TY - RPRT TI - Scaling Behavior Foundation Model for Humanoid Robots AU - Zeng, Weishuai AU - Yin, Kangning AU - Niu, Xiaojie AU - Lu, Shunlin AU - Zhong, Weixiang AU - Chen, Jiahe AU - Jia, Feiyu AU - Chen, Xiao AU - Wang, Zirui AU - Xu, Furui AU - Zhou, Ming AU - Li, Kailin AU - Zhang, Weinan AU - Wang, He AU - Yi, Li AU - Lin, Dahua AU - Pang, Jiangmiao AU - Wang, Jingbo PY - 2026 UR - https://arxiv.org/abs/2607.15163 DO - 10.48550/arXiv.2607.15163 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/03_%E5%85%A8%E8%BA%AB%E8%BF%90%E5%8A%A8%E6%8E%A7%E5%88%B6%E5%9F%BA%E7%A1%80/2026__Scaling-BFM__Scaling-Behavior-Foundation-Model-for-Humanoid-Robots__arXiv-2607.15163v1.pdf KW - 全身控制基础 ER - TY - RPRT TI - Energy-Weighted Flow Matching for Offline Reinforcement Learning AU - Zhang, Shiyuan AU - Zhang, Weitong AU - Gu, Quanquan PY - 2025 UR - https://arxiv.org/abs/2503.04975 DO - 10.48550/arXiv.2503.04975 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2025__EFM-QIPO__Energy-Weighted-Flow-Matching-for-Offline-Reinforcement-Learning__arXiv-2503.04975v1.pdf KW - Offline RL / flow ER - TY - RPRT TI - $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization AU - Intelligence, Physical AU - Black, Kevin AU - Brown, Noah AU - Darpinian, James AU - Dhabalia, Karan AU - Driess, Danny AU - Esmail, Adnan AU - Equi, Michael AU - Finn, Chelsea AU - Fusai, Niccolo AU - Galliker, Manuel Y. AU - Ghosh, Dibya AU - Groom, Lachy AU - Hausman, Karol AU - Ichter, Brian AU - Jakubczak, Szymon AU - Jones, Tim AU - Ke, Liyiming AU - LeBlanc, Devin AU - Levine, Sergey AU - Li-Bell, Adrian AU - Mothukuri, Mohith AU - Nair, Suraj AU - Pertsch, Karl AU - Ren, Allen Z. AU - Shi, Lucy Xiaoyang AU - Smith, Laura AU - Springenberg, Jost Tobias AU - Stachowicz, Kyle AU - Tanner, James AU - Vuong, Quan AU - Walke, Homer AU - Walling, Anna AU - Wang, Haohuan AU - Yu, Lili AU - Zhilinsky, Ury PY - 2025 UR - https://arxiv.org/abs/2504.16054 DO - 10.48550/arXiv.2504.16054 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/05_VLA%E4%B8%8E%E7%94%9F%E6%88%90%E7%AD%96%E7%95%A5%E5%9F%BA%E7%A1%80/2025__pi-0.5__pi-0-5-a-Vision-Language-Action-Model-with-Open-World-Generalization__arXiv-2504.16054v1.pdf KW - 通用 VLA ER - TY - RPRT TI - Flow Matching Policy Gradients AU - McAllister, David AU - Ge, Songwei AU - Yi, Brent AU - Kim, Chung Min AU - Weber, Ethan AU - Choi, Hongsuk AU - Feng, Haiwen AU - Kanazawa, Angjoo PY - 2025 UR - https://arxiv.org/abs/2507.21053 DO - 10.48550/arXiv.2507.21053 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/03_Diffusion%E4%B8%8EFlow%E7%AD%96%E7%95%A5%E4%BC%98%E5%8C%96/2025__FPO__Flow-Matching-Policy-Gradients__arXiv-2507.21053v2.pdf KW - On-policy flow RL ER - TY - RPRT TI - RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning AU - Lei, Kun AU - Li, Huanyu AU - Yu, Dongjie AU - Wei, Zhenyu AU - Guo, Lingxiao AU - Jiang, Zhennan AU - Wang, Ziyu AU - Liang, Shiyu AU - Xu, Huazhe PY - 2025 UR - https://arxiv.org/abs/2510.14830 DO - 10.48550/arXiv.2510.14830 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/04_%E7%9C%9F%E6%9C%BA%E5%9C%A8%E7%BA%BF%E5%AD%A6%E4%B9%A0%E4%B8%8E%E5%B9%B2%E9%A2%84/2025__RL-100__Performant-Robotic-Manipulation-with-Real-World-Reinforcement-Learning__arXiv-2510.14830v4.pdf KW - 真机 RL / diffusion ER - TY - RPRT TI - $\pi^{*}_{0.6}$: a VLA That Learns From Experience AU - Intelligence, Physical AU - Amin, Ali AU - Aniceto, Raichelle AU - Balakrishna, Ashwin AU - Black, Kevin AU - Conley, Ken AU - Connors, Grace AU - Darpinian, James AU - Dhabalia, Karan AU - DiCarlo, Jared AU - Driess, Danny AU - Equi, Michael AU - Esmail, Adnan AU - Fang, Yunhao AU - Finn, Chelsea AU - Glossop, Catherine AU - Godden, Thomas AU - Goryachev, Ivan AU - Groom, Lachy AU - Hancock, Hunter AU - Hausman, Karol AU - Hussein, Gashon AU - Ichter, Brian AU - Jakubczak, Szymon AU - Jen, Rowan AU - Jones, Tim AU - Katz, Ben AU - Ke, Liyiming AU - Kuchi, Chandra AU - Lamb, Marinda AU - LeBlanc, Devin AU - Levine, Sergey AU - Li-Bell, Adrian AU - Lu, Yao AU - Mano, Vishnu AU - Mothukuri, Mohith AU - Nair, Suraj AU - Pertsch, Karl AU - Ren, Allen Z. AU - Sharma, Charvi AU - Shi, Lucy Xiaoyang AU - Smith, Laura AU - Springenberg, Jost Tobias AU - Stachowicz, Kyle AU - Stoeckle, Will AU - Swerdlow, Alex AU - Tanner, James AU - Torne, Marcel AU - Vuong, Quan AU - Walling, Anna AU - Wang, Haohuan AU - Williams, Blake AU - Yoo, Sukwon AU - Yu, Lili AU - Zhilinsky, Ury AU - Zhou, Zhiyuan PY - 2025 UR - https://arxiv.org/abs/2511.14759 DO - 10.48550/arXiv.2511.14759 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2025__pi-star-0.6-RECAP__pi-0-6-a-VLA-That-Learns-From-Experience__arXiv-2511.14759v2.pdf