprint = {2510.27114}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.27114}, } @misc{chen2026warp, title = {{WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations}}, author = {Zhenyang Chen and Chuizheng Kong and Chuye Zhang and Yuanshao Yang and Lawrence Y. Zhu and Shreyas Kousik and Danfei Xu}, year = {2026}, eprint = {2606.29940}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.29940}, } @misc{wang2026imitation, title = {{Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models}}, author = {Tianyou Wang and Anson Lei and Joe Watson and Ingmar Posner}, year = {2026}, eprint = {2606.21672}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.21672}, } @misc{gupta2026lucid, title = {{LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition}}, author = {Harsh Gupta and Guanya Shi and Wenzhen Yuan}, year = {2026}, eprint = {2606.11628}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.11628}, } @misc{lin2026activemimic, title = {{ActiveMimic: Egocentric Video Pretraining with Active Perception}}, author = {Xingyao Lin and Guojin Zhong and Tianyi Lu and Ziyi Ye and Yichen Zhu and Zuxuan Wu and Yu-Gang Jiang}, year = {2026}, eprint = {2606.06194}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.06194}, } @misc{qian2026synthicl, title = {{SynthICL: Scalable In-context Imitation Learning with Synthetic Data}}, author = {Cheng Qian and Ruomeng Fan and Yifei Ren and Yilong Wang and Edward Johns}, year = {2026}, eprint = {2606.08154}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08154}, } @misc{torne2026freeform, title = {{Freeform Preference Learning for Robotic Manipulation}}, author = {Marcel Torne and Anubha Mahajan and Abhijnya Bhat and Chelsea Finn}, year = {2026}, eprint = {2606.32027}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.32027}, } @misc{shi2026flowdpg, title = {{FlowDPG: Deterministic Policy Gradient on Flow Matching Policies for Real-World Manipulation}}, author = {Kexin Shi and Junyao Shi and Poorvi Hebbar and Zhuolun Zhao and Tarun Amarnath and Yifan Su and Shikhar Bahl and Deepak Pathak}, year = {2026}, eprint = {2606.22303}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22303}, } @misc{yin2026how, title = {{How to Learn from What a Human Would Avoid? Intervention-Aware World Models with Real-World RL for Dexterous Manipulation}}, author = {Jiaju Yin and Zhenhui Zhang and Lixin Xu and Heng Zhang and Jun Shao and Yating Feng and Arash Ajoudani and Renjing Xu}, year = {2026}, eprint = {2609.06009}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.06009}, } @misc{wang2026ai, title = {{AI Coaching for Accelerating Human Skill Development with Reinforcement Learning}}, author = {Wei Wang and Enlin Gu and Antonio Loquercio and Haimin Hu and Rahul Mangharam}, year = {2026}, eprint = {2606.25337}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.25337}, } @misc{li2026harbor, title = {{HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning}}, author = {Zechu Li and Yufeng Jin and Xiaoyang Liu and Puze Liu and Vignesh Prasad and Carlo D'Eramo and Georgia Chalvatzaki}, year = {2026}, eprint = {2606.08610}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08610}, } @misc{wang2026localized, title = {{Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies}}, author = {Ruiyu Wang and Zheyu Zhuang and Danica Kragic and Florian T. Pokorny}, year = {2026}, eprint = {2609.08408}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.08408}, } @misc{guo2026chameleon, title = {{Chameleon: Control-Indexed Prospective Memory for Visuomotor Manipulation}}, author = {Xinying Guo and Chenxi Jiang and Hyun Bin Kim and Yuhang Han and Ying Sun and Yang Xiao and Jianfei Yang}, year = {2026}, eprint = {2603.24576}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.24576}, } @misc{li2026object, title = {{Object-Centric Conditioning for Visuomotor Flow Matching}}, author = {Jijie Li and Xu Yang and Junhong Zou and Chunhai Zhao and Chaoyang Zhao and Zhen Lei and Xiangyu Zhu}, year = {2026}, eprint = {2609.24155}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.24155}, } @misc{liu2026preference, title = {{Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation}}, author = {Zeyi Liu and Guangyao Liu and Yinuo Qu and Yuquan Xue and Bofang Jia and Chunhua Yang and Weihua Gui and Keke Huang and Ziwei Wang}, year = {2026}, eprint = {2606.03949}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.03949}, } @misc{wei2026learning, title = {{Learning Additively Compositional Latent Actions for Embodied AI}}, author = {Hangxing Wei and Xiaoyu Chen and Chuheng Zhang and Tim Pearce and Jianyu Chen and Alex Lamb and Li Zhao and Jiang Bian}, year = {2026}, eprint = {2604.03340}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2604.03340}, } @misc{matsumoto2026learning, title = {{Learning Coordinated Visuomotor Box-Pushing from Solo Demonstrations}}, author = {Ryusei Matsumoto and Mei Kinjo and Yoko Sasaki and Keisuke Okumura}, year = {2026}, eprint = {2610.05677}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.05677}, } @misc{dashora2026workspace, title = {{Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision}}, author = {Nitish Dashora and Douglas Chen and Idan Shenfeld and John Marangola and Pulkit Agrawal and Max Simchowitz}, year = {2026}, eprint = {2609.20820}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.20820}, } @misc{yang2026rarm, title = {{RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation}}, author = {Pengzhi Yang and Xinyu Wang and Pengyu Jing and Kehan Wen and Yiduo Qu and Zhenhao Huang and Minghao Fu and Xin Liu and Yaheng Shen and Fan Shi}, year = {2026}, eprint = {2606.22027}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22027}, } @misc{merker2026asking, title = {{Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards}}, author = {Helena Merker and Nick Walker and Andreea Bobu}, year = {2026}, eprint = {2610.22285}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22285}, } @misc{zhang2026rethinking, title = {{Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration}}, author = {Qiping Zhang and Kate Candon and Debasmita Ghose and Marynel Vázquez}, year = {2026}, eprint = {2609.13982}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.13982}, } @misc{asayesh2026task, title = {{Task-Space Imitation Guidance for Efficient Reinforcement Learning}}, author = {Salar Asayesh and Hossein Darani and Todd Cao and Evgeny Andriash and Mani Ranjbar}, year = {2026}, eprint = {2610.07527}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.07527}, } @misc{liang2026efficient, title = {{Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging}}, author = {Yuanchu Liang and Yue Yang and An-Chi He and Hanna Kurniawati}, year = {2026}, eprint = {2611.07275}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.07275}, } @misc{shen2026learning, title = {{Learning Object Manipulation from Scratch via Contrastive Interaction}}, author = {Tongle Shen and Caleb Chuck and Fan Feng and Biwei Huang}, year = {2026}, eprint = {2606.11525}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.11525}, } @misc{tang2026improving, title = {{Improving Robotic Generalist Policies via Flow Reversal Steering}}, author = {Andy Tang and William Chen and Andrew Wagenmaker and Chelsea Finn and Sergey Levine}, year = {2026}, eprint = {2606.13675}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13675}, } @misc{andreu2026leave, title = {{Leave It Better Than Found: Value-Guided Cooperation in Sequential Tasks}}, author = {Mario Gomez Andreu and Michael Amir and Antonio Marino and Tianxu An and Marco Hutter and Amanda Prorok}, year = {2026}, eprint = {2611.08075}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08075}, } @misc{ning2026proxy, title = {{Proxy Policy Steering}}, author = {Chuanruo Ning and Tianrui Wang and Wei-Chiu Ma and Kuan Fang}, year = {2026}, eprint = {2609.09148}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.09148}, } @misc{clark2025what, title = {{What Do You Need for Compositional Generalization in Diffusion Planning?}}, author = {Quentin Clark and Florian Shkurti}, year = {2025}, eprint = {2505.18083}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2505.18083}, } @misc{park2026simultaneous, title = {{Simultaneous Forward and Inverse Human-in-the-Loop Optimization}}, author = {Kyeongwon Park and Steven H. Collins}, year = {2026}, eprint = {2609.22630}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.22630}, } @misc{qin2026beyond, title = {{Beyond Monotonic Progress: Retry-Supervised Value Learning for Robot Imitation}}, author = {Xinyao Qin and Junjie Lu and Kaixin Wang and Chuheng Zhang and Sinjae Kang and Kimin Lee and Min Xu and Bin Liang and Jun Yang and Li Zhao}, year = {2026}, eprint = {2606.24633}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.24633}, } @misc{zhu2026scape, title = {{SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation}}, author = {Dijie Zhu and Seunghun Oh and Ruopeng Huang and Zhiyu Huang and Jiaqi Ma and Chen Tang}, year = {2026}, eprint = {2608.19425}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.19425}, } @misc{kang2026implicit, title = {{Implicit Neural Representations of Individual Behavior}}, author = {Andrew Kang and Priya Narasimhan}, year = {2026}, eprint = {2606.12200}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2606.12200}, } @misc{lazzati2026why, title = {{Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?}}, author = {Filippo Lazzati and Kyle Stachowicz and William Chen and Alberto Maria Metelli and Andrew Wagenmaker and Sergey Levine}, year = {2026}, eprint = {2608.02547}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.02547}, } @misc{parashar2026coverage, title = {{Coverage Aware Active Evaluation for Failure Discovery with Paired Systems}}, author = {Anjali Parashar and Rachel Luo and Apoorva Sharma and Sushant Veer and Edward Schmerling and Carson Sobolewski and Mingxin Yu and Chuchu Fan and Marco Pavone}, year = {2026}, eprint = {2608.13719}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2608.13719}, } @misc{deng2026robofqe, title = {{RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories}}, author = {Yunfu Deng and Sangwoo Shin and Brahma S. Pavse and Josiah P. Hanna}, year = {2026}, eprint = {2610.18699}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18699}, } @misc{badithela2026anyrank, title = {{AnyRank: Reliable Anytime Policy Ranking via Sequential Testing}}, author = {Apurva Badithela and David Snyder and Tenny Yin and Jade Sceats and George Pappas and Nikolai Matni and Masha Itkina and Haruki Nishimura and Anirudha Majumdar}, year = {2026}, eprint = {2610.14603}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.14603}, } @misc{jayasinghe2026when, title = {{When Robots Sleep: Offline Skill Consolidation for Shared-Policy Robot Learning}}, author = {Nethmi Jayasinghe and Diana Gontero and Amit Ranjan Trivedi}, year = {2026}, eprint = {2606.17493}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.17493}, } @misc{dai2026where, title = {{Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies}}, author = {Meipo Dai and Qiyuan Zhuang and He-Yang Xu and Ying-Jie Shuai and Yijun Wang and Qi Dou and Xiu-Shen Wei}, year = {2026}, eprint = {2606.17408}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.17408}, } @misc{yu2026guided, title = {{Guided Discovery of New Behaviors using Diffusion Policies}}, author = {Dian Yu and Sebastian Sanokowski and Majid Khadiv}, year = {2026}, eprint = {2606.08743}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08743}, } @misc{bernat2026magma, title = {{MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution}}, author = {Loan Bernat and Matthieu Grard and Ariane Herbulot and Florent Lamiraux}, year = {2026}, eprint = {2609.20056}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2609.20056}, } @misc{wang2026behavior, title = {{Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering}}, author = {Hao Wang and Jiuzhou Lei and Dayou Li and Bangya Liu and Minghui Zheng and Manling Li and Ruohan Zhang and Zhiwen Fan}, year = {2026}, eprint = {2606.29201}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.29201}, } @misc{sochopoulos2026optimal, title = {{Optimal Transport Q-Learning for Flow Policy Steering and Acceleration}}, author = {Andreas Sochopoulos and Esmeralda S. Whitammer and Nikolaos Tsagkas and João Moura and Michael Gienger