4 embodied-AI and robotics papers accepted at NeurIPS 2025, 3 with code.4 篇被 NeurIPS 2025 接收的具身智能与机器人论文，其中 3 篇附代码。
arXiv papers are listed when their arXiv comment says they were accepted (e.g. 'Accepted to CoRL 2026'); papers that do not say so are missing, and the list grows as authors post camera-ready versions. Curated entries carry a hand-checked venue. For CoRL 2026 the official program is used as well.arXiv 论文仅在其 arXiv 备注写明已被接收（如 “Accepted to CoRL 2026”）时列入；未注明的论文不会出现，列表会随作者上传终稿而增加。精选条目的会议/期刊信息经过人工核对。CoRL 2026 另依据官方日程。
Learns highly dynamic skills such as kung fu and dancing, through multi-step motion processing and adaptive motion tracking.通过多步动作处理和自适应动作跟踪，学习功夫、舞蹈等高动态技能。
@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{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},
}
GPU tactile simulation combining IPC and ABD; the authors report running 18 times faster than real time across thousands of parallel environments.结合 IPC 与 ABD 的 GPU 触觉仿真；作者报告在数千并行环境下达到实时速度的 18 倍。
@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},
}
Empirical study of whether RL fine-tuning generalises better than supervised fine-tuning, which suffers compounding errors under distribution shift.实证研究强化学习微调是否比监督微调泛化更好；后者在分布偏移下易累积误差。
@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},
}