KW - VLA offline-to-online RL ER - TY - RPRT TI - BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models AU - Chen, Zhongxi AU - Han, Yifan AU - Shao, Yanming AU - Liu, Huanming AU - Xu, Congsheng AU - Chen, Xiaoyu AU - Mu, Yao AU - Lian, Wenzhao PY - 2026 UR - https://arxiv.org/abs/2605.30226 DO - 10.48550/arXiv.2605.30226 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__BORA__Bridging-Offline-Reinforcement-Learning-and-Online-Residual-Adaptation-for-Real-World-Dext__arXiv-2605.30226v2.pdf KW - 灵巧手 VLA offline-to-online RL ER - TY - RPRT TI - Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies AU - Wang, Ziqian AU - Zhang, Rui AU - Liu, Yitian AU - Mao, Xingjian AU - Wang, Minqian AU - Mu, Yao PY - 2026 UR - https://arxiv.org/abs/2606.08015 DO - 10.48550/arXiv.2606.08015 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__Q-VGM__Q-Guided-Value-Gradient-Matching-for-Offline-to-Online-RL-of-Flow-Matching-VLA-Policies__arXiv-2606.08015v5.pdf KW - Flow VLA offline-to-online RL ER - TY - RPRT TI - RL Token: Bootstrapping Online RL with Vision-Language-Action Models AU - Xu, Charles AU - Springenberg, Jost Tobias AU - Equi, Michael AU - Amin, Ali AU - Esmail, Adnan AU - Levine, Sergey AU - Ke, Liyiming PY - 2026 UR - https://arxiv.org/abs/2604.23073 DO - 10.48550/arXiv.2604.23073 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__RL-Token__Bootstrapping-Online-RL-with-Vision-Language-Action-Models__arXiv-2604.23073v2.pdf KW - 轻量真机在线 RL ER - TY - RPRT TI - RoboReward: General-Purpose Vision-Language Reward Models for Robotics AU - Lee, Tony AU - Wagenmaker, Andrew AU - Pertsch, Karl AU - Liang, Percy AU - Levine, Sergey AU - Finn, Chelsea PY - 2026 UR - https://arxiv.org/abs/2601.00675 DO - 10.48550/arXiv.2601.00675 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/05_%E5%A5%96%E5%8A%B1%E6%A8%A1%E5%9E%8B/2026__RoboReward__General-Purpose-Vision-Language-Reward-Models-for-Robotics__arXiv-2601.00675v2.pdf KW - 机器人奖励模型 ER - TY - RPRT TI - VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning AU - Lu, Guanxing AU - Guo, Wenkai AU - Zhang, Chubin AU - Zhou, Yuheng AU - Jiang, Haonan AU - Gao, Zifeng AU - Tang, Yansong AU - Wang, Ziwei PY - 2025 UR - https://arxiv.org/abs/2505.18719 DO - 10.48550/arXiv.2505.18719 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2025__VLA-RL__Towards-Masterful-and-General-Robotic-Manipulation-with-Scalable-Reinforcement-Learning__arXiv-2505.18719v1.pdf KW - VLA 在线 RL ER - TY - RPRT TI - Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data AU - Kim, Ji Woong AU - Wang, Ke AU - Fu, Zipeng AU - Chen, Sirui AU - Zhao, Cong AU - Lai, Jeff AU - Finn, Chelsea PY - 2026 UR - https://arxiv.org/abs/2606.08107 DO - 10.48550/arXiv.2606.08107 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/01_%E4%BA%BA%E7%B1%BB%E6%95%B0%E6%8D%AE%E4%B8%8E%E9%81%A5%E6%93%8D%E4%BD%9C/2026__Ego-Pi__VLA-Fine-Tuning-for-Ego-Centric-Human-and-Robot-Data__arXiv-2606.08107v1.pdf KW - 人类数据到 VLA ER - TY - RPRT TI - EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data AU - Zheng, Ruijie AU - Niu, Dantong AU - Xie, Yuqi AU - Wang, Jing AU - Xu, Mengda AU - Jiang, Yunfan AU - Castañeda, Fernando AU - Hu, Fengyuan AU - Tan, You Liang AU - Fu, Letian AU - Darrell, Trevor AU - Huang, Furong AU - Zhu, Yuke AU - Xu, Danfei AU - Fan, Linxi PY - 2026 UR - https://arxiv.org/abs/2602.16710 DO - 10.48550/arXiv.2602.16710 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/01_%E4%BA%BA%E7%B1%BB%E6%95%B0%E6%8D%AE%E4%B8%8E%E9%81%A5%E6%93%8D%E4%BD%9C/2026__EgoScale__Scaling-Dexterous-Manipulation-with-Diverse-Egocentric-Human-Data__arXiv-2602.16710v1.pdf KW - 灵巧手人类数据 ER - TY - RPRT TI - DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control AU - Wen, Junjie AU - Zhu, Yichen AU - Li, Jinming AU - Tang, Zhibin AU - Shen, Chaomin AU - Feng, Feifei PY - 2025 UR - https://arxiv.org/abs/2502.05855 DO - 10.48550/arXiv.2502.05855 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/05_VLA%E4%B8%8E%E7%94%9F%E6%88%90%E7%AD%96%E7%95%A5%E5%9F%BA%E7%A1%80/2025__DexVLA__Vision-Language-Model-with-Plug-In-Diffusion-Expert-for-General-Robot-Control__arXiv-2502.05855v3.pdf KW - VLA 架构基础 ER - TY - RPRT TI - End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection AU - Cui, Yu AU - Zhang, Yujian AU - Tao, Lina AU - Li, Yang AU - Yi, Xinyu AU - Li, Zhibin PY - 2025 UR - https://arxiv.org/abs/2511.00139 DO - 10.48550/arXiv.2511.00139 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2025__DexVLA-Seed-Shared-Autonomy__End-to-End-Dexterous-Arm-Hand-VLA-Policies-via-Shared-Autonomy-VR-Teleoperation-Augmented-by-Au__arXiv-2511.00139v2.pdf