and Sethu Vijayakumar}, year = {2026}, eprint = {2607.06262}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.06262}, } @misc{xu2026expertgen, title = {{ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors}}, author = {Zifan Xu and Ran Gong and Maria Vittoria Minniti and Kausik Sivakumar and Ahmet Salih Gundogdu and Eric Rosen and Riedana Yan and Tushar Kusnur and Zixing Wang and Di Deng and Peter Stone and Xiaohan Zhang and Karl Schmeckpeper}, year = {2026}, eprint = {2603.15956}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.15956}, } @misc{zhu2026skillweaver, title = {{SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation}}, author = {He Zhu and Lusen Zhao and Kwan Man Cheng and Su Li and Katerina Fragkiadaki}, year = {2026}, eprint = {2609.36171}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.36171}, } @misc{dass2026guild, title = {{GUILD: Guided Iterative Data Collection for Imitation Learning}}, author = {Shivin Dass and Kevin Nguyen and Rohan Yelandur and Junhong Xu and Roberto Martín-Martín}, year = {2026}, eprint = {2611.05368}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05368}, } @misc{you2026efficient, title = {{Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient}}, author = {Haoxiang You and Yilang Liu and Davis Zong and Qian Wang and Teeratham Vitchutripop and Qi Wang and Daniel Rakita and Ian Abraham}, year = {2026}, eprint = {2605.26478}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.26478}, } @misc{xu2026mind, title = {{Mind the Gap: Rethinking I/O Design for Contact-Rich Visuomotor Policy Learning}}, author = {Cuijie Xu and Shurui Zheng and Zihao Su and Zhongchen Jian and Yuanfan Xu and Tinghao Yi and Xudong Zhang and Jian Wang and Yu Wang and Jinchen Yu}, year = {2026}, eprint = {2602.08776}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.08776}, } @misc{teegavarapu2026q, title = {{Q-OIL: Optimistic Exploration in Learning from Human Interventions}}, author = {Pranav Teegavarapu and Sriyash Poddar and Rico Qi and Cleah Winston and Krisha Khandelwal and Aykut Onyol and Natasha Jaques and Abhishek Gupta}, year = {2026}, eprint = {2611.08576}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08576}, } @misc{larchenko2026off, title = {{Off-Policy RL with Online Inference Tuning: My Solution to the CoRL 2026 RoboEval Challenge}}, author = {Ilia Larchenko}, year = {2026}, eprint = {2611.11464}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.11464}, } @misc{chia2026explicitly, title = {{Explicitly capturing demonstrator multi-modality for distillation into diffusion policies}}, author = {Shao Yuan Chew Chia and Rebecca H. Jiang and Abhinav Agarwal and Andreas Hofmann and Leslie Pack Kaelbling and Russ Tedrake}, year = {2026}, eprint = {2611.10949}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10949}, } @misc{kim2026spark, title = {{SPARK: Simple Post-training for Adapting pRetrained Knowledge to Robot Control}}, author = {Taekyung Kim and Jeongeun Park and Byeongho Heo and Sungjoon Choi and Sangdoo Yun and Dongyoon Han}, year = {2026}, eprint = {2611.12102}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.12102}, } @misc{ding2026unilatent, title = {{UniLatent: Cross-Embodiment Transfer via Latent Observation Alignment}}, author = {Yufei Ding and Yi Du and Weiduo Yuan and Hao Jiang and Dylan Goetting and Lawrence Yunliang Chen and Daniel Seita and Yue Wang}, year = {2026}, eprint = {2611.10061}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10061}, } @misc{zakka2025mujoco, title = {{MuJoCo Playground}}, author = {Kevin Zakka and Baruch Tabanpour and Qiayuan Liao and Mustafa Haiderbhai and Samuel Holt and Jing Yuan Luo and Arthur Allshire and Erik Frey and Koushil Sreenath and Lueder A. Kahrs and Carmelo Sferrazza and Yuval Tassa and Pieter Abbeel}, year = {2025}, eprint = {2502.08844}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.08844}, } @misc{makoviychuk2021isaac, title = {{Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning}}, author = {Viktor Makoviychuk and Lukasz Wawrzyniak and Yunrong Guo and Michelle Lu and Kier Storey and Miles Macklin and David Hoeller and Nikita Rudin and Arthur Allshire and Ankur Handa and Gavriel State}, year = {2021}, eprint = {2108.10470}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2108.10470}, } @misc{mittal2023orbit, title = {{Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments}}, author = {Mayank Mittal and Calvin Yu and Qinxi Yu and Jingzhou Liu and Nikita Rudin and David Hoeller and Jia Lin Yuan and Ritvik Singh and Yunrong Guo and Hammad Mazhar and Ajay Mandlekar and Buck Babich and Gavriel State and Marco Hutter and Animesh Garg}, year = {2023}, eprint = {2301.04195}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2301.04195}, } @misc{tao2024maniskill, title = {{ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI}}, author = {Stone Tao and Fanbo Xiang and Arth Shukla and Yuzhe Qin and Xander Hinrichsen and Xiaodi Yuan and Chen Bao and Xinsong Lin and Yulin Liu and Tse-kai Chan and Yuan Gao and Xuanlin Li and Tongzhou Mu and Nan Xiao and Arnav Gurha and Viswesh Nagaswamy Rajesh and Yong Woo Choi and Yen-Ru Chen and Zhiao Huang and Roberto Calandra and Rui Chen and Shan Luo and Hao Su}, year = {2024}, eprint = {2410.00425}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.00425}, } @misc{zhu2020robosuite, title = {{robosuite: A Modular Simulation Framework and Benchmark for Robot Learning}}, author = {Yuke Zhu and Josiah Wong and Ajay Mandlekar and Roberto Martín-Martín and Abhishek Joshi and Kevin Lin and Abhiram Maddukuri and Soroush Nasiriany and Yifeng Zhu}, year = {2020}, eprint = {2009.12293}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2009.12293}, } @misc{nasiriany2024robocasa, title = {{RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots}}, author = {Soroush Nasiriany and Abhiram Maddukuri and Lance Zhang and Adeet Parikh and Aaron Lo and Abhishek Joshi and Ajay Mandlekar and Yuke Zhu}, year = {2024}, eprint = {2406.02523}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2406.02523}, } @misc{xiang2020sapien, title = {{SAPIEN: A SimulAted Part-based Interactive ENvironment}}, author = {Fanbo Xiang and Yuzhe Qin and Kaichun Mo and Yikuan Xia and Hao Zhu and Fangchen Liu and Minghua Liu and Hanxiao Jiang and Yifu Yuan and He Wang and Li Yi and Angel X. Chang and Leonidas J. Guibas and Hao Su}, year = {2020}, eprint = {2003.08515}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2003.08515}, } @misc{tobin2017domain, title = {{Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World}}, author = {Josh Tobin and Rachel Fong and Alex Ray and Jonas Schneider and Wojciech Zaremba and Pieter Abbeel}, year = {2017}, eprint = {1703.06907}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1703.06907}, } @misc{peng2017sim, title = {{Sim-to-Real Transfer of Robotic Control with Dynamics Randomization}}, author = {Xue Bin Peng and Marcin Andrychowicz and Wojciech Zaremba and Pieter Abbeel}, year = {2017}, eprint = {1710.06537}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1710.06537}, } @misc{ma2026active, title = {{Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training}}, author = {Liqian Ma and Vaibhav Saxena and Utkarsh Aashu Mishra and Shuo Cheng and Yongxin Chen and Danfei Xu}, year = {2026}, eprint = {2610.19479}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.19479}, } @misc{chen2025robotwin, title = {{RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation}}, author = {Tianxing Chen and Zanxin Chen and Baijun Chen and Zijian Cai and Yibin Liu and Zixuan Li and Qiwei Liang and Xianliang Lin and Yiheng Ge and Zhenyu Gu and Weiliang Deng and Yubin Guo and Tian Nian and Xuanbing Xie and Qiangyu Chen and Kailun Su and Tianling Xu and Guodong Liu and Mengkang Hu and Huan-ang Gao and Kaixuan Wang and Zhixuan Liang and Yusen Qin and Xiaokang Yang and Ping Luo and Yao Mu}, year = {2025}, eprint = {2506.18088}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.18088}, } @misc{mandlekar2023mimicgen, title = {{MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations}}, author = {Ajay Mandlekar and Soroush Nasiriany and Bowen Wen and Iretiayo Akinola and Yashraj Narang and Linxi Fan and Yuke Zhu and Dieter Fox}, year = {2023}, eprint = {2310.17596}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2310.17596}, } @misc{li2024behavior, title = {{BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation}}, author = {Chengshu Li and Ruohan Zhang and Josiah Wong and Cem Gokmen and Sanjana Srivastava and Roberto Martín-Martín and Chen Wang and Gabrael Levine and Wensi Ai and Benjamin Martinez and Hang Yin and Michael Lingelbach and Minjune Hwang and Ayano Hiranaka and Sujay Garlanka and Arman Aydin and Sharon Lee and Jiankai Sun and Mona Anvari and Manasi Sharma and Dhruva Bansal and Samuel Hunter and Kyu-Young Kim and Alan Lou and Caleb R Matthews and Ivan Villa-Renteria and Jerry Huayang Tang and Claire Tang and Fei Xia and Yunzhu Li and Silvio Savarese and Hyowon Gweon and C. Karen Liu and Jiajun Wu and Li Fei-Fei}, year = {2024}, eprint = {2403.09227}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.09227}, } @misc{nvidia2025isaac, title = {{Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning}}, author = {NVIDIA and : and Mayank Mittal and Pascal Roth and James Tigue and Antoine Richard and Octi Zhang and Peter Du and Antonio Serrano-Muñoz and Xinjie Yao and René Zurbrügg and Nikita Rudin and Lukasz Wawrzyniak and Milad Rakhsha and Alain Denzler and Eric Heiden and Ales Borovicka and Ossama Ahmed and Iretiayo Akinola and Abrar Anwar and Mark T. Carlson and Ji Yuan Feng and Animesh Garg and Renato Gasoto and Lionel Gulich and Yijie Guo and M. Gussert and Alex Hansen and Mihir Kulkarni and Chenran Li and Wei Liu and Viktor Makoviychuk and Grzegorz Malczyk and Hammad Mazhar and Masoud Moghani and Adithyavairavan Murali and Michael Noseworthy and Alexander Poddubny and Nathan Ratliff and Welf Rehberg and Clemens Schwarke and Ritvik Singh and James Latham Smith and Bingjie Tang and Ruchik Thaker and Matthew Trepte and Karl Van Wyk and Fangzhou Yu and Alex Millane and Vikram Ramasamy and others}, year = {2025}, eprint = {2511.04831}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.04831}, } @misc{kolve2017ai, title = {{AI2-THOR: An Interactive 3D Environment for Visual AI}}, author = {Eric Kolve and Roozbeh Mottaghi and Winson Han and Eli VanderBilt and Luca Weihs and Alvaro Herrasti and Matt Deitke and Kiana Ehsani and Daniel Gordon and Yuke Zhu and Aniruddha Kembhavi and Abhinav Gupta and Ali Farhadi}, year = {2017}, eprint = {1712.05474}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/1712.05474}, } @misc{puig2023habitat, title = {{Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots}}, author = {Xavier Puig and Eric Undersander and Andrew Szot and Mikael Dallaire Cote and Tsung-Yen Yang and Ruslan Partsey and Ruta Desai and Alexander William Clegg and Michal Hlavac and So Yeon Min and Vladimír Vondruš and Theophile Gervet and Vincent-Pierre Berges and John M. Turner and Oleksandr Maksymets and Zsolt Kira and Mrinal Kalakrishnan and Jitendra Malik and Devendra Singh Chaplot and Unnat Jain and Dhruv Batra and Akshara Rai and Roozbeh Mottaghi}, year = {2023}, eprint = {2310.13724}, archivePrefix = {arXiv}, primaryClass = {cs.HC}, url = {https://arxiv.org/abs/2310.13724}, } @misc{eschmann2026hyperdrone, title = {{HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second}}, author = {Jonas Eschmann and Giuseppe Loianno}, year = {2026}, eprint = {2610.28950}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28950}, } @misc{freeman2021brax, title = {{Brax: A Differentiable Physics Engine for Large Scale Rigid Body Simulation}}, author = {C. Daniel Freeman and Erik Frey and Anton Raichuk and Sertan Girgin and Igor Mordatch and Olivier Bachem}, year = {2021}, eprint = {2106.13281}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2106.13281}, } @misc{szot2021habitat, title = {{Habitat 2.0: Training Home Assistants to Rearrange their Habitat}}, author = {Andrew Szot and Alex Clegg and Eric Undersander and Erik Wijmans and Yili Zhao and John Turner and Noah Maestre and Mustafa Mukadam and Devendra Chaplot and Oleksandr Maksymets and Aaron Gokaslan and Vladimir Vondrus and Sameer Dharur and Franziska Meier and Wojciech Galuba and Angel Chang and Zsolt Kira and