% Embodied AI Radar: agent picks added on 2026-11-10 (14 entries). https://embodied-ai-radar.com/

@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},
  keywords = {VLA \& Robot Foundation Models, Embodied AI Radar},
  note = {SPARK-VLA distils a frozen 3D expert into a LoRA visual branch beside the original one, and a small router passes only action-relevant tokens to a 0.5B LLM. No 3D input at inference; ~53M trainable parameters. — SPARK-VLA 把冻结的 3D 专家蒸馏到与原视觉通路并行的 LoRA 分支，并用轻量路由器只把与动作相关的视觉 token 送入 0.5B 语言模型。推理时无需 3D 输入，可训练参数约 5300 万。},
}

@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},
  keywords = {Manipulation \& Dexterous Hands, Robot Learning: RL \& Imitation, Embodied AI Radar},
  note = {One shared object-pose reward, varied training scenes: RL experts discover regrasping, in-hand adjustment and handover on their own, then distil into one policy. Reports 61 of 80 real trials with unseen objects. — 只用统一的物体位姿奖励并变换训练环境，强化学习专家自行学会重抓、手内调整与双手交接，再蒸馏成单一策略。报告在未见物体上真实实验 80 次成功 61 次。},
}

@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},
  keywords = {Manipulation \& Dexterous Hands, World Models, Embodied AI Radar},
  note = {Trains a world model of 3D hand-point and scene motion, then aligns policy latents to it; at test time only the RGB policy runs, with no depth or future frames. Reports 49.4\% → 60.5\% on 11 DexJoCo tasks. — 先训练预测 3D 手部点与场景变化的世界模型，再把策略潜表示对齐到它；部署时只保留 RGB 策略，无需深度或未来预测。在 11 个 DexJoCo 任务上成功率从 49.4\% 提升到 60.5\%。},
}

@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},
  keywords = {World Models, Datasets \& Benchmarks, Manipulation \& Dexterous Hands, Embodied AI Radar},
  note = {Represents object motion as dense 3D trajectories over the whole surface, occluded parts included, for rigid and deformable objects. Adds a 1,210-hour flow dataset and a world model predicting it from image + task. — 把物体运动表示为覆盖整个表面（含遮挡部分）的稠密 3D 轨迹，适用于刚体与可形变物体。发布 1210 小时的全物体流数据集，并训练从图像和任务描述预测该流的世界模型。},
}

@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},
  keywords = {Navigation \& Embodied Agents, Embodied AI Radar},
  note = {Wraps VLM action scores for object-goal search in a conformal prediction layer with a user-set risk level, plus collision-free primitives and backtracking. Reports gains on HM3D/MP3D and on a small real robot. — 为目标物体搜索中的 VLM 动作打分加上共形预测校准层（风险水平可设定），结合无碰撞运动基元与回溯探索。在 HM3D/MP3D 及小型真实机器人上报告提升。 — Code: https://github.com/practice-lab-ucla/CPnav},
}

@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},
  keywords = {Navigation \& Embodied Agents, Embodied AI Radar},
  note = {Outdoor long-range navigation where a VLM first reasons on context and only pulls in geometry and motion cues when an interaction stays unclear. Reports real-world success up from 61.8\% to 94.2\% over MOSU. — 户外长距离导航：VLM 先基于场景上下文推理，只有交互情形仍不明确时才调取几何与运动信息。真实实验中导航成功率相对前作 MOSU 从 61.8\% 提升到 94.2\%。},
}

@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},
  keywords = {Planning / Control \& Safety, Embodied AI Radar},
  note = {Shows predictive sampling, MPPI, CEM and their variants are one SMC algorithm set by proposal, update rule and resampling threshold. Resampling cuts long-horizon collisions by 30\%; programmable proposals lift push-T. — 指出预测采样、MPPI、CEM 及其变体都是同一个序贯蒙特卡洛算法，只是提议分布、更新规则与重采样阈值不同。重采样使长时域碰撞率降低 30\%，可编程提议显著提升 push-T 成功率。 — Code: https://github.com/CoMMALab/PFMP},
}