KW - Arm-hand VLA / 共享自主 ER - TY - RPRT TI - GR-Dexter Technical Report AU - Wen, Ruoshi AU - Chen, Guangzeng AU - Cui, Zhongren AU - Du, Min AU - Gou, Yang AU - Han, Zhigang AU - Huang, Liqun AU - Lei, Mingyu AU - Li, Yunfei AU - Li, Zhuohang AU - Liu, Wenlei AU - Liu, Yuxiao AU - Ma, Xiao AU - Niu, Hao AU - Ouyang, Yutao AU - Ren, Zeyu AU - Shi, Haixin AU - Xu, Wei AU - Zhang, Haoxiang AU - Zhang, Jiajun AU - Zhang, Xiao AU - Zheng, Liwei AU - Zhong, Weiheng AU - Zhou, Yifei AU - Zhu, Zhengming AU - Li, Hang PY - 2025 UR - https://arxiv.org/abs/2512.24210 DO - 10.48550/arXiv.2512.24210 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2025__GR-Dexter__Technical-Report__arXiv-2512.24210v2.pdf KW - 双臂双灵巧手 VLA ER - TY - RPRT TI - Causal World Modeling for Robot Control AU - Li, Lin AU - Zhang, Qihang AU - Luo, Yiming AU - Yang, Shuai AU - Wang, Ruilin AU - Han, Fei AU - Yu, Mingrui AU - Gao, Zelin AU - Xue, Nan AU - Zhu, Xing AU - Shen, Yujun AU - Xu, Yinghao PY - 2026 UR - https://arxiv.org/abs/2601.21998 DO - 10.48550/arXiv.2601.21998 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/06_%E4%B8%96%E7%95%8C%E5%8A%A8%E4%BD%9C%E6%A8%A1%E5%9E%8B/2026__LingBot-VA__Causal-World-Modeling-for-Robot-Control__arXiv-2601.21998v2.pdf KW - 世界动作模型 ER - TY - RPRT TI - World Action Models are Zero-shot Policies AU - Ye, Seonghyeon AU - Ge, Yunhao AU - Zheng, Kaiyuan AU - Gao, Shenyuan AU - Yu, Sihyun AU - Kurian, George AU - Indupuru, Suneel AU - Tan, You Liang AU - Zhu, Chuning AU - Xiang, Jiannan AU - Malik, Ayaan AU - Lee, Kyungmin AU - Liang, William AU - Ranawaka, Nadun AU - Gu, Jiasheng AU - Xu, Yinzhen AU - Wang, Guanzhi AU - Hu, Fengyuan AU - Narayan, Avnish AU - Bjorck, Johan AU - Wang, Jing AU - Kim, Gwanghyun AU - Niu, Dantong AU - Zheng, Ruijie AU - Xie, Yuqi AU - Wu, Jimmy AU - Wang, Qi AU - Julian, Ryan AU - Xu, Danfei AU - Du, Yilun AU - Chebotar, Yevgen AU - Reed, Scott AU - Kautz, Jan AU - Zhu, Yuke AU - Fan, Linxi "Jim" AU - Jang, Joel PY - 2026 UR - https://arxiv.org/abs/2602.15922 DO - 10.48550/arXiv.2602.15922 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/06_%E4%B8%96%E7%95%8C%E5%8A%A8%E4%BD%9C%E6%A8%A1%E5%9E%8B/2026__DreamZero__World-Action-Models-are-Zero-shot-Policies__arXiv-2602.15922v1.pdf KW - 世界动作模型 ER - TY - RPRT TI - SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse AU - Zhai, Xuanran AU - Huang, Zekai AU - Wu, Longyan AU - Zhao, Qianyou AU - Yu, Qiaojun AU - Ren, Jieji AU - Hao, Ce AU - Soh, Harold PY - 2026 UR - https://arxiv.org/abs/2603.03836 DO - 10.48550/arXiv.2603.03836 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2026__SkillVLA__Tackling-Combinatorial-Diversity-in-Dual-Arm-Manipulation-via-Skill-Reuse__arXiv-2603.03836v1.pdf KW - 双臂技能组合 VLA ER - TY - RPRT TI - Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA AU - Tang, Tutian AU - Ji, Xingyu AU - Xing, Wanli AU - Hao, Ce AU - Xu, Wenqiang AU - Shao, Lin AU - Lu, Cewu AU - Yu, Qiaojun AU - Pang, Jiangmiao AU - Zhang, Kaifeng PY - 2026 UR - https://arxiv.org/abs/2603.08122 DO - 10.48550/arXiv.2603.08122 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2026__MoDE-VLA-IMCopilot__Towards-Human-Like-Manipulation-through-RL-Augmented-Teleoperation-and-Mixture-of-Dexterous-Exp__arXiv-2603.08122v1.pdf KW - 触觉 VLA / RL 技能 ER - TY - RPRT TI - Motubrain: An Advanced World Action Model for Robot Control AU - Motubrain Team AU - Xiang, Chendong AU - Bao, Fan AU - Liu, Haitian AU - Tan, Hengkai AU - Bi, Hongzhe AU - Li, James AU - Liu, Jiabao AU - Pang, Jingrui AU - Jing, Kiro AU - Liu, Louis AU - Cai, Mengchen AU - Cui, Rongxu AU - Zhao, Ruowen AU - Wang, Runqing AU - Huang, Shuhe AU - Feng, Yao AU - Rong, Yinze AU - Wang, Zeyuan AU - Zhu, Jun PY - 2026 UR - https://arxiv.org/abs/2604.27792 DO - 10.48550/arXiv.2604.27792 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/06_%E4%B8%96%E7%95%8C%E5%8A%A8%E4%BD%9C%E6%A8%A1%E5%9E%8B/2026__MotuBrain__An-Advanced-World-Action-Model-for-Robot-Control__arXiv-2604.27792v5.pdf KW - 世界动作模型 ER - TY - RPRT TI - Dexora: Open-source VLA for High-DoF Bimanual Dexterity AU - Zhang, Zongzheng AU - Pang, Jingrui AU - Yang, Zhuo AU - Li, Kun AU - Liao, Minwen AU - Zhang, Saining AU - Chi, Guoxuan AU - Guo, Jinbang AU - Gao, Huan-ang AU - Shi, Modi AU - Ge, Dongyun AU - Mu, Yao AU - Gu, Jiayuan AU - Chen, Rui AU - Dong, Hao AU - Xu, Huazhe AU - Yi, Li AU - Zhu, Yixin AU - Zhao, Hang AU - Wang, Pengwei AU - Zhang, Shanghang AU - Yao, Guocai AU - Chen, Jianyu AU - Li, Hongyang AU - Zhao, Hao PY - 2026 UR - https://arxiv.org/abs/2605.18722 DO - 10.48550/arXiv.2605.18722 