Vladlen Koltun and Jitendra Malik and Manolis Savva and Dhruv Batra}, year = {2021}, eprint = {2106.14405}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2106.14405}, } @misc{gu2024humanoid, title = {{Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer}}, author = {Xinyang Gu and Yen-Jen Wang and Jianyu Chen}, year = {2024}, eprint = {2404.05695}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2404.05695}, } @misc{tassa2020dm, title = {{dm_control: Software and Tasks for Continuous Control}}, author = {Yuval Tassa and Saran Tunyasuvunakool and Alistair Muldal and Yotam Doron and Piotr Trochim and Siqi Liu and Steven Bohez and Josh Merel and Tom Erez and Timothy Lillicrap and Nicolas Heess}, year = {2020}, eprint = {2006.12983}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2006.12983}, } @misc{lin2020softgym, title = {{SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation}}, author = {Xingyu Lin and Yufei Wang and Jake Olkin and David Held}, year = {2020}, eprint = {2011.07215}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2011.07215}, } @misc{jiang2024dexmimicgen, title = {{DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning}}, author = {Zhenyu Jiang and Yuqi Xie and Kevin Lin and Zhenjia Xu and Weikang Wan and Ajay Mandlekar and Linxi Fan and Yuke Zhu}, year = {2024}, eprint = {2410.24185}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2410.24185}, } @misc{liu2026scenebloom, title = {{SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning}}, author = {Yuhan Liu and Lianhui Qin and Shenji Wan}, year = {2026}, eprint = {2610.32978}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.32978}, } @misc{gao2025genmanip, title = {{GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation}}, author = {Ning Gao and Yilun Chen and Shuai Yang and Xinyi Chen and Yang Tian and Hao Li and Haifeng Huang and Hanqing Wang and Tai Wang and Jiangmiao Pang}, year = {2025}, eprint = {2506.10966}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2506.10966}, } @misc{castillaarquillo2026mare, title = {{MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy}}, author = {Raúl Castilla-Arquillo and Miguel Olivares-Mendez}, year = {2026}, eprint = {2610.28465}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.28465}, } @misc{houssaini2026dexsuite, title = {{DexSuite: An All-in-One Framework for Dexterous Manipulation Across Arms, Hands, and Tasks}}, author = {Anas Houssaini and Hugo He and Junming Shi and Amin Abyaneh and Ricardo Chahine and Shuo Wen and Mohamad H. Danesh and Charles-Étienne Fréchette and Mariana Sosa Guzman and Mathias Desrochers and Rayan Houssaini and Adam Landa and Theophile Soulie and Charlotte Morissette and Annie Tims and Martino Russi and Jonathan Lussier and Gregory Dudek and Doina Precup and Julen Urain and Hsiu-Chin Lin and David Meger}, year = {2026}, eprint = {2610.37799}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37799}, } @misc{aggarwal2026gym, title = {{Gym-Anything for Robotics: Scaling physical simulations with digital agents}}, author = {Pranjal Aggarwal and Sean Welleck}, year = {2026}, eprint = {2610.40565}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40565}, } @misc{zhou2026when, title = {{When the Simulator Fails, Not the Policy: Auditing Contact Artifacts in Simulated Robot Benchmarks}}, author = {Alex Zhou and Junhao Wu and Xueyang Zhou and Yixiao Huo and Hongcheng Gao and Di Zhu and Zhenghao Zhang and Yongchao Chen}, year = {2026}, eprint = {2610.41857}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41857}, } @misc{deshpande2026molmob, title = {{MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation}}, author = {Abhay Deshpande and Maya Guru and Rose Hendrix and Snehal Jauhri and Ainaz Eftekhar and Rohun Tripathi and Max Argus and Jordi Salvador and Haoquan Fang and Matthew Wallingford and Wilbert Pumacay and Yejin Kim and Quinn Pfeifer and Ying-Chun Lee and Piper Wolters and Omar Rayyan and Mingtong Zhang and Jiafei Duan and Karen Farley and Winson Han and Eli Vanderbilt and Dieter Fox and Ali Farhadi and Georgia Chalvatzaki and Dhruv Shah and Ranjay Krishna}, year = {2026}, eprint = {2603.16861}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.16861}, } @misc{tsounis2026kamino, title = {{Kamino: GPU-based Simulation of Rigid Multi-Body Physics with Kinematic Loops}}, author = {Vassilios Tsounis and Guirec Maloisel and Christian Schumacher and Ruben Grandia and Agon Serifi and David Müller and Chris Amevor and Tobias Widmer and Moritz Bächer}, year = {2026}, eprint = {2603.16536}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.16536}, } @misc{yu2026aura, title = {{AuRA: From Atoms to Bits through Autonomous Robot Interaction}}, author = {Xinchen Yu and Yoonkyo Jung and Haoran Chen and Zikui Cai and Aayush Talreja and Seungjae Lee and Hyunjin Kim and Furong Huang}, year = {2026}, eprint = {2610.34452}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34452}, } @misc{zhang2026closing, title = {{Closing the Dynamics Gap through Self-Directed Robotic Interaction}}, author = {Xilun Zhang and Liam Achenbach and Luis Pabon and Matthew Foutter and Marco Pavone}, year = {2026}, eprint = {2611.02691}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02691}, } @misc{si2024difftactile, title = {{DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation}}, author = {Zilin Si and Gu Zhang and Qingwei Ben and Branden Romero and Zhou Xian and Chao Liu and Chuang Gan}, year = {2024}, eprint = {2403.08716}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.08716}, } @misc{li2025taccel, title = {{Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation}}, author = {Yuyang Li and Wenxin Du and Chang Yu and Puhao Li and Zihang Zhao and Tengyu Liu and Chenfanfu Jiang and Yixin Zhu and Siyuan Huang}, year = {2025}, eprint = {2504.12908}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2504.12908}, } @misc{nguyen2024tacex, title = {{TacEx: GelSight Tactile Simulation in Isaac Sim -- Combining Soft-Body and Visuotactile Simulators}}, author = {Duc Huy Nguyen and Tim Schneider and Guillaume Duret and Alap Kshirsagar and Boris Belousov and Jan Peters}, year = {2024}, eprint = {2411.04776}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2411.04776}, } @misc{chernyadev2024bigym, title = {{BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark}}, author = {Nikita Chernyadev and Nicholas Backshall and Xiao Ma and Yunfan Lu and Younggyo Seo and Stephen James}, year = {2024}, eprint = {2407.07788}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.07788}, } @misc{wang2024grutopia, title = {{GRUtopia: Dream General Robots in a City at Scale}}, author = {Hanqing Wang and Jiahe Chen and Wensi Huang and Qingwei Ben and Tai Wang and Boyu Mi and Tao Huang and Siheng Zhao and Yilun Chen and Sizhe Yang and Peizhou Cao and Wenye Yu and Zichao Ye and Jialun Li and Junfeng Long and Zirui Wang and Huiling Wang and Ying Zhao and Zhongying Tu and Yu Qiao and Dahua Lin and Jiangmiao Pang}, year = {2024}, eprint = {2407.10943}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.10943}, } @misc{shukla2024maniskill, title = {{ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks}}, author = {Arth Shukla and Stone Tao and Hao Su}, year = {2024}, eprint = {2412.13211}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.13211}, } @misc{patel2026learning, title = {{Learning Physics-Guided Residual Dynamics for Deformable Object Simulation}}, author = {Shivansh Patel and Kaifeng Zhang and Sanjay Pokkali and Svetlana Lazebnik and Yunzhu Li}, year = {2026}, eprint = {2607.13451}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.13451}, } @misc{escontrela2025gaussgym, title = {{GaussGym: An open-source real-to-sim framework for learning locomotion from pixels}}, author = {Alejandro Escontrela and Justin Kerr and Arthur Allshire and Jonas Frey and Rocky Duan and Carmelo Sferrazza and Pieter Abbeel}, year = {2025}, eprint = {2510.15352}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.15352}, } @misc{yin2026genie, title = {{Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot}}, author = {Chenghao Yin and Da Huang and Di Yang and Jichao Wang and Nanshu Zhao and Chen Xu and Wenjun Sun and Linjie Hou and Zhijun Li and Junhui Wu and Zhaobo Liu and Zhen Xiao and Sheng Zhang and Lei Bao and Rui Feng and Zhenquan Pang and Jiayu Li and Qian Wang and Maoqing Yao}, year = {2026}, eprint = {2601.02078}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2601.02078}, } @misc{gu2023maniskill, title = {{ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills}}, author = {Jiayuan Gu and Fanbo Xiang and Xuanlin Li and Zhan Ling and Xiqiang Liu and Tongzhou Mu and Yihe Tang and Stone Tao and Xinyue Wei and Yunchao Yao and Xiaodi Yuan and Pengwei Xie and Zhiao Huang and Rui Chen and Hao Su}, year = {2023}, eprint = {2302.04659}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2302.04659}, } @misc{zhong2024unrealzoo, title = {{UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI}}, author = {Fangwei Zhong and Kui Wu and Churan Wang and Hao Chen and Hai Ci and Zhoujun Li and Yizhou Wang}, year = {2024}, eprint = {2412.20977}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2412.20977}, } @misc{yu2026coda, title = {{CoDA: Co-Evolution of Data Engines and Action Policies}}, author = {Tianjiao Yu and Zhilin Ou and Yifan Shen and Xinzhuo Li and Yuanzhe Liu and Onkar Kishor Susladkar and Fan Wang and Ismini Lourentzou}, year = {2026}, eprint = {2610.22362}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22362}, } @misc{choi2026scaling, title = {{Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds}}, author = {Andrew Choi and Xinjie Wang and Zhizhong Su and Wei Xu}, year = {2026}, eprint = {2603.18532}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.18532}, } @misc{guo2026worlds, title = {{Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation}}, author = {Lingxiao Guo and Huanyu Li and Guanya Shi}, year = {2026}, eprint = {2607.13154}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.13154}, } @misc{tao2026silo, title = {{SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing}}, author = {Stone Tao and Jie Xu and Hesam Rabeti and Yashraj Narang and Yijie Guo and Iretiayo Akinola}, year = {2026}, eprint = {2607.04616}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.04616}, } @misc{schneider2026sim, title = {{Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks}}, author = {Jan Schneider and Mridul Mahajan and Le Chen and Simon Guist and Bernhard Schölkopf and Ingmar Posner and Dieter Büchler}, year = {2026}, eprint = {2604.09487}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.09487}, } @misc{zhang2026robosnap, title = {{RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation}}, author = {Shujie Zhang and Jingkun Yi and Weipeng Zhong and Zirui Zhou and Yangkun Zhu and Hanqing Wang and Xudong Xu and Weinan Zhang and Chunhua Shen}, year = {2026}, eprint = {2607.06699}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.06699}, } @misc{qin2026comsim, title = {{ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation}}, author = {Yiran Qin and Jiahua Ma and Li Kang and Wenzhan Li and Yihang Jiao and Xin Wen and Xiufeng Song and Heng Zhou and Jiwen Yu and Zhenfei Yin and Xihui Liu and Philip Torr and Yilun Du and Ruimao Zhang}, year = {2026}, eprint = {2604.11386}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.11386}, } @misc{jia2026unilab, title = {{UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms}}, author = {Yufei Jia and Zhanxiang Cao and Mingrui Yu and Heng Zhang and Shenyu Chen and Dixuan Jiang and Meng Li and Xiaofan Li and Yiyang Liu and Junzhe Wu and Zheng Li and XiLin Fang and Ting-Yu Tsui and Shengcheng Fu and Haoyang Li and Anqi Wang and Zifan Wang and Dongjie Zhu and Chenyu Cao and Zhenbiao Huang and Ziang Zheng and Jie Lu and Xin Ma and Zhengyang Wei and Xiang Zhao and Tianyue Zhan and Ye He and Yuxiang Chen and Yizhou Jiang and Yue Li and Haizhou Ge and Yuhang Dong and Fan Jia and Ziheng Zhang and Meng Zhang and Xiwa Deng and Zhixing Chen and Hanyang Shao and Chenxin Dong and Yixuan Li and Yizhi Chen and Bokui Chen and Kaifeng Zhang and Hanqing Cui and Yusen Qin and Ruqi Huang and Lei Han and Tiancai Wang and Xiang Li and Yue Gao and others}, year = {2026}, eprint = {2605.30313}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2605.30313}, } @misc{ranawaka2026simfoundry, title = {{SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation}}, author = {Nadun Ranawaka and Josiah Wong and Wei-Lin Pai and Wei-Teng Chu and Tianyuan Dai and Masoud Moghani and Hang Yin and Yunfan Jiang and Wesley Durbano and Brandon Huynh and Yu Fang and Danfei Xu and Ruohan Zhang and Li Fei-Fei and Linxi Fan and Bowen Wen and Ajay Mandlekar and Yuke Zhu}, year = {2026}, eprint = {2606.28276}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.28276}, } @misc{shentu2026do, title = {{Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots}}, author = {Chengnan Shentu and Nicholas Baldassini and Tongjia Zheng and Priyanka Rao and Jessica Burgner-Kahrs}, year = {2026}, eprint = {2606.22397}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22397}, } @misc{joshi2025procedural, title = {{Procedural Generation of Articulated Simulation-Ready Assets}}, author = {Abhishek Joshi and Beining Han and Jack Nugent and Max Gonzalez Saez-Diez and Yiming Zuo and Jonathan Liu and Hongyu Wen and Stamatis Alexandropoulos and Karhan Kayan and Anna Calveri and Tao Sun and Gaowen Liu and Yi Shao and Alexander Raistrick and Jia Deng}, year = {2025}, eprint = {2505.10755}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.10755}, } @misc{wang2026am, title = {{AM-Bench: A Modular Simulation Suite and Benchmark for Aerial Manipulation Policy Learning}}, author = {Yutong Wang and Dongjae Lee and Xiaofeng Guo and Yuanzhu Zhan and Yufei Jiang and Bavin Saravanan and Muqing Cao and Jia Xie and Chenyang Mao and Sebastian Scherer and Junyi Geng and Guanya Shi}, year = {2026}, eprint = {2609.00641}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.00641}, } @misc{wei2026simple, title = {{SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation}}, author = {Songlin Wei and Zhenhao Ni and Jie Liu and Zhenyu Zhao and Junjie Ye and Hongyi Jing and Junkai Xia and Xiawei Liu and Michael Leong and Liang Heng and Di Huang and Yue Wang}, year = {2026}, eprint = {2606.08278}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.08278}, } @misc{jungerman2026visionsim, title = {{VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception}}, author = {Sacha Jungerman and Kaustubh Sadekar and Avery Gump and Sriram Narayanan and Shantanu Gupta and Bhuyashi Deka and Srinivasa Narasimhan and Atul Ingle and Mohit Gupta}, year = {2026}, eprint = {2611.08368}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08368}, } @misc{xu2026gif, title = {{GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning}}, author = {Long Xu and Zhiqi Zhang and Mi Yan and Shengliang Deng and Chong Xia and Mingyu Dong and Jiayi Chen and Jiangran Lyu and Fei Gao and Zhizheng Zhang and He Wang}, year = {2026}, eprint = {2609.05927}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.05927}, } @misc{beker2026lodos, title = {{Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes}}, author = {Onur Beker and Andreas René Geist and Georg Martius}, year = {2026}, eprint = {2611.08872}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.08872}, } @misc{collaboration2023open, title = {{Open X-Embodiment: Robotic Learning Datasets and RT-X Models}}, author = {Open X-Embodiment Collaboration and Abby O'Neill and Abdul Rehman and Abhinav Gupta and Abhiram Maddukuri and Abhishek Gupta and Abhishek Padalkar and Abraham Lee and Acorn Pooley and Agrim Gupta and Ajay Mandlekar and Ajinkya Jain and Albert Tung and Alex Bewley and Alex Herzog and Alex Irpan and Alexander Khazatsky and Anant Rai and Anchit Gupta and Andrew Wang and Andrey Kolobov and Anikait Singh and Animesh Garg and Aniruddha Kembhavi and Annie Xie and Anthony Brohan and Antonin Raffin and Archit Sharma and Arefeh Yavary and Arhan Jain and Ashwin Balakrishna and Ayzaan Wahid and Ben Burgess-Limerick and Beomjoon Kim and Bernhard Schölkopf and Blake Wulfe and Brian Ichter and Cewu Lu and Charles Xu and Charlotte Le and Chelsea Finn and Chen Wang and Chenfeng Xu and Cheng Chi and Chenguang Huang and Christine Chan and Christopher Agia and Chuer Pan and Chuyuan Fu and Coline Devin and others}, year = {2023}, eprint = {2310.08864}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2310.08864}, } @misc{khazatsky2024droid, title = {{DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset}}, author = {Alexander Khazatsky and Karl Pertsch and Suraj Nair and Ashwin Balakrishna and Sudeep Dasari and Siddharth Karamcheti and Soroush Nasiriany and Mohan Kumar Srirama and Lawrence Yunliang Chen and Kirsty Ellis and Peter David Fagan and Joey Hejna and Masha Itkina and Marion Lepert and Yecheng Jason Ma and Patrick Tree Miller and Jimmy Wu and Suneel Belkhale and Shivin Dass and Huy Ha and Arhan Jain and Abraham Lee and Youngwoon Lee and Marius Memmel and Sungjae Park and Ilija Radosavovic and Kaiyuan Wang and Albert Zhan and Kevin Black and Cheng Chi and Kyle Beltran Hatch and Shan Lin and Jingpei Lu and Jean Mercat and Abdul Rehman and Pannag R Sanketi and Archit Sharma and Cody Simpson and Quan Vuong and Homer Rich Walke and Blake Wulfe and Ted Xiao and Jonathan Heewon Yang and Arefeh Yavary and Tony Z. Zhao and Christopher Agia and Rohan Baijal and Mateo Guaman Castro and Daphne Chen and Qiuyu Chen and others}, year = {2024}, eprint = {2403.12945}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.12945}, } @misc{walke2023bridgedata, title = {{BridgeData V2: A Dataset for Robot Learning at Scale}}, author = {Homer Walke and Kevin Black and Abraham Lee and Moo Jin Kim and Max Du and Chongyi Zheng and Tony Zhao and Philippe Hansen-Estruch and Quan Vuong and Andre He and Vivek Myers and Kuan Fang and Chelsea Finn and Sergey Levine}, year = {2023}, eprint = {2308.12952}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2308.12952}, } @misc{fang2023rh, title = {{RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot}}, author = {Hao-Shu Fang and Hongjie Fang and Zhenyu Tang and Jirong Liu and Chenxi Wang and Junbo Wang and Haoyi Zhu and Cewu Lu}, year = {2023}, eprint = {2307.00595}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2307.00595}, } @misc{agibotworldcontributors2025agibot, title = {{AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems}}, author = {AgiBot-World-Contributors and Qingwen Bu and Jisong Cai and Li Chen and Xiuqi Cui and Yan Ding and Siyuan Feng and Shenyuan Gao and Xindong He and Xuan Hu and Xu Huang and Shu Jiang and Yuxin Jiang and Cheng Jing and Hongyang Li and Jialu Li and Chiming Liu and Yi Liu and Yuxiang Lu and Jianlan Luo and Ping Luo and Yao Mu and Yuehan Niu and Yixuan Pan and Jiangmiao Pang and Yu Qiao and Guanghui Ren and Cheng Ruan and Jiaqi Shan and Yongjian Shen and Chengshi Shi and Mingkang Shi and Modi Shi and Chonghao Sima and Jianheng Song and Huijie Wang and Wenhao Wang and Dafeng Wei and Chengen Xie and Guo Xu and Junchi Yan and Cunbiao Yang and Lei Yang and Shukai Yang and Maoqing Yao and Jia Zeng and Chi Zhang and Qinglin Zhang and Bin Zhao and Chengyue Zhao and others}, year = {2025}, eprint = {2503.06669}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.06669}, } @misc{grauman2021ego, title = {{Ego4D: Around the World in 3,000 Hours of Egocentric Video}}, author = {Kristen Grauman and Andrew Westbury and Eugene Byrne and Zachary Chavis and Antonino Furnari and Rohit Girdhar and Jackson Hamburger and Hao Jiang and Miao Liu and Xingyu Liu and Miguel Martin and Tushar Nagarajan and Ilija Radosavovic and Santhosh Kumar Ramakrishnan and Fiona Ryan and Jayant Sharma and Michael Wray and Mengmeng Xu and Eric Zhongcong Xu and Chen Zhao and Siddhant Bansal and Dhruv Batra and Vincent Cartillier and Sean Crane and Tien Do and Morrie Doulaty and Akshay Erapalli and Christoph Feichtenhofer and Adriano Fragomeni and Qichen Fu and Abrham Gebreselasie and Cristina Gonzalez and James Hillis and Xuhua Huang and Yifei Huang and Wenqi Jia and Weslie Khoo and Jachym Kolar and Satwik Kottur and Anurag Kumar and Federico Landini and Chao Li and Yanghao Li and Zhenqiang Li and Karttikeya Mangalam and Raghava Modhugu and Jonathan Munro and Tullie Murrell and Takumi Nishiyasu and Will Price and others}, year = {2021}, eprint = {2110.07058}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2110.07058}, } @misc{liu2023libero, title = {{LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning}}, author = {Bo Liu and Yifeng Zhu and Chongkai Gao and Yihao Feng and Qiang Liu and Yuke Zhu and Peter Stone}, year = {2023}, eprint = {2306.03310}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2306.03310}, } @misc{mees2021calvin, title = {{CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks}}, author = {Oier Mees and Lukas Hermann and Erick Rosete-Beas and Wolfram Burgard}, year = {2021}, eprint = {2112.03227}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2112.03227}, } @misc{james2019rlbench, title = {{RLBench: The Robot Learning Benchmark \& Learning Environment}}, author = {Stephen James and Zicong Ma and David Rovick Arrojo and Andrew J. Davison}, year = {2019}, eprint = {1909.12271}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1909.12271}, } @misc{yu2019meta, title = {{Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning}}, author = {Tianhe Yu and Deirdre Quillen and Zhanpeng He and Ryan Julian and Avnish Narayan and Hayden Shively and Adithya Bellathur and Karol Hausman and Chelsea Finn and Sergey Levine}, year = {2019}, eprint = {1910.10897}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/1910.10897}, } @misc{li2024evaluating, title = {{Evaluating Real-World Robot Manipulation Policies in Simulation}}, author = {Xuanlin Li and Kyle Hsu and Jiayuan Gu and Karl Pertsch and Oier Mees and Homer Rich Walke and Chuyuan Fu and Ishikaa Lunawat and Isabel Sieh and Sean Kirmani and Sergey Levine and Jiajun Wu and Chelsea Finn and Hao Su and Quan Vuong and Ted Xiao}, year = {2024}, eprint = {2405.05941}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2405.05941}, } @misc{savva2019habitat, title = {{Habitat: A Platform for Embodied AI Research}}, author = {Manolis Savva and Abhishek Kadian and Oleksandr Maksymets and Yili Zhao and Erik Wijmans and Bhavana Jain and Julian Straub and Jia Liu and Vladlen Koltun and Jitendra Malik and Devi Parikh and Dhruv Batra}, year = {2019}, eprint = {1904.01201}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/1904.01201}, } @misc{han2026embodied, title = {{Embodied Skill Bench: Benchmarking How Well Agents with Embodied Skills Perform on Physical Tasks}}, author = {Zhi Han and Zihan Guo and Chenxi Zeng and Zicai Cui and Yue Xin and Ming Zhou and Dongzhan Zhou and Weinan Zhang and Yang Li}, year = {2026}, eprint = {2610.16238}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.16238}, } @misc{wu2024robomind, title = {{RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation}}, author = {Kun Wu and Chengkai Hou and Jiaming Liu and Zhengping Che and Xiaozhu Ju and Zhuqin Yang and Meng Li and Yinuo Zhao and Zhiyuan Xu and Guang Yang and Shichao Fan and Xinhua Wang and Fei Liao and Zhen Zhao and Guangyu Li and Zhao Jin and Lecheng Wang and Jilei Mao and Ning Liu and Pei Ren and Qiang Zhang and Yaoxu Lyu and Mengzhen Liu and Jingyang He and Yulin Luo and Zeyu Gao and Chenxuan Li and Chenyang Gu and Yankai Fu and Di Wu and Xingyu Wang and Sixiang Chen and Zhenyu Wang and Pengju An and Siyuan Qian and Shanghang Zhang and Jian Tang}, year = {2024}, eprint = {2412.13877}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.13877}, } @misc{wang2026robocasa, title = {{RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation}}, author = {Haocheng Wang and Youquan Liu and Weiyu Guo and Aokai Zhang and Donghang Wu and Hongyu Liu and Sha Zhang and Weidong Yang and Ben Fei}, year = {2026}, eprint = {2610.27861}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27861}, } @misc{ramakrishnan2021habitat, title = {{Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI}}, author = {Santhosh K. Ramakrishnan and Aaron Gokaslan and Erik Wijmans and Oleksandr Maksymets and Alex Clegg and John Turner and Eric Undersander and Wojciech Galuba and Andrew Westbury and Angel X. Chang and Manolis Savva and Yili Zhao and Dhruv Batra}, year = {2021}, eprint = {2109.08238}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2109.08238}, } @misc{dasari2019robonet, title = {{RoboNet: Large-Scale Multi-Robot Learning}}, author = {Sudeep Dasari and Frederik Ebert and