@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},
  keywords = {Robot Learning: RL \& Imitation, VLA \& Robot Foundation Models, Embodied AI Radar},
  note = {Challenge report: a π0.5 policy that is its own critic, trained off-policy on the exact score; Thompson sampling tunes ~20 inference settings; adds generated and recovery demos. Reports 0.987 RDS. — 比赛技术报告：基于 π0.5 的策略同时充当价值函数，直接以官方评分做离策略 RL，每次 rollout 用 Thompson 采样调约 20 个推理参数，并加入生成示范与失败恢复数据。官方种子上报告 0.987 RDS。 — Code: https://github.com/IliaLarchenko/RoboEvalSolution},
}

@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},
  keywords = {Robot Learning: RL \& Imitation, Embodied AI Radar},
  note = {Diffusion policies trained on sliding-window demos often memorise one action per state; querying the demonstrator k times at one state (vine sampling) keeps the multimodality and aids best-of-N and expert iteration. — 用滑窗示范训练的扩散策略往往每个状态只记住一个动作。在同一状态下向示范者查询 k 次（vine 采样）可保留其多模态分布，并提升 best-of-N 与专家迭代效果。},
}

@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},
  keywords = {Robot Learning: RL \& Imitation, Embodied AI Radar},
  note = {Post-trains a vision foundation model for robot control: a temporal-abstraction loss keeps action-relevant change, patch alignment to the original keeps semantics. Gains on several benchmarks and a real arm. — 不从头预训练，而是对现成视觉基础模型做面向机器人控制的后训练：时间抽象目标保留与动作相关的变化，与原模型的 patch 级对齐保留其语义。在多个基准和真实机械臂上提升成功率与泛化。},
}

@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},
  keywords = {Robot Learning: RL \& Imitation, Embodied AI Radar},
  note = {Reuses demos across arms by aligning a source encoder to a frozen target encoder on sim-rendered paired views, no pixel translation. Up to 93\% zero-shot in sim; real xArm→Franka 27/30 with 10 demos per task. — 用仿真渲染的成对视角，把源机器人的视觉编码器对齐到冻结的目标编码器，无需像素级图像翻译即可跨机械臂复用示范。仿真零样本成功率最高 93\%；真实 xArm→Franka 每任务仅用 10 条目标示范微调即 27/30 成功。},
}

@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},
  keywords = {Datasets \& Benchmarks, Manipulation \& Dexterous Hands, Embodied AI Radar},
  note = {Manipulation benchmark where simulated humans cue goals, finish parts of the task, interrupt or share the workspace. Reports that VLA and IL policies drop when humans act, and higher success does not mean safer motion. — 让仿真人类参与其中的操作基准：人会提示目标、完成部分任务、打断或与机器人共处同一工作区。报告显示 VLA 与模仿学习策略在有人活动时性能下降，且成功率更高并不意味着更安全。 — Code: https://github.com/UMass-Embodied-AGI/harp},
}

@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},
  keywords = {Datasets \& Benchmarks, Locomotion \& Humanoids, Embodied AI Radar},
  note = {200+ hours from 14 people: six head cameras, wrist vision and IMU, plus 120 Hz optical full-body mocap, covering walking, terrain and carrying. Benchmarks body reconstruction, foot contact and humanoid retargeting. — 14 名参与者、200 多小时数据：六个头戴相机、腕部视觉与惯性传感，加 120 Hz 光学全身动捕，覆盖行走、地形穿越与搬运等。提供全身重建、足部接触估计与人形重定向三项基准。},
}

@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},
  keywords = {Datasets \& Benchmarks, Manipulation \& Dexterous Hands, Embodied AI Radar},
  note = {'Stochastic challenges': reproducible real scenes with tasks sampled from a shared distribution, so robots in different labs compare by success rate like a hidden test set. Shown with two robots in two labs. — 提出“随机挑战”评测范式：可复现的真实场景 + 从同一分布随机抽取任务，让不同实验室的机器人能像隐藏测试集一样按成功率比较。在一个移动操作基准上用两个实验室的两台机器人做了演示。},
}