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2026__Dexora__Open-source-VLA-for-High-DoF-Bimanual-Dexterity__arXiv-2605.18722v1.pdf KW - 双臂双灵巧手 VLA ER - TY - RPRT TI - Steering Your Diffusion Policy with Latent Space Reinforcement Learning AU - Wagenmaker, Andrew AU - Nakamoto, Mitsuhiko AU - Zhang, Yunchu AU - Park, Seohong AU - Yagoub, Waleed AU - Nagabandi, Anusha AU - Gupta, Abhishek AU - Levine, Sergey PY - 2025 UR - https://arxiv.org/abs/2506.15799 DO - 10.48550/arXiv.2506.15799 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/03_Diffusion%E4%B8%8EFlow%E7%AD%96%E7%95%A5%E4%BC%98%E5%8C%96/2025__DSRL__Steering-Your-Diffusion-Policy-with-Latent-Space-Reinforcement-Learning__arXiv-2506.15799v2.pdf KW - 潜空间在线 RL ER - TY - RPRT TI - Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware AU - Zhao, Tony Z. AU - Kumar, Vikash AU - Levine, Sergey AU - Finn, Chelsea PY - 2023 UR - https://arxiv.org/abs/2304.13705 DO - 10.48550/arXiv.2304.13705 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/01_ACT%E4%B8%8E%E6%A8%A1%E4%BB%BF%E5%AD%A6%E4%B9%A0/2023__ACT-ALOHA__Learning-Fine-Grained-Bimanual-Manipulation-with-Low-Cost-Hardware__arXiv-2304.13705v1.pdf KW - ACT / 双臂模仿学习 ER - TY - RPRT TI - Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation AU - Fu, Zipeng AU - Zhao, Tony Z. AU - Finn, Chelsea PY - 2024 UR - https://arxiv.org/abs/2401.02117 DO - 10.48550/arXiv.2401.02117 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/01_ACT%E4%B8%8E%E6%A8%A1%E4%BB%BF%E5%AD%A6%E4%B9%A0/2024__Mobile-ALOHA__Learning-Bimanual-Mobile-Manipulation-with-Low-Cost-Whole-Body-Teleoperation__arXiv-2401.02117v1.pdf KW - 移动双臂 ACT ER - TY - RPRT TI - Diffusion Policy: Visuomotor Policy Learning via Action Diffusion AU - Chi, Cheng AU - Xu, Zhenjia AU - Feng, Siyuan AU - Cousineau, Eric AU - Du, Yilun AU - Burchfiel, Benjamin AU - Tedrake, Russ AU - Song, Shuran PY - 2023 UR - https://arxiv.org/abs/2303.04137 DO - 10.48550/arXiv.2303.04137 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/05_VLA%E4%B8%8E%E7%94%9F%E6%88%90%E7%AD%96%E7%95%A5%E5%9F%BA%E7%A1%80/2023__Diffusion-Policy__Visuomotor-Policy-Learning-via-Action-Diffusion__arXiv-2303.04137v5.pdf KW - 生成式模仿学习 ER - TY - RPRT TI - OpenVLA: An Open-Source Vision-Language-Action Model AU - Kim, Moo Jin AU - Pertsch, Karl AU - Karamcheti, Siddharth AU - Xiao, Ted AU - Balakrishna, Ashwin AU - Nair, Suraj AU - Rafailov, Rafael AU - Foster, Ethan AU - Lam, Grace AU - Sanketi, Pannag AU - Vuong, Quan AU - Kollar, Thomas AU - Burchfiel, Benjamin AU - Tedrake, Russ AU - Sadigh, Dorsa AU - Levine, Sergey AU - Liang, Percy AU - Finn, Chelsea PY - 2024 UR - https://arxiv.org/abs/2406.09246 DO - 10.48550/arXiv.2406.09246 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/05_VLA%E4%B8%8E%E7%94%9F%E6%88%90%E7%AD%96%E7%95%A5%E5%9F%BA%E7%A1%80/2024__OpenVLA__An-Open-Source-Vision-Language-Action-Model__arXiv-2406.09246v3.pdf KW - 通用 VLA ER - TY - RPRT TI - $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control AU - Black, Kevin AU - Brown, Noah AU - Driess, Danny AU - Esmail, Adnan AU - Equi, Michael AU - Finn, Chelsea AU - Fusai, Niccolo AU - Groom, Lachy AU - Hausman, Karol AU - Ichter, Brian AU - Jakubczak, Szymon AU - Jones, Tim AU - Ke, Liyiming AU - Levine, Sergey AU - Li-Bell, Adrian AU - Mothukuri, Mohith AU - Nair, Suraj AU - Pertsch, Karl AU - Shi, Lucy Xiaoyang AU - Tanner, James AU - Vuong, Quan AU - Walling, Anna AU - Wang, Haohuan AU - Zhilinsky, Ury PY - 2024 UR - https://arxiv.org/abs/2410.24164 DO - 10.48550/arXiv.2410.24164 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/05_VLA%E4%B8%8E%E7%94%9F%E6%88%90%E7%AD%96%E7%95%A5%E5%9F%BA%E7%A1%80/2024__pi-0__A-Vision-Language-Action-Flow-Model-for-General-Robot-Control__arXiv-2410.24164v4.pdf KW - Flow VLA ER - TY - RPRT TI - Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success AU - Kim, Moo Jin AU - Finn, Chelsea AU - Liang, Percy PY - 2025 UR - https://arxiv.org/abs/2502.19645 DO - 10.48550/arXiv.2502.19645 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/05_VLA%E4%B8%8E%E7%94%9F%E6%88%90%E7%AD%96%E7%95%A5%E5%9F%BA%E7%A1%80/2025__OpenVLA-OFT__Fine-Tuning-Vision-Language-Action-Models-Optimizing-Speed-and-Success__arXiv-2502.19645v2.pdf KW - VLA 高效微调 ER - TY - RPRT TI - DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation AU - Xu, Mengda AU - Zhang, Han AU - Hou, Yifan AU - Xu, Zhenjia AU - Fan, Linxi AU - Veloso, Manuela AU - Song, Shuran PY - 2025 UR - https://arxiv.org/abs/2505.21864 DO - 10.48550/arXiv.2505.21864 