Stephen Tian and Suraj Nair and Bernadette Bucher and Karl Schmeckpeper and Siddharth Singh and Sergey Levine and Chelsea Finn}, year = {2019}, eprint = {1910.11215}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1910.11215}, } @misc{grauman2023ego, title = {{Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives}}, author = {Kristen Grauman and Andrew Westbury and Lorenzo Torresani and Kris Kitani and Jitendra Malik and Triantafyllos Afouras and Kumar Ashutosh and Vijay Baiyya and Siddhant Bansal and Bikram Boote and Eugene Byrne and Zach Chavis and Joya Chen and Feng Cheng and Fu-Jen Chu and Sean Crane and Avijit Dasgupta and Jing Dong and Maria Escobar and Cristhian Forigua and Abrham Gebreselasie and Sanjay Haresh and Jing Huang and Md Mohaiminul Islam and Suyog Jain and Rawal Khirodkar and Devansh Kukreja and Kevin J Liang and Jia-Wei Liu and Sagnik Majumder and Yongsen Mao and Miguel Martin and Effrosyni Mavroudi and Tushar Nagarajan and Francesco Ragusa and Santhosh Kumar Ramakrishnan and Luigi Seminara and Arjun Somayazulu and Yale Song and Shan Su and Zihui Xue and Edward Zhang and Jinxu Zhang and Angela Castillo and Changan Chen and Xinzhu Fu and Ryosuke Furuta and Cristina Gonzalez and Prince Gupta and Jiabo Hu and others}, year = {2023}, eprint = {2311.18259}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2311.18259}, } @misc{deitke2022objaverse, title = {{Objaverse: A Universe of Annotated 3D Objects}}, author = {Matt Deitke and Dustin Schwenk and Jordi Salvador and Luca Weihs and Oscar Michel and Eli VanderBilt and Ludwig Schmidt and Kiana Ehsani and Aniruddha Kembhavi and Ali Farhadi}, year = {2022}, eprint = {2212.08051}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2212.08051}, } @misc{dai2017scannet, title = {{ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes}}, author = {Angela Dai and Angel X. Chang and Manolis Savva and Maciej Halber and Thomas Funkhouser and Matthias Nießner}, year = {2017}, eprint = {1702.04405}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/1702.04405}, } @misc{sferrazza2024humanoidbench, title = {{HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation}}, author = {Carmelo Sferrazza and Dun-Ming Huang and Xingyu Lin and Youngwoon Lee and Pieter Abbeel}, year = {2024}, eprint = {2403.10506}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.10506}, } @misc{pumacay2024colosseum, title = {{THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation}}, author = {Wilbert Pumacay and Ishika Singh and Jiafei Duan and Ranjay Krishna and Jesse Thomason and Dieter Fox}, year = {2024}, eprint = {2402.08191}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2402.08191}, } @misc{chao2021dexycb, title = {{DexYCB: A Benchmark for Capturing Hand Grasping of Objects}}, author = {Yu-Wei Chao and Wei Yang and Yu Xiang and Pavlo Molchanov and Ankur Handa and Jonathan Tremblay and Yashraj S. Narang and Karl Van Wyk and Umar Iqbal and Stan Birchfield and Jan Kautz and Dieter Fox}, year = {2021}, eprint = {2104.04631}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2104.04631}, } @misc{calli2015benchmarking, title = {{Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols}}, author = {Berk Calli and Aaron Walsman and Arjun Singh and Siddhartha Srinivasa and Pieter Abbeel and Aaron M. Dollar}, year = {2015}, eprint = {1502.03143}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1502.03143}, } @misc{damen2020rescaling, title = {{Rescaling Egocentric Vision}}, author = {Dima Damen and Hazel Doughty and Giovanni Maria Farinella and Antonino Furnari and Evangelos Kazakos and Jian Ma and Davide Moltisanti and Jonathan Munro and Toby Perrett and Will Price and Michael Wray}, year = {2020}, eprint = {2006.13256}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2006.13256}, } @misc{liu2022hoi, title = {{HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction}}, author = {Yunze Liu and Yun Liu and Che Jiang and Kangbo Lyu and Weikang Wan and Hao Shen and Boqiang Liang and Zhoujie Fu and He Wang and Li Yi}, year = {2022}, eprint = {2203.01577}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2203.01577}, } @misc{yang2022oakink, title = {{OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction}}, author = {Lixin Yang and Kailin Li and Xinyu Zhan and Fei Wu and Anran Xu and Liu Liu and Cewu Lu}, year = {2022}, eprint = {2203.15709}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2203.15709}, } @misc{fan2022arctic, title = {{ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}}, author = {Zicong Fan and Omid Taheri and Dimitrios Tzionas and Muhammed Kocabas and Manuel Kaufmann and Michael J. Black and Otmar Hilliges}, year = {2022}, eprint = {2204.13662}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2204.13662}, } @misc{zhang2024vlabench, title = {{VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks}}, author = {Shiduo Zhang and Zhe Xu and Peiju Liu and Xiaopeng Yu and Yuan Li and Qinghui Gao and Zhaoye Fei and Zhangyue Yin and Zuxuan Wu and Yu-Gang Jiang and Xipeng Qiu}, year = {2024}, eprint = {2412.18194}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.18194}, } @misc{geng2025roboverse, title = {{RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning}}, author = {Haoran Geng and Feishi Wang and Songlin Wei and Yuyang Li and Bangjun Wang and Boshi An and Charlie Tianyue Cheng and Haozhe Lou and Peihao Li and Yen-Jen Wang and Yutong Liang and Dylan Goetting and Chaoyi Xu and Haozhe Chen and Yuxi Qian and Yiran Geng and Jiageng Mao and Weikang Wan and Mingtong Zhang and Jiangran Lyu and Siheng Zhao and Jiazhao Zhang and Jialiang Zhang and Chengyang Zhao and Haoran Lu and Yufei Ding and Ran Gong and Yuran Wang and Yuxuan Kuang and Ruihai Wu and Baoxiong Jia and Carlo Sferrazza and Hao Dong and Siyuan Huang and Yue Wang and Jitendra Malik and Pieter Abbeel}, year = {2025}, eprint = {2504.18904}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2504.18904}, } @misc{zhou2026egoexplorer, title = {{EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ}}, author = {Yunsong Zhou and Xuekun Jiang and Haiqi Shen and Hangxu Liu and Chaojian Shi and Yujie Liu and Jingyuan Li and Haoran Yang and Jiafei Cao and Dongzhan Zhou and Dong Wang and Yao Mu and Chunhua Shen and Weinan Zhang}, year = {2026}, eprint = {2610.18872}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.18872}, } @misc{luo2026handson, title = {{HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation}}, author = {Tianwei Luo and Yiming He and Hongjin Wu and Ting Pan and Debin Ren and Haorui Guo and Junlin Yang and Yuxin Zuo and Zhehao Kou and Kaisen Yang and Zhuoqun Lai and Yi Ding and Jiale Yu and Yuchen Zhang and Zijie Qiu and Haozhan Li and Ning Ding}, year = {2026}, eprint = {2610.26765}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26765}, } @misc{liu2026robovalue, title = {{RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models}}, author = {Shengbang Liu and Zhengye Du and Zhilong Wan and Honghao Su and Chenxiang Xia and Chang Ge and Jinyang Xiao and Nan Wang and Zhipeng Hu and Huining Yuan and Shu'ang Yu and Yue Chen and Tianxing Chen and Chuankang Li and Maoqing Yao and Wenbo Ding and Yu Wang and Guanghui Ren and Chao Yu}, year = {2026}, eprint = {2610.26663}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.26663}, } @misc{sung2026libero, title = {{LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints}}, author = {Ming Shin Cindy Sung and Duan Leijiahao and Haoxiang Wang and Boning Tan and Liangna Fu and Chao Tan and Yafu Li and Yulong Chen and Chaoqun Wan and Zhen Huang and Shuxian Liang and Xian-Sheng Hua}, year = {2026}, eprint = {2610.16782}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2610.16782}, } @misc{hoque2025egodex, title = {{EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video}}, author = {Ryan Hoque and Peide Huang and David J. Yoon and Mouli Sivapurapu and Jian Zhang}, year = {2025}, eprint = {2505.11709}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2505.11709}, } @misc{leng2026flora, title = {{FLORA: An Open Model Suite for Scaling Robotics Data Engines}}, author = {Sicong Leng and Yunze Man and Zhiqi Li and Jing Wang and Yuhe Zhang and Ryan Punamiya and Siddharth Patki and Kaiyuan Zheng and Zi-ang Cao and Zhiding Yu and Sifei Liu and Danfei Xu and Ben Levin and Jan Kautz and Yuke Zhu and Johan Bjorck and Linxi "Jim" Fan}, year = {2026}, eprint = {2610.31779}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31779}, } @misc{wang2026bidex, title = {{BiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks}}, author = {Yong Wang and Kecheng Zheng and Xing Zhu and Chao Xu and Yujun Shen and Shengze Cai}, year = {2026}, eprint = {2610.25459}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.25459}, } @misc{wang2026astrobench, title = {{AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation}}, author = {Zizhe Wang and Jia Deng and Xin Lu and Zehao Jia and Yi Huang and Yao Zhu}, year = {2026}, eprint = {2610.31064}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.31064}, } @misc{chen2026embodied, title = {{Embodied Playground: A Long-Horizon Agentic Robotics Benchmark for Physical, Strategic, and Spatial Reasoning}}, author = {Feng Chen and Pei Zhou and Lixuan He and Yunchao Yao and Li Sun and Shenghua Gao and Mingyu Ding and Kaifeng Zhang and Kaichen Zhou and Yi Ma}, year = {2026}, eprint = {2610.27039}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27039}, } @misc{chen2026behavior, title = {{Behavior Spatial Benchmark: Evaluating Spatial Understanding for Robotics}}, author = {Sirui Chen and Huang Huang and Qineng Wang and Wenlong Huang and Manling Li and Ruohan Zhang and Li Fei-Fei and Jiajun Wu}, year = {2026}, eprint = {2610.34051}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34051}, } @misc{gao2026embodiedlab, title = {{EmbodiedLab: Benchmarking Embodied Agents That Act to Know}}, author = {Hongcheng Gao and Zelin Zheng and Alex Zhou and Jay Zhu and Shijia Ge and Yazhe Wang and Xiping Li and Jianshu Zeng and Di Wu and Xuan Shangguan and Yexing Wan and Lingyu He and Yongli Wang and Xiaohan Yu and Zhiqi Jia and Yue Liu and Bryan Hooi and Yinpeng Dong and Wentao Zhang and Sihang Wu and Xiao He}, year = {2026}, eprint = {2610.35385}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.35385}, } @misc{mao2026robotagentbench, title = {{RobotAgentBench: Towards Open-world Robot Autonomy}}, author = {Lingjun Mao and Jinglin Cao and Lukun He and Wenpeng Xu and Yuchen Yan and Hengyu Jin and Zijun Zhang and Jinzhou Tang and Songyao Jin and Ziche Liu and Yifei Shao and Junbo Huang and Fang Nan and Ruobing Han and Ziqiao Xi and Ziming Xu and Shuang Liang and Sibo Zhu and Wenyi Wu and Xinyue Wang and Yiming Huang and Xinkai Zou and Gao Zhu and Kun Zhou and Biwei Huang}, year = {2026}, eprint = {2610.34649}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.34649}, } @misc{hickok2026so, title = {{SO-101 Bench: Accessible Spatial Manipulation}}, author = {Truman Hickok}, year = {2026}, eprint = {2610.36420}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.36420}, } @misc{ma2026robojudge, title = {{RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation}}, author = {Siyuan Ma and Yu Qi and Cheng Ye and Ruotian Peng and Xinyi Xu and Zitiantao Lin and Zedong Cai and Yijian Huang and Weiyang Liu and Siyuan Wang and Yandong Wen}, year = {2026}, eprint = {2610.27782}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2610.27782}, } @misc{deryo2026egocontact, title = {{EgoContact: Evaluating Physical Intelligence with Egocentric Video}}, author = {Adam Deryło and Alexey Gavryushin and Daniel Cremers and Marc Pollefeys and Xi Wang}, year = {2026}, eprint = {2610.39167}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39167}, } @misc{guru2026molmospaces, title = {{MolmoSpaces-CommonSense: Evaluating Commonsense in Robotic Manipulation Policies}}, author = {Arjun Guru and Max Argus and Jae Sung Park and Jiafei Duan and Ali Farhadi and Ranjay Krishna}, year = {2026}, eprint = {2610.41377}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.41377}, } @misc{zhu2026wirecraft, title = {{WireCraft: A Simulation Benchmark for Industrial DLO Manipulation}}, author = {Chongyu Zhu and Ramy ElMallah and Hyegang Kim and Zachary Tang and Jiachen Rao and Artem Arutyunov and Seungyeon Ha and Chi-Guhn Lee}, year = {2026}, eprint = {2606.18097}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.18097}, } @misc{xu2026burger, title = {{BURGER: Benchmarking and Understanding Robotic Generalization via Embodied Drawing}}, author = {Xiangyu Xu and Bangshuai Peng and Ziyi Liu and Mengjie Zhao and Chenhao Lu and Zhengyang Fan and Huazhe Xu and Kaizhe Hu}, year = {2026}, eprint = {2610.40532}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40532}, } @misc{sirigiri2026diversity, title = {{Diversity You Can Actually Measure: A Fast, Model-Free Diversity Metric for Robotics Datasets}}, author = {Sreevardhan Sirigiri and Nathan Samuel de Lara and Christopher Agia and Florian Shkurti and Fabio Ramos}, year = {2026}, eprint = {2603.11634}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.11634}, } @misc{jiang2026what, title = {{What Are We Actually Benchmarking in Robot Manipulation?