Shanghai AI Lab (InternRobotics) · embodied AI & robot learning上海人工智能实验室（InternRobotics） · 具身智能与机器人学习

@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{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{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{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{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{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{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{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{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{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{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{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{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},
}