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/01_%E4%BA%BA%E7%B1%BB%E6%95%B0%E6%8D%AE%E4%B8%8E%E9%81%A5%E6%93%8D%E4%BD%9C/2025__DexUMI__Using-Human-Hand-as-the-Universal-Manipulation-Interface-for-Dexterous-Manipulation__arXiv-2505.21864v3.pdf KW - 灵巧手数据采集 ER - TY - RPRT TI - DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation AU - Wang, Chen AU - Shi, Haochen AU - Wang, Weizhuo AU - Zhang, Ruohan AU - Fei-Fei, Li AU - Liu, C. Karen PY - 2024 UR - https://arxiv.org/abs/2403.07788 DO - 10.48550/arXiv.2403.07788 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/01_%E4%BA%BA%E7%B1%BB%E6%95%B0%E6%8D%AE%E4%B8%8E%E9%81%A5%E6%93%8D%E4%BD%9C/2024__DexCap__Scalable-and-Portable-Mocap-Data-Collection-System-for-Dexterous-Manipulation__arXiv-2403.07788v2.pdf KW - 灵巧手动捕与模仿 ER - TY - RPRT TI - DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning AU - Jiang, Zhenyu AU - Xie, Yuqi AU - Lin, Kevin AU - Xu, Zhenjia AU - Wan, Weikang AU - Mandlekar, Ajay AU - Fan, Linxi AU - Zhu, Yuke PY - 2024 UR - https://arxiv.org/abs/2410.24185 DO - 10.48550/arXiv.2410.24185 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/02_%E4%BB%BF%E7%9C%9F%E6%95%B0%E6%8D%AE%E4%B8%8E%E5%9F%BA%E5%87%86/2024__DexMimicGen__Automated-Data-Generation-for-Bimanual-Dexterous-Manipulation-via-Imitation-Learnin__arXiv-2410.24185v2.pdf KW - 双臂灵巧仿真数据 ER - TY - RPRT TI - RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation AU - Chen, Tianxing AU - Chen, Zanxin AU - Chen, Baijun AU - Cai, Zijian AU - Liu, Yibin AU - Li, Zixuan AU - Liang, Qiwei AU - Lin, Xianliang AU - Ge, Yiheng AU - Gu, Zhenyu AU - Deng, Weiliang AU - Guo, Yubin AU - Nian, Tian AU - Xie, Xuanbing AU - Chen, Qiangyu AU - Su, Kailun AU - Xu, Tianling AU - Liu, Guodong AU - Hu, Mengkang AU - Gao, Huan-ang AU - Wang, Kaixuan AU - Liang, Zhixuan AU - Qin, Yusen AU - Yang, Xiaokang AU - Luo, Ping AU - Mu, Yao PY - 2025 UR - https://arxiv.org/abs/2506.18088 DO - 10.48550/arXiv.2506.18088 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/02_%E4%BB%BF%E7%9C%9F%E6%95%B0%E6%8D%AE%E4%B8%8E%E5%9F%BA%E5%87%86/2025__RoboTwin-2.0__RoboTwin-2-0-A-Scalable-Data-Generator-and-Benchmark-with-Strong-Domain-Randomization-for-Robus__arXiv-2506.18088v2.pdf KW - 双臂评测与数据 ER - TY - RPRT TI - Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots AU - Chi, Cheng AU - Xu, Zhenjia AU - Pan, Chuer AU - Cousineau, Eric AU - Burchfiel, Benjamin AU - Feng, Siyuan AU - Tedrake, Russ AU - Song, Shuran PY - 2024 UR - https://arxiv.org/abs/2402.10329 DO - 10.48550/arXiv.2402.10329 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/04_%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E8%AF%84%E6%B5%8B/01_%E4%BA%BA%E7%B1%BB%E6%95%B0%E6%8D%AE%E4%B8%8E%E9%81%A5%E6%93%8D%E4%BD%9C/2024__UMI__Universal-Manipulation-Interface-In-The-Wild-Robot-Teaching-Without-In-The-Wild-Robots__arXiv-2402.10329v3.pdf KW - 机器人无关采集接口 ER - TY - RPRT TI - DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination AU - Fu, Yankai AU - Chen, Ning AU - Zhao, Junkai AU - Zhang, Heng AU - Yao, Guocai AU - Wang, Pengwei AU - Wang, Zhongyuan AU - Zhang, Shanghang PY - 2026 UR - https://arxiv.org/abs/2609.09119 DO - 10.48550/arXiv.2609.09119 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2026__DeCAL__Towards-Physically-Grounded-Dexterous-Vision-Language-Action-Models-via-Contact-Aware-Lat__arXiv-2609.09119v1.pdf KW - 触觉双手 VLA ER - TY - RPRT TI - T-Rex: Tactile-Reactive Dexterous Manipulation AU - Niu, Dantong AU - Liu, Zhuoyang AU - Wang, Zekai AU - Shao, Boning AU - Yin, Zhao-Heng AU - Pai, Anirudh AU - Sharma, Yuvan AU - Saravalle, Stefano AU - Zheng, Ruijie AU - Wang, Jing AU - Punamiya, Ryan AU - Xu, Mengda AU - Xie, Yuqi AU - Jiang, Yunfan AU - Fu, Letian AU - Kallidromitis, Konstantinos AU - Gioia, Matteo AU - Zhang, Junyi AU - Ge, Jiaxin AU - Feng, Haiwen AU - Galasso, Fabio AU - Zhan, Wei AU - Chan, David M. AU - Bai, Yutong AU - Herzig, Roei AU - Lei, Jiahui AU - Fei-Fei, Li AU - Goldberg, Ken AU - Malik, Jitendra AU - Abbeel, Pieter AU - Zhu, Yuke AU - Xu, Danfei AU - Fan, Linxi AU - Darrell, Trevor PY - 2026 UR - https://arxiv.org/abs/2606.17055 DO - 10.48550/arXiv.2606.17055 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/01_%E5%8F%8C%E8%87%82%E4%B8%8E%E7%81%B5%E5%B7%A7%E6%89%8BVLA/2026__T-Rex__Tactile-Reactive-Dexterous-Manipulation__arXiv-2606.17055v2.pdf KW - 高频触觉 VLA ER - TY - RPRT TI - Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention AU - Li, Zhuohang AU - Huang, Liqun AU - Xu, Wei AU - Zhu, Zhengming AU - Lin, Nie AU - Ma, Xiao AU - Sheng, Xinjun AU - Wen, Ruoshi PY - 2026 UR - https://arxiv.org/abs/2605.15157 DO - 10.48550/arXiv.2605.15157 