}}, author = {Tianchong Jiang and Xiangshan Tan and Samuel Wheeler and Luzhe Sun and Tewodros W. Ayalew and Matthew Walter}, year = {2026}, eprint = {2606.04233}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.04233}, } @misc{wang2026ego, title = {{Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data}}, author = {Ye Wang and Pei Lin and Xiong-Hui Chen and Haoqi Yuan and Zhixuan Liang and Yiyang Huang and Anzhe Chen and Zixing Lei and Jie Zhang and Tao Zhang and Haoyang Li and Tong Zhang and Chenxi Xiao and Ziyuan Jiao and Qin Jin}, year = {2026}, eprint = {2608.02580}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.02580}, } @misc{wu2026atom, title = {{ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies}}, author = {Zenan Wu and Bingqing Wei and Lu Liu and Zheqi He and Xi Wang and Jiakang Liu and Zehui Li and Guocai Yao and Jing-Shu Zheng and Xi Yang and Yongtao Wang}, year = {2026}, eprint = {2606.16826}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16826}, } @misc{lee2025phuma, title = {{PHUMA: Physically Reliable Humanoid Locomotion Dataset}}, author = {Kyungmin Lee and Sibeen Kim and Youngdo Lee and Minho Park and Hyunseung Kim and Dongyoon Hwang and Donghu Kim and Hojoon Lee and Jaegul Choo}, year = {2025}, eprint = {2510.26236}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.26236}, } @misc{chen2026robojev, title = {{RoboJev: An Open Vision-Language Judge for Robot Success Detection}}, author = {Josef Liyanjun Chen}, year = {2026}, eprint = {2610.33718}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.33718}, } @misc{ping2026dexarena, title = {{DexArena: A Unified Benchmark for Long-Horizon Dexterous Manipulation}}, author = {Haonan Ping and Jianshu Hu and Yimin Wang and Yi Zhu and Pai Liang and Qiyan Jin and Qirui Bao and Ying Qian and Xinyang Ding and Hongfei Qiao and Tianle Xue and Yucheng Bai and Soo Wei Jie and Shuguang Li and Yutong Ban}, year = {2026}, eprint = {2611.02629}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.02629}, } @misc{xu2026omnipiano, title = {{OmniPiano: Diverse Dexterous Piano-Playing Challenges for Standard, Robust, Safe, and Multi-Agent RL}}, author = {Fan Xu and Fan Yang and Yifan Xu and Ruiyuan Zhang and Yimou Wu and Nuo Yi and Muning Wen and Guang Chen and Costas Spanos and Shangding Gu}, year = {2026}, eprint = {2611.00243}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2611.00243}, } @misc{selvaraj2026rollout, title = {{Rollout then Recycle: 3,718 Labelled Real-Robot Episodes from Benchmarking 7 Policies on 12 Tasks}}, author = {Praveen Selvaraj and Lorenzo Uttini and Ville Kuosmanen}, year = {2026}, eprint = {2611.03168}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03168}, } @misc{huang2026clothdojo, title = {{ClothDojo: Learned Data Generation and Benchmarking for Bimanual Garment Flattening and Folding}}, author = {Zilong Huang and Zipeng Ye and Caicheng Wang and Yuchen Xie and Jiaxiang Luo}, year = {2026}, eprint = {2611.01190}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.01190}, } @misc{wang2026vision, title = {{Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines}}, author = {Ziyao Wang and Bingying Wang and Hanrong Zhang and Tingting Du and Tianyang Chen and Guoheng Sun and Yexiao He and Zheyu Shen and Wanghao Ye and Ang Li}, year = {2026}, eprint = {2604.23001}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.23001}, } @misc{yakefu2025robochallenge, title = {{RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies}}, author = {Adina Yakefu and Bin Xie and Chongyang Xu and Enwen Zhang and Erjin Zhou and Fan Jia and Haitao Yang and Haoqiang Fan and Haowei Zhang and Hongyang Peng and Jing Tan and Junwen Huang and Kai Liu and Kaixin Liu and Kefan Gu and Qinglun Zhang and Ruitao Zhang and Saike Huang and Shen Cheng and Shuaicheng Liu and Tiancai Wang and Tiezhen Wang and Wei Sun and Wenbin Tang and Yajun Wei and Yang Chen and Youqiang Gui and Yucheng Zhao and Yunchao Ma and Yunfei Wei and Yunhuan Yang and Yutong Guo and Ze Chen and Zhengyuan Du and Ziheng Zhang and Ziming Liu and Ziwei Yan}, year = {2025}, eprint = {2510.17950}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2510.17950}, } @misc{gilewicz2026is, title = {{Is It the Curriculum or Just the Easy Start? Benchmarking Unsupervised Environment Design on Quadrupeds}}, author = {Jakub Gilewicz and Dominik Galus and Piotr Wojdas}, year = {2026}, eprint = {2610.40364}, archivePrefix = {arXiv}, primaryClass = {cs.LG}, url = {https://arxiv.org/abs/2610.40364}, } @misc{zhang2026pyrua, title = {{PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data}}, author = {Kewei Zhang and Juncheng Ma and Guodong Lv and Duomin Wang and Feixiang Ruan and Ruiyang Si and Chuanrui Zhang and Yuxuan Chen and Hao Chen and Yichen Liu and Yintianrun Zhang and Yufan Deng and Enze Xie and Daquan Zhou}, year = {2026}, eprint = {2611.05320}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05320}, } @misc{wu2026roboscope, title = {{RoboScope Kit: Unified Interfaces for Fast and Scalable Embodied-AI Evaluation}}, author = {Deng-Ke Wu and Yifan Jin and Yida Yang and Lei Qian and Zhaoye Zhou and Hongru Zhang and Kai Ye and Shuyuan Hu and Yiran Mao and Zewei Ye and Bo Zhao}, year = {2026}, eprint = {2611.03850}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03850}, } @misc{wu2026cronos, title = {{CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation}}, author = {Po-Yi Wu and Djengo Cyun-Jyun Fang and Dian Cheng and Tsung-Wei Ke}, year = {2026}, eprint = {2611.05080}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05080}, } @misc{punamiya2026egoverse, title = {{EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World}}, author = {Ryan Punamiya and Simar Kareer and Zeyi Liu and Josh Citron and Ri-Zhao Qiu and Xiongyi Cai and Alexey Gavryushin and Jiaqi Chen and Davide Liconti and Lawrence Y. Zhu and Patcharapong Aphiwetsa and Baoyu Li and Aniketh Cheluva and Pranav Kuppili and Yangcen Liu and Dhruv Patel and Aidan Gao and Hye-Young Chung and Ryan Co and Renee Zbizika and Jeff Liu and Xiaomeng Xu and Haoyu Xiong and Geng Chen and Sebastiano Oliani and Wenkai Xuan and Chenyu Yang and Xi Wang and James Fort and Richard Newcombe and Josh Gao and Jason Chong and Garrett Matsuda and Aseem Doriwala and Marc Pollefeys and Robert Katzschmann and Xiaolong Wang and Shuran Song and Judy Hoffman and Danfei Xu}, year = {2026}, eprint = {2604.07607}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.07607}, } @misc{jiang2026robowm, title = {{RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation}}, author = {Feng Jiang and Yang Chen and Kyle Xu and Yuchen Liu and Haifeng Wang and Zhenhao Shen and Jasper Lu and Shengze Huang and Yuanfei Wang and Chen Xie and Ruihai Wu}, year = {2026}, eprint = {2604.19092}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2604.19092}, } @misc{ze2025twist, title = {{TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System}}, author = {Yanjie Ze and Siheng Zhao and Weizhuo Wang and Angjoo Kanazawa and Rocky Duan and Pieter Abbeel and Guanya Shi and Jiajun Wu and C. Karen Liu}, year = {2025}, eprint = {2511.02832}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2511.02832}, } @misc{wilcox2026mesa, title = {{MESA: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics}}, author = {Albert Wilcox and Frank Chang and Nhi Nguyen and Aishani Chakraborty and Jeremy A. Collins and Vaibhav Saxena and Benjamin Joffe and Siddharth Karamcheti and Animesh Garg}, year = {2026}, eprint = {2611.05567}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.05567}, } @misc{lin2026beaker, title = {{BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories}}, author = {Fei Lin and Tengchao Zhang and Ziyang Gong and Xiaotong Yu and Bohan Zhang and Yifan Zhou and Qihao Yang and Ji Dai and Dong Li and Yining Jiang and Qinghua Ni and Jun Huang and Qiang Zhang and Yue Zhou and Zhihang Zhong and Yonglin Tian and Fei-Yue Wang and Xue Yang}, year = {2026}, eprint = {2611.06911}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2611.06911}, } @misc{gong2023arnold, title = {{ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes}}, author = {Ran Gong and Jiangyong Huang and Yizhou Zhao and Haoran Geng and Xiaofeng Gao and Qingyang Wu and Wensi Ai and Ziheng Zhou and Demetri Terzopoulos and Song-Chun Zhu and Baoxiong Jia and Siyuan Huang}, year = {2023}, eprint = {2304.04321}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2304.04321}, } @misc{zhu2024point, title = {{Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning}}, author = {Haoyi Zhu and Yating Wang and Di Huang and Weicai Ye and Wanli Ouyang and Tong He}, year = {2024}, eprint = {2402.02500}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2402.02500}, } @misc{bulat2026beyond, title = {{Beyond Infraction Scores: Failure-Boundary Profiles for Closed-Loop Evaluation of Driving and Robot Navigation Agents}}, author = {Milan Bulat and Gino Ardelean and Ellington Kirby}, year = {2026}, eprint = {2611.06453}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.06453}, } @misc{guo2026robofollow, title = {{RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents}}, author = {Chang Guo and Yukun Xie and Bohan Tan and Zheng Chang and Zhaokai Yin and Qianli Ma and Yingqiao Wang and Chao Liang and Zhipeng Zhang}, year = {2026}, eprint = {2609.25636}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.25636}, } @misc{li2026rmmbench, title = {{RMMBench: A Comprehensive Benchmark for Robotic Mobile Manipulation}}, author = {Huapeng Li and Fuxiang Feng and Jinqiu Fan and Shuo Yang and Fengjiao Chen and Xuezhi Cao and Ran Song and Wei Zhang}, year = {2026}, eprint = {2610.05414}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.05414}, } @misc{chen2026foldnet, title = {{FoldNet++: a Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding}}, author = {Yuxing Chen and Zhiyuan Wei and Bowen Xiao and Zhizheng Zhang and He Wang}, year = {2026}, eprint = {2609.12433}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.12433}, } @misc{allshire2026scalable, title = {{Scalable Behavior Cloning with Open Data, Training, and Evaluation}}, author = {Arthur Allshire and Himanshu Gaurav Singh and Ritvik Singh and Adam Rashid and Hongsuk Choi and David McAllister and Justin Yu and Yiyuan Chen and Huang Huang and Pieter Abbeel and Xi Chen and Rocky Duan and Phillip Isola and Jitendra Malik and Fred Shentu and Guanya Shi and Philipp Wu and Angjoo Kanazawa}, year = {2026}, eprint = {2606.27375}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.27375}, } @misc{wang2026probing, title = {{Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration}}, author = {Jun Wang and Xiaohao Xu and Xiaonan Huang}, year = {2026}, eprint = {2605.31196}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2605.31196}, } @misc{fang2026robopocket, title = {{RoboPocket: Improve Robot Policies Instantly with Your Phone}}, author = {Junjie Fang and Wendi Chen and Han Xue and Fangyuan Zhou and Tian Le and Yi Wang and Yuting Zhang and Jun Lv and Chuan Wen and Cewu Lu}, year = {2026}, eprint = {2603.05504}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.05504}, } @misc{jindal2025can, title = {{Can AI Perceive Physical Danger and Intervene?