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/04_%E7%9C%9F%E6%9C%BA%E5%9C%A8%E7%BA%BF%E5%AD%A6%E4%B9%A0%E4%B8%8E%E5%B9%B2%E9%A2%84/2026__Hand-in-the-Loop__Improving-VLA-Policies-for-Dexterous-Manipulation-via-Seamless-Hand-Arm-Interv__arXiv-2605.15157v2.pdf KW - 交互式模仿学习 ER - TY - RPRT TI - Self-Adaptive VLA for Robust Robot Deployment AU - Zhang, Hongxin AU - Lin, Chunru AU - Wang, Tsun-Hsuan AU - Xu, Zhenjia AU - Gan, Chuang PY - 2026 UR - https://arxiv.org/abs/2609.30092 DO - 10.48550/arXiv.2609.30092 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__Self-Adaptive-VLA__for-Robust-Robot-Deployment__arXiv-2609.30092v1.pdf KW - 上下文适配后训练 ER - TY - RPRT TI - Offline Reinforcement Learning with Implicit Q-Learning AU - Kostrikov, Ilya AU - Nair, Ashvin AU - Levine, Sergey PY - 2021 UR - https://arxiv.org/abs/2110.06169 DO - 10.48550/arXiv.2110.06169 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2021__IQL__Offline-Reinforcement-Learning-with-Implicit-Q-Learning__arXiv-2110.06169v1.pdf KW - Offline RL 基础 ER - TY - RPRT TI - Efficient Online Reinforcement Learning with Offline Data AU - Ball, Philip J. AU - Smith, Laura AU - Kostrikov, Ilya AU - Levine, Sergey PY - 2023 UR - https://arxiv.org/abs/2302.02948 DO - 10.48550/arXiv.2302.02948 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2023__RLPD__Efficient-Online-Reinforcement-Learning-with-Offline-Data__arXiv-2302.02948v4.pdf KW - Offline data + Online RL ER - TY - RPRT TI - Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning AU - Nakamoto, Mitsuhiko AU - Zhai, Yuexiang AU - Singh, Anikait AU - Mark, Max Sobol AU - Ma, Yi AU - Finn, Chelsea AU - Kumar, Aviral AU - Levine, Sergey PY - 2023 UR - https://arxiv.org/abs/2303.05479 DO - 10.48550/arXiv.2303.05479 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2023__Cal-QL__Calibrated-Offline-RL-Pre-Training-for-Efficient-Online-Fine-Tuning__arXiv-2303.05479v4.pdf KW - Offline-to-online RL 基础 ER - TY - RPRT TI - Flow Q-Learning AU - Park, Seohong AU - Li, Qiyang AU - Levine, Sergey PY - 2025 UR - https://arxiv.org/abs/2502.02538 DO - 10.48550/arXiv.2502.02538 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2025__FQL__Flow-Q-Learning__arXiv-2502.02538v2.pdf KW - Offline flow RL ER - TY - RPRT TI - Diffusion Policy Policy Optimization AU - Ren, Allen Z. AU - Lidard, Justin AU - Ankile, Lars L. AU - Simeonov, Anthony AU - Agrawal, Pulkit AU - Majumdar, Anirudha AU - Burchfiel, Benjamin AU - Dai, Hongkai AU - Simchowitz, Max PY - 2024 UR - https://arxiv.org/abs/2409.00588 DO - 10.48550/arXiv.2409.00588 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/03_Diffusion%E4%B8%8EFlow%E7%AD%96%E7%95%A5%E4%BC%98%E5%8C%96/2024__DPPO__Diffusion-Policy-Policy-Optimization__arXiv-2409.00588v3.pdf KW - Diffusion 在线 RL ER - TY - RPRT TI - ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning AU - Zhang, Tonghe AU - Yu, Chao AU - Su, Sichang AU - Wang, Yu PY - 2025 UR - https://arxiv.org/abs/2505.22094 DO - 10.48550/arXiv.2505.22094 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/03_Diffusion%E4%B8%8EFlow%E7%AD%96%E7%95%A5%E4%BC%98%E5%8C%96/2025__ReinFlow__Fine-tuning-Flow-Matching-Policy-with-Online-Reinforcement-Learning__arXiv-2505.22094v7.pdf KW - Flow 在线 RL ER - TY - RPRT TI - Interactive Post-Training for Vision-Language-Action Models AU - Tan, Shuhan AU - Dou, Kairan AU - Zhao, Yue AU - Krähenbühl, Philipp PY - 2025 UR - https://arxiv.org/abs/2505.17016 DO - 10.48550/arXiv.2505.17016 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2025__RIPT-VLA__Interactive-Post-Training-for-Vision-Language-Action-Models__arXiv-2505.17016v1.pdf KW - VLA 在线后训练 ER - TY - RPRT TI - SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning AU - Li, Haozhan AU - Zuo, Yuxin AU - Yu, Jiale AU - Zhang, Yuhao AU - Yang, Zhaohui AU - Zhang, Kaiyan AU - Zhu, Xuekai AU - Zhang, Yuchen AU - Chen, Tianxing AU - Cui, Ganqu AU - Wang, Dehui AU - Luo, Dingxiang AU - Fan, Yuchen AU - Sun, Youbang AU - Zeng, Jia AU - Pang, Jiangmiao AU - Zhang, Shanghang AU - Wang, Yu AU - Mu, Yao AU - Zhou, Bowen AU - Ding, Ning PY - 2025 UR - https://arxiv.org/abs/2509.09674 DO - 10.48550/arXiv.2509.09674 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2025__SimpleVLA-RL__Scaling-VLA-Training-via-Reinforcement-Learning__arXiv-2509.09674v1.pdf KW - 规模化 VLA 在线 RL ER - TY - RPRT TI - CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning AU - Huang, Dongchi AU - Fang, Zhirui AU - Zhang, Tianle AU - Li, Yihang AU - Zhao, Lin AU - Xia, Chunhe PY - 2025 UR - https://arxiv.org/abs/2508.02219 DO - 10.48550/arXiv.2508.02219 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2025__CO-RFT__Efficient-Fine-Tuning-of-Vision-Language-Action-Models-through-Chunked-Offline-Reinforce__arXiv-2508.02219v1.pdf