}}, author = {Abhishek Jindal and Dmitry Kalashnikov and R. Alex Hofer and Oscar Chang and Divya Garikapati and Anirudha Majumdar and Pierre Sermanet and Vikas Sindhwani}, year = {2025}, eprint = {2509.21651}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2509.21651}, } @misc{wang2026helpmeout, title = {{HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution}}, author = {Haoran Wang and Jingwei Huang and Anqing Duan and Ho Seok Ahn and Bruce Macdonald}, year = {2026}, eprint = {2610.17694}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.17694}, } @misc{gu2026monkey, title = {{Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation}}, author = {Weiwei Gu and Anmol Gupta and Anant Sah and Ryan Varghese and Lalitha Shreya Vanam and Prabhath Adireddi and Peter Karkus and Nakul Gopalan}, year = {2026}, eprint = {2609.08209}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.08209}, } @misc{ji2026hiphi, title = {{HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object-Interaction}}, author = {Jiahao Ji and Ji Ma and Runhan Zhang and Runyi Yu and Wenjia Wang and Weiheng Chi and Qianqian Peng and Weichao Yan and Yongfei Gu and Ye Tian and Ting Wu and Longwei Li and Chun Yuan and Ruoli Dai and Lei Han}, year = {2026}, eprint = {2608.16222}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.16222}, } @misc{zhou2026imitator, title = {{The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction}}, author = {Xunzhe Zhou and Yiyang Cai and Fengyi Wang and Ran Ju and Hanxiang Ren and Ruizhe Liu and Yu Zhang and Qian Luo and Feng Chen and Pei Zhou and Yi Ma and Yanchao Yang}, year = {2026}, eprint = {2608.22301}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2608.22301}, } @misc{maurya2026imbench, title = {{IMBench: A Benchmark for Intuitive Robotic Manipulation}}, author = {Anurag Maurya and Sukhvansh Jain and Prajwal Avhad and Gautham Balachandran and Ziyi Zhou and Atharva Kshirsagar and Satyam Singh and Bowen Li. Rishabh Mukund and Ritul Singh and Jatin Vira and Suvonil Chatterjee and Devesh K. Jha}, year = {2026}, eprint = {2607.15641}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.15641}, } @misc{paliwal2026do, title = {{Do as I Do: Dexterous Manipulation Data from Everyday Human Videos}}, author = {Bhawna Paliwal and Haritheja Etukuru and William Liang and Pieter Abbeel and Nur Muhammad Mahi Shafiullah and Jitendra Malik}, year = {2026}, eprint = {2606.19333}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.19333}, } @misc{luo2026robolineage, title = {{RoboLineage: Agent-Native Data Lifecycle Governance Across Robot Policy Iterations}}, author = {Qian Luo and Wentao Guo and Zhennan Qin and Nanchun Guo and Yunhan Zhao and Yi Ma and Yanchao Yang}, year = {2026}, eprint = {2606.22142}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22142}, } @misc{ohkawa2026yubi, title = {{YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale}}, author = {Takehiko Ohkawa and Jumpei Arima and Yuki Noguchi and Masatoshi Tateno and Makoto Sugiura and Takuya Okubo and Kengo Ikeuchi and Yuma Shin and Hiroki Nishizawa and Naoaki Kanazawa and Yuki Wakayama and Daiki Fukunaga and Koshi Makihara and Tomohiro Motoda and Floris Erich and Yukiyasu Domae and Tatsuya Matsushima and Yohishiro Okumatsu and Kei Ota}, year = {2026}, eprint = {2606.10244}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.10244}, } @misc{brandes2026egohtr, title = {{EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal}}, author = {Alex Brandes and Haig Conti Georges Sajelian and Manthan Patel and Dominik Hollidt and Chenhao Li and Matthias Heyrman and Oliver Hausdoerfer and Manuel Kaufmann and Xi Wang and Jonas Frey and Angela P. Schoellig and Christian Holz and Marc Pollefeys and Marco Hutter}, year = {2026}, eprint = {2607.13472}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.13472}, } @misc{zhang2026robogene, title = {{RoboGene: Diversity-Driven Agentic Task Generation Framework for VLA Pre-training}}, author = {Yixue Zhang and Kun Wu and Zhi Gao and Zhen Zhao and Pei Ren and Zhiyuan Xu and Fei Liao and Xinhua Wang and Shichao Fan and Di Wu and Qiuxuan Feng and Meng Li and Zhengping Che and Chang Liu and Jian Tang}, year = {2026}, eprint = {2602.16444}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2602.16444}, } @misc{wu2026navverse, title = {{NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulation}}, author = {Junzhe Wu and Yue Hu and Zeyu Han and Po-Hsun Chang and Yinan Dong and Behrad Rabiei and Maani Ghaffari}, year = {2026}, eprint = {2607.19695}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.19695}, } @misc{choi2026autodex, title = {{AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection}}, author = {Mingi Choi and Gunhee Kim and Jisoo Kim and Taeksoo Kim and Taeyun Ha and Jongbin Lim and Hanbyul Joo}, year = {2026}, eprint = {2606.23689}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.23689}, } @misc{wang2026im, title = {{IM-ENGINE: Image Editing for Embodied Data Generation}}, author = {Yian Wang and Junyi Cao and Xiaowen Qiu and Chuang Gan}, year = {2026}, eprint = {2609.06279}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.06279}, } @misc{xu2026athena, title = {{ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation}}, author = {Tao Xu and Jiaxin Wang and Runhao Zhang and Jiayi Guan and Xianchao Zeng and Weixi Song and Xinyu Zhou and Zhetao Chen and Guang Chen and Yong-Lu Li}, year = {2026}, eprint = {2606.16208}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.16208}, } @misc{xiao2026h, title = {{H2RBench: A Real-to-Sim Benchmark for Evaluating Human-to-Robot Transfer}}, author = {Chuyang Xiao and Haotian Zhan and Sriram Krishna and Peilin Meng and Muhammad Zubair Irshad and Sergey Zakharov and David Held}, year = {2026}, eprint = {2609.24778}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.24778}, } @misc{blank2026sparc, title = {{SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale}}, author = {Nils Blank and Paul Mattes and Maximilian Xiling Li and Jakub Suliga and Thomas Roth and Moritz Reuss and Pankhuri Vanjani and Rudolf Lioutikov}, year = {2026}, eprint = {2606.13497}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.13497}, } @misc{sohm2026klasktron, title = {{KlaskTron-IL: A Contact-Rich Adversarial Imitation Learning Benchmark with a Validated Sim-to-Real Bridge}}, author = {Nicklas Sohm and Aswin Ramachandran and Raffaello D'Andrea}, year = {2026}, eprint = {2611.03091}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03091}, } @misc{elmoghany2026tooldex, title = {{ToolDex: An Ego-Exo Human Demonstration Dataset for Creative Physical Tool Use}}, author = {Mohamed Elmoghany and Kehan Li and Ruoqu Chen and Tarun Chiruvolu and Shutong Zhang and Ryan Wang and Stephen Tian and Yaru Niu and Michelle Guo and Ding Zhao and Weiyu Liu and Mengdi Xu and Li Fei-Fei and Jiajun Wu}, year = {2026}, eprint = {2611.09036}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.09036}, } @misc{zhang2026flex, title = {{Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents}}, author = {Jingdong Zhang and Jionghao Wang and Zhengming Yu and Yancheng Cai and Wei Chow and Chris Choy and Zhiyang Dou and Hang Hua and Jiachen Li and Zhixuan Liu and Chen Wang and Songlin Wei and Siyuan Yang and Yu Yuan and Xiaohang Zhan and Yucheng Zhang and Shuhong Zheng and Xin Li and Lingjie Liu and Wojciech Matusik and Zhengzhong Tu and Wenping Wang}, year = {2026}, eprint = {2611.08946}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2611.08946}, } @misc{zhou2026harp, title = {{HARP-Bench: Benchmarking Robot Manipulation Around Active Humans}}, author = {Qinhong Zhou and Riley Zong and Chunru Lin and Diyi Hu and Shivraj Singh Bhatti and Hongxin Zhang and Lin Qiu and Hanqing Zeng and Chuang Gan}, year = {2026}, eprint = {2611.11123}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.11123}, } @misc{deshmukh2026robomocap, title = {{RoboMoCap: A Large-Scale Whole-Body Motion Capture Dataset with Egocentric Vision for Robot Learning}}, author = {Mayur Deshmukh and Aaron Tung and Junyi Li and Nikash Bhardwaj and Ademi Adeniji and Vincent Liu and Michael Cho and Jiafei Duan}, year = {2026}, eprint = {2611.10994}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.10994}, } @misc{glaer2026benchmarking, title = {{Benchmarking Real-World Robotic Manipulation through Stochastic Challenges}}, author = {Elias Gläßer and Gülhan Şikaroğlu and Pavlo Kupyn and Marc Pollefeys and Zuria Bauer and Hermann Blum}, year = {2026}, eprint = {2611.12804}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.12804}, } @misc{shaw2023leap, title = {{LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning}}, author = {Kenneth Shaw and Ananye Agarwal and Deepak Pathak}, year = {2023}, eprint = {2309.06440}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.06440}, } @misc{wu2023gello, title = {{GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators}}, author = {Philipp Wu and Yide Shentu and Zhongke Yi and Xingyu Lin and Pieter Abbeel}, year = {2023}, eprint = {2309.13037}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.13037}, } @misc{cheng2024open, title = {{Open-TeleVision: Teleoperation with Immersive Active Visual Feedback}}, author = {Xuxin Cheng and Jialong Li and Shiqi Yang and Ge Yang and Xiaolong Wang}, year = {2024}, eprint = {2407.01512}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.01512}, } @misc{liao2024berkeley, title = {{Berkeley Humanoid: A Research Platform for Learning-based Control}}, author = {Qiayuan Liao and Bike Zhang and Xuanyu Huang and Xiaoyu Huang and Zhongyu Li and Koushil Sreenath}, year = {2024}, eprint = {2407.21781}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.21781}, } @misc{chi2025demonstrating, title = {{Demonstrating Berkeley Humanoid Lite: An Open-source, Accessible, and Customizable 3D-printed Humanoid Robot}}, author = {Yufeng Chi and Qiayuan Liao and Junfeng Long and Xiaoyu Huang and Sophia Shao and Borivoje Nikolic and Zhongyu Li and Koushil Sreenath}, year = {2025}, eprint = {2504.17249}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2504.17249}, } @misc{shi2025toddlerbot, title = {{ToddlerBot: Open-Source ML-Compatible Humanoid Platform for Loco-Manipulation}}, author = {Haochen Shi and Weizhuo Wang and Shuran Song and C. Karen Liu}, year = {2025}, eprint = {2502.00893}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.00893}, } @misc{jiang2025behavior, title = {{BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities}}, author = {Yunfan Jiang and Ruohan Zhang and Josiah Wong and Chen Wang and Yanjie Ze and Hang Yin and Cem Gokmen and Shuran Song and Jiajun Wu and Li Fei-Fei}, year = {2025}, eprint = {2503.05652}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.05652}, } @misc{team2024aloha, title = {{ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperation}}, author = {ALOHA 2 Team and Jorge Aldaco and Travis Armstrong and Robert Baruch and Jeff Bingham and Sanky Chan and Kenneth Draper and Debidatta Dwibedi and Chelsea Finn and Pete Florence and Spencer Goodrich and Wayne Gramlich and Torr Hage and Alexander Herzog and Jonathan Hoech and Thinh Nguyen and Ian Storz and Baruch Tabanpour and Leila Takayama and Jonathan Tompson and Ayzaan Wahid and Ted Wahrburg and Sichun Xu and Sergey Yaroshenko and Kevin Zakka and Tony Z. Zhao}, year = {2024}, eprint = {2405.02292}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2405.02292}, } @misc{kemp2021design, title = {{The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environments}}, author = {Charles C. Kemp and Aaron Edsinger and Henry M. Clever and Blaine Matulevich}, year = {2021}, eprint = {2109.10892}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2109.10892}, } @misc{christoph2025orca, title = {{ORCA: An Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning}}, author = {Clemens C. Christoph and Maximilian Eberlein and Filippos Katsimalis and Arturo Roberti and Aristotelis Sympetheros and Michel R. Vogt and Davide Liconti and Chenyu Yang and Barnabas Gavin Cangan and Ronan J. Hinchet and Robert K. Katzschmann}, year = {2025}, eprint = {2504.04259}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2504.04259}, } @misc{ben2025homie, title = {{HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit}}, author = {Qingwei Ben and Feiyu Jia and Jia Zeng and Junting Dong and Dahua Lin and Jiangmiao Pang}, year = {2025}, eprint = {2502.13013}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.13013}, } @misc{qin2023anyteleop, title = {{AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System}}, author = {Yuzhe Qin and Wei Yang and Binghao Huang and Karl Van Wyk and Hao Su and Xiaolong Wang and Yu-Wei Chao and Dieter Fox}, year = {2023}, eprint = {2307.04577}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2307.04577}, } @misc{fang2023airexo, title = {{AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wild}}, author = {Hongjie Fang and Hao-Shu Fang and Yiming Wang and Jieji Ren and Jingjing Chen and Ruo Zhang and Weiming Wang and Cewu Lu}, year = {2023}, eprint = {2309.14975}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2309.14975}, } @misc{fang2025airexo, title = {{AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons}}, author = {Hongjie Fang and Chenxi Wang and Yiming Wang and Jingjing Chen and Shangning Xia and Jun Lv and Zihao He and Xiyan Yi and Yunhan Guo and Xinyu Zhan and Lixin Yang and Weiming Wang and Cewu Lu and Hao-Shu Fang}, year = {2025}, eprint = {2503.03081}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2503.03081}, } @misc{ding2024bunny, title = {{Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning}}, author = {Runyu Ding and Yuzhe Qin and Jiyue Zhu and Chengzhe Jia and Shiqi Yang and Ruihan Yang and Xiaojuan Qi and Xiaolong Wang}, year = {2024}, eprint = {2407.03162}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.03162}, } @misc{dass2024telemoma, title = {{TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation}}, author = {Shivin Dass and Wensi Ai and Yuqian Jiang and Samik Singh and Jiaheng Hu and Ruohan Zhang and Peter Stone and Ben Abbatematteo and Roberto Martín-Martín}, year = {2024}, eprint = {2403.07869}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2403.07869}, } @misc{grimminger2019open, title = {{An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research}}, author = {Felix Grimminger and Avadesh Meduri and Majid Khadiv and Julian Viereck and Manuel Wüthrich and Maximilien Naveau and Vincent Berenz and Steve Heim and Felix Widmaier and Thomas Flayols and Jonathan Fiene and Alexander Badri-Spröwitz and Ludovic Righetti}, year = {2019}, eprint = {1910.00093}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/1910.00093}, } @misc{xu2025dexumi, title = {{DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation}}, author = {Mengda Xu and Han Zhang and Yifan Hou and Zhenjia Xu and Linxi Fan and Manuela Veloso and Shuran Song}, year = {2025}, eprint = {2505.21864}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2505.21864}, } @misc{yang2024ace, title = {{ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation}}, author = {Shiqi Yang and Minghuan Liu and Yuzhe Qin and Runyu Ding and Jialong Li and Xuxin Cheng and Ruihan Yang and Sha Yi and Xiaolong Wang}, year = {2024}, eprint = {2408.11805}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2408.11805}, } @misc{lin2024learning, title = {{Learning Visuotactile Skills with Two Multifingered Hands}}, author = {Toru Lin and Yu Zhang and Qiyang Li and Haozhi Qi and Brent Yi and Sergey Levine and Jitendra Malik}, year = {2024}, eprint = {2404.16823}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2404.16823}, } @misc{wu2024tidybot, title = {{TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning}}, author = {Jimmy Wu and William Chong and Robert Holmberg and Aaditya Prasad and Yihuai Gao and Oussama Khatib and Shuran Song and Szymon Rusinkiewicz and Jeannette Bohg}, year = {2024}, eprint = {2412.10447}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2412.10447}, } @misc{ha2024umi, title = {{UMI-on-Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers}}, author = {Huy Ha and Yihuai Gao and Zipeng Fu and Jie Tan and Shuran Song}, year = {2024}, eprint = {2407.10353}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2407.10353}, } @misc{zhang2025doglove, title = {{DOGlove: Dexterous Manipulation with a Low-Cost Open-Source Haptic Force Feedback Glove}}, author = {Han Zhang and Songbo Hu and Zhecheng Yuan and Huazhe Xu}, year = {2025}, eprint = {2502.07730}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2502.07730}, } @misc{zorin2025ruka, title = {{RUKA: Rethinking the Design of Humanoid Hands with Learning}}, author = {Anya Zorin and Irmak Guzey and Billy Yan and Aadhithya Iyer and Lisa Kondrich and Nikhil X. Bhattasali and Lerrel Pinto}, year = {2025}, eprint = {2504.13165}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2504.13165}, } @misc{shaw2024bimanual, title = {{Bimanual Dexterity for Complex Tasks}}, author = {Kenneth Shaw and Yulong Li and Jiahui Yang and Mohan Kumar Srirama and Ray Liu and Haoyu Xiong and Russell Mendonca and Deepak Pathak}, year = {2024}, eprint = {2411.13677}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2411.13677}, } @misc{xie2026dexport, title = {{DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection}}, author = {Amber Xie and Jiawei Fu and Xiaofeng Guo and Carmelo Sferrazza and Guanya Shi and Haozhi Qi}, year = {2026}, eprint = {2610.32969}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.32969}, } @misc{adwani2026phd, title = {{PHD-Hand: A Printable Humanoid Dexterous Hand with Linkage-Driven 3-DOA Digits}}, author = {Neel Adwani and Muhaiminul Islam Akash and Saffia Ouali and Ethan Liu and Cong Wang}, year = {2026}, eprint = {2610.29030}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.29030}, } @misc{langella2026locopilot, title = {{LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning}}, author = {Antonio Langella and Giovanni Minelli and Giovanni B. Dessy and Lorenzo Amatucci and Giulio Turrisi and Victor Barasuol and Claudio Semini}, year = {2026}, eprint = {2610.27998}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.27998}, } @misc{murali2026openjaws, title = {{OpenJaws: An Open Hardware UMI Framework with Stereo Localization for Generalist Manipulation}}, author = {Adithyavairavan Murali and Yash Oza and Karanbir Chahal and Neel Jawale and Silas De Vries and Hesam Rabeti and Erwin Coumans and Balakumar Sundaralingam and Stan Birchfield}, year = {2026}, eprint = {2610.36598}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.36598}, } @misc{hou2026egothumb, title = {{EgoThumb: A Vision-Driven Supernumerary Robotic Thumb for Autonomous Grasp and Holding Assistance}}, author = {Jianyu Hou and Jiawei Fu and Weikang Wan and Minghui Jiang and Jiajun Li and Hao Su}, year = {2026}, eprint = {2610.37582}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.37582}, } @misc{velamoor2026umi, title = {{UMI-Live for In-The-Wild Bimanual Robotics Data Collection}}, author = {Govind Velamoor and Adrian Lin and Sam Jung and Spencer Mateega and Brandon Y. Yang and Amish Sethi}, year = {2026}, eprint = {2610.39385}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.39385}, } @misc{zhang2026swapbot, title = {{SwapBot: Tool-Centric Robot Manipulation via Interchangeable End-Effectors and Tactile Sensing}}, author = {Yunchu Zhang and Ray Song and Junhan Jiao and Liyiming Ke and Yuchen Yang and Ruihan Gao and Emma Romig and Siddhartha Srinivasa and Yiyue Luo}, year = {2026}, eprint = {2610.40646}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.40646}, } @misc{tao2026pixel, title = {{Pixel: A Co-Designed Full-Stack Robot System for Learning General-Purpose Mobile Manipulation}}, author = {Tony Tao and Jason Jingzhou Liu and Ruslan Salakhutdinov and Deepak Pathak}, year = {2026}, eprint = {2611.03648}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03648}, } @misc{ramachandran2026klasktron, title = {{KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL}}, author = {Aswin Ramachandran and Jona Schulz and Maurus Derungs and Carlo Angelini and Tobias Meier and Raffaello D'Andrea}, year = {2026}, eprint = {2611.03138}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.03138}, } @misc{kawaharazuka2025mevita, title = {{MEVITA: Open-Source Bipedal Robot Assembled from E-Commerce Components via Sheet Metal Welding}}, author = {Kento Kawaharazuka and Shogo Sawaguchi and Ayumu Iwata and Keita Yoneda and Temma Suzuki and Kei Okada}, year = {2025}, eprint = {2508.17684}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2508.17684}, } @misc{xia2024duke, title = {{The Duke Humanoid: Design and Control For Energy Efficient Bipedal Locomotion Using Passive Dynamics}}, author = {Boxi Xia and Bokuan Li and Jacob Lee and Michael Scutari and Boyuan Chen}, year = {2024}, eprint = {2409.19795}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2409.19795}, } @misc{cheng2026mabel, title = {{MABEL: An Open Anthropomorphic Mobile Bimanual Platform for Teleoperation and Learning}}, author = {Qilong Cheng and Rooholla Khorrambakht and Mohamed Yassine Kabouri and Quang Nam Nguyen and Luca Macesanu and Haoran Zhou and Yipeng Wang and Ludovic Righetti}, year = {2026}, eprint = {2611.04083}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04083}, } @misc{kim2026raipal, title = {{RAIPAL: A Powerful and Agile Humanoid Arm for Human Tasks}}, author = {Donggeon Kim and Hyungho Chris Choi and Donghyuk Choi and Jeongsoo Park and Choongin Lee and Chan Park and Jemin Hwangbo}, year = {2026}, eprint = {2611.04334}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2611.04334}, } @misc{bohlinger2026shape, title = {{Shape Your Body: Value Gradients for Multi-Embodiment Robot Design}}, author = {Nico Bohlinger and Jan Peters}, year = {2026}, eprint = {2606.00702}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.00702}, } @misc{qin2026panovine, title = {{PanoVine: Whole-Body Visuomotor Control for Soft Growing Vine Robot}}, author = {Yimeng Qin and Xiaomeng Xu and William Heap and Aditi Oak and Shuran Song and Allison Okamura}, year = {2026}, eprint = {2606.22923}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.22923}, } @misc{ha2026transformer, title = {{Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design}}, author = {Huy Ha and C. Karen Liu and Shuran Song}, year = {2026}, eprint = {2607.25798}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2607.25798}, } @misc{liang2026universal, title = {{Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback}}, author = {Litian Liang and Jingxi Xu and Xinda Qi and Yujun Cai and Houzhu Ding and Luqi Wang and Zhixin Sun and Jyh-Herng Chow and Ming Yang and Mark Cutkosky}, year = {2026}, eprint = {2606.14218}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.14218}, } @misc{chen2026supersuit, title = {{SuperSuit: An Isomorphic Bimodal Interface for Scalable Mobile Manipulation}}, author = {Tongqing Chen and Hang Wu and Jiasen Wang and Xiaotao Li}, year = {2026}, eprint = {2603.06280}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2603.06280}, } @misc{fang2026spot, title = {{SPOT: Spatial Perception-Oriented Long-Horizon Humanoid Teleoperation}}, author = {Lixing Fang and Ziyan Xiong and Sunli Chen and Zhiyang Dou and Chuang Gan}, year = {2026}, eprint = {2609.07933}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.07933}, } @misc{yu2026seed, title = {{SEED-UMI: Sharing the Exoskeleton between human and robot for onE-to-one Dexterous demonstration}}, author = {Tengbo Yu and Jiahao Wu and Daohan Li and Bingxu Chen and Hao Liu and Xiaojian Ma and Hangxin Liu}, year = {2026}, eprint = {2609.11753}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2609.11753}, } @misc{xu2026realdexumi, title = {{RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning}}, author = {Chaoyi Xu and Yixuan Jiang and Jiahui Huan and Yuhui Fu and Haoyu Zhou and Weitian Yuan and Jiayi Yu and Wanpeng Zhang and Haoqi Yuan and Zongqing Lu}, year = {2026}, eprint = {2606.06033}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.06033}, } @misc{zhang2026yoco, title = {{YOCO: You Only Calibrate Once! Fast Mocap Calibration for Dexterous Teleoperation}}, author = {Yu Zhang and Yunqi Li and Yushi Du and Yi Ma and Yanchao Yang}, year = {2026}, eprint = {2610.11657}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.11657}, } @misc{zhang2026belt, title = {{Belt-Finger: An Affordable Soft Belt-Driven Gripper for Dexterous In-Hand Manipulation}}, author = {Boya Zhang and Andreas Zell and Georg Martius}, year = {2026}, eprint = {2606.20193}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2606.20193}, } @misc{ichiwara2026hardware, title = {{Hardware-as-Regularization: Enhancing Data Consistency in Imitation Learning via an Adjustable Passive Compliant Leader Arm}}, author = {Hideyuki Ichiwara and Yushi Kaida and Hirokazu Ishida}, year = {2026}, eprint = {2610.22977}, archivePrefix = {arXiv}, primaryClass = {cs.RO}, url = {https://arxiv.org/abs/2610.22977}, }