KW - 动作块 Offline VLA RL ER - TY - RPRT TI - Reinforcement Learning with Action Chunking AU - Li, Qiyang AU - Zhou, Zhiyuan AU - Levine, Sergey PY - 2025 UR - https://arxiv.org/abs/2507.07969 DO - 10.48550/arXiv.2507.07969 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2025__Q-Chunking__Reinforcement-Learning-with-Action-Chunking__arXiv-2507.07969v4.pdf KW - 动作块 Offline-to-online RL ER - TY - RPRT TI - Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning AU - Gireesh, Nandiraju AU - Ju, Yuanliang AU - Wang, He PY - 2026 UR - https://arxiv.org/abs/2605.05544 DO - 10.48550/arXiv.2605.05544 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/01_Offline%E4%B8%8EOffline-to-Online%E5%9F%BA%E7%A1%80/2026__Adaptive-Q-Chunking__for-Offline-to-Online-Reinforcement-Learning__arXiv-2605.05544v1.pdf KW - 自适应动作块 O2O RL ER - TY - RPRT TI - Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning AU - Luo, Jianlan AU - Xu, Charles AU - Wu, Jeffrey AU - Levine, Sergey PY - 2024 UR - https://arxiv.org/abs/2410.21845 DO - 10.48550/arXiv.2410.21845 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/04_%E7%9C%9F%E6%9C%BA%E5%9C%A8%E7%BA%BF%E5%AD%A6%E4%B9%A0%E4%B8%8E%E5%B9%B2%E9%A2%84/2024__HIL-SERL__Precise-and-Dexterous-Robotic-Manipulation-via-Human-in-the-Loop-Reinforcement-Learning__arXiv-2410.21845v3.pdf KW - 真机人机协同 RL ER - TY - RPRT TI - Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies AU - Wang, Yi AU - Li, Xinchen AU - Xie, Pengwei AU - Yang, Pu AU - Nie, Buqing AU - Cai, Yunuo AU - Zhang, Qinglin AU - Qu, Chendi AU - Wu, Jeffrey AU - Song, Jianheng AU - Ren, Xinlin AU - Huang, Jingshun AU - Pan, Mingjie AU - Feng, Siyuan AU - Chen, Zhi AU - Luo, Jianlan PY - 2026 UR - https://arxiv.org/abs/2605.00416 DO - 10.48550/arXiv.2605.00416 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__Learning-While-Deploying__Fleet-Scale-Reinforcement-Learning-for-Generalist-Robot-Policies__arXiv-2605.00416v4.pdf KW - 多机器人 VLA O2O RL ER - TY - RPRT TI - Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models AU - Poyarkov, Dmitriy AU - Staroverov, Aleksei AU - Panov, Aleksandr I. PY - 2026 UR - https://arxiv.org/abs/2607.19399 DO - 10.48550/arXiv.2607.19399 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__Offline-Supervision-VLA-RL__Leveraging-Offline-Supervision-for-Efficient-and-Generalizable-Reinforcement-Learning-in-Large__arXiv-2607.19399v1.pdf KW - 离线监督正则化 RL ER - TY - RPRT TI - Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy AU - Yardımcı, Mehmet Turan AU - Çoğurcu, Yunus Emre PY - 2026 UR - https://arxiv.org/abs/2609.28838 DO - 10.48550/arXiv.2609.28838 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/02_VLA%E5%90%8E%E8%AE%AD%E7%BB%83/2026__Uncertainty-Gated-Exploration__Noise-Suppresses-Task-Collapse-in-Online-RL-Fine-Tuning-of-a-Flow__arXiv-2609.28838v1.pdf KW - 在线 RL 失败模式 ER - TY - RPRT TI - SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control AU - Wang, Yuxuan AU - Jiang, Haobin AU - Yao, Shiqing AU - Ding, Ziluo AU - Lu, Zongqing PY - 2025 UR - https://arxiv.org/abs/2511.19236 DO - 10.48550/arXiv.2511.19236 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/02_%E4%BB%BB%E5%8A%A1%E8%AF%AD%E8%A8%80%E5%88%B0%E5%8A%A8%E4%BD%9C%E6%8E%A5%E5%8F%A3/2025__SENTINEL__A-Fully-End-to-End-Language-Action-Model-for-Humanoid-Whole-Body-Control__arXiv-2511.19236v1.pdf KW - 语言到关节目标 ER - TY - RPRT TI - WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control AU - Jiang, Haoran AU - Chen, Jin AU - Bu, Qingwen AU - Chen, Li AU - Shi, Modi AU - Zhang, Yanjie AU - Li, Delong AU - Suo, Chuanzhe AU - Wang, Chuang AU - Peng, Zhihui AU - Li, Hongyang PY - 2025 UR - https://arxiv.org/abs/2512.11047 DO - 10.48550/arXiv.2512.11047 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/02_%E4%BB%BB%E5%8A%A1%E8%AF%AD%E8%A8%80%E5%88%B0%E5%8A%A8%E4%BD%9C%E6%8E%A5%E5%8F%A3/2025__WholeBodyVLA__Towards-Unified-Latent-VLA-for-Whole-Body-Loco-Manipulation-Control__arXiv-2512.11047v2.pdf KW - 分层全身 VLA ER - TY - RPRT TI - HumanPlus: Humanoid Shadowing and Imitation from Humans AU - Fu, Zipeng AU - Zhao, Qingqing AU - Wu, Qi AU - Wetzstein, Gordon AU - Finn, Chelsea PY - 2024 UR - https://arxiv.org/abs/2406.10454 DO - 10.48550/arXiv.2406.10454 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/01_ACT%E4%B8%8E%E6%A8%A1%E4%BB%BF%E5%AD%A6%E4%B9%A0/2024__HumanPlus__Humanoid-Shadowing-and-Imitation-from-Humans__arXiv-2406.10454v1.pdf KW - ACT 衍生人形 IL ER - TY - RPRT TI - OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning AU - He, Tairan AU - Luo, Zhengyi AU - He, Xialin AU - Xiao, Wenli AU - Zhang, Chong AU - Zhang, Weinan AU - Kitani, Kris AU - Liu, Changliu AU - Shi, Guanya PY - 2024 UR - https://arxiv.org/abs/2406.08858 DO - 10.48550/arXiv.2406.08858 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/03_%E5%85%A8%E8%BA%AB%E8%BF%90%E5%8A%A8%E6%8E%A7%E5%88%B6%E5%9F%BA%E7%A1%80/2024__OmniH2O__Universal-and-Dexterous-Human-to-Humanoid-Whole-Body-Teleoperation-and-Learning__arXiv-2406.08858v1.pdf KW - 全身遥操作与学习 ER - TY - RPRT TI - TWIST: Teleoperated Whole-Body Imitation System AU - Ze, Yanjie AU - Chen, Zixuan AU - Araújo, João Pedro AU - Cao, Zi-ang AU - Peng, Xue Bin AU - Wu, Jiajun AU - Liu, C. Karen PY - 2025 UR - https://arxiv.org/abs/2505.02833 DO - 10.48550/arXiv.2505.02833 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/03_%E5%85%A8%E8%BA%AB%E8%BF%90%E5%8A%A8%E6%8E%A7%E5%88%B6%E5%9F%BA%E7%A1%80/2025__TWIST__Teleoperated-Whole-Body-Imitation-System__arXiv-2505.02833v1.pdf KW - 全身控制与遥操作 ER - TY - RPRT TI - TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System AU - Ze, Yanjie AU - Zhao, Siheng AU - Wang, Weizhuo AU - Kanazawa, Angjoo AU - Duan, Rocky AU - Abbeel, Pieter AU - Shi, Guanya AU - Wu, Jiajun AU - Liu, C. Karen PY - 2025 UR - https://arxiv.org/abs/2511.02832 DO - 10.48550/arXiv.2511.02832 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/03_%E5%85%A8%E8%BA%AB%E8%BF%90%E5%8A%A8%E6%8E%A7%E5%88%B6%E5%9F%BA%E7%A1%80/2025__TWIST2__Scalable-Portable-and-Holistic-Humanoid-Data-Collection-System__arXiv-2511.02832v1.pdf KW - 人形数据采集系统 ER - TY - RPRT TI - GR00T N1: An Open Foundation Model for Generalist Humanoid Robots AU - NVIDIA AU - : AU - Bjorck, Johan AU - Castañeda, Fernando AU - Cherniadev, Nikita AU - Da, Xingye AU - Ding, Runyu AU - Fan, Linxi "Jim" AU - Fang, Yu AU - Fox, Dieter AU - Hu, Fengyuan AU - Huang, Spencer AU - Jang, Joel AU - Jiang, Zhenyu AU - Kautz, Jan AU - Kundalia, Kaushil AU - Lao, Lawrence AU - Li, Zhiqi AU - Lin, Zongyu AU - Lin, Kevin AU - Liu, Guilin AU - Llontop, Edith AU - Magne, Loic AU - Mandlekar, Ajay AU - Narayan, Avnish AU - Nasiriany, Soroush AU - Reed, Scott AU - Tan, You Liang AU - Wang, Guanzhi AU - Wang, Zu AU - Wang, Jing AU - Wang, Qi AU - Xiang, Jiannan AU - Xie, Yuqi AU - Xu, Yinzhen AU - Xu, Zhenjia AU - Ye, Seonghyeon AU - Yu, Zhiding AU - Zhang, Ao AU - Zhang, Hao AU - Zhao, Yizhou AU - Zheng, Ruijie AU - Zhu, Yuke PY - 2025 UR - https://arxiv.org/abs/2503.14734 DO - 10.48550/arXiv.2503.14734 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/02_%E4%BB%BB%E5%8A%A1%E8%AF%AD%E8%A8%80%E5%88%B0%E5%8A%A8%E4%BD%9C%E6%8E%A5%E5%8F%A3/2025__GR00T-N1__An-Open-Foundation-Model-for-Generalist-Humanoid-Robots__arXiv-2503.14734v2.pdf KW - 人形 VLA 基础 ER - TY - RPRT TI - TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model AU - Li, Anqi AU - Chen, Yuxin AU - Li, Zhaobo AU - Cao, Zhuo AU - Ren, Junli AU - Tomizuka, Masayoshi AU - Shah, Dhruv PY - 2026 UR - https://arxiv.org/abs/2609.09158 DO - 10.48550/arXiv.2609.09158 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/02_%E4%BB%BB%E5%8A%A1%E8%AF%AD%E8%A8%80%E5%88%B0%E5%8A%A8%E4%BD%9C%E6%8E%A5%E5%8F%A3/2026__TANGO__Humanoid-Navigation-in-Cluttered-Environments-with-a-Whole-Body-Vision-Language-Action-Mo__arXiv-2609.09158v1.pdf KW - 语言视觉全身导航 ER - TY - RPRT TI - TACT: Humanoid Whole-body Contact Manipulation through Deep Imitation Learning with Tactile Modality AU - Murooka, Masaki AU - Hoshi, Takahiro AU - Fukumitsu, Kensuke AU - Masuda, Shimpei AU - Hamze, Marwan AU - Sasaki, Tomoya AU - Morisawa, Mitsuharu AU - Yoshida, Eiichi PY - 2025 UR - https://arxiv.org/abs/2506.15146 DO - 10.48550/arXiv.2506.15146 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/01_ACT%E4%B8%8E%E6%A8%A1%E4%BB%BF%E5%AD%A6%E4%B9%A0/2025__TACT__Humanoid-Whole-body-Contact-Manipulation-through-Deep-Imitation-Learning-with-Tactile-Moda__arXiv-2506.15146v1.pdf KW - 触觉 ACT / 人形接触操作 ER - TY - RPRT TI - FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences AU - Rayyan, Omar AU - Li, Zhi AU - Argus, Max AU - Jiang, Yuxin AU - Yu, Chang AU - Jiang, Chenfanfu AU - Cui, Yuchen PY - 2026 UR - https://arxiv.org/abs/2608.17027 DO - 10.48550/arXiv.2608.17027 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/02_%E4%BB%BB%E5%8A%A1%E8%AF%AD%E8%A8%80%E5%88%B0%E5%8A%A8%E4%BD%9C%E6%8E%A5%E5%8F%A3/2026__FetchMan__Learning-Visual-Humanoid-Loco-Manipulation-Policies-from-Simulated-Experiences__arXiv-2608.17027v2.pdf KW - 人形视觉策略 + RL ER - TY - RPRT TI - Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation AU - Liu, Fukang AU - Chen, Yipu AU - Jang, Jaehwi AU - Xu, Danfei AU - Kira, Zsolt AU - Zhao, Ye PY - 2026 UR - https://arxiv.org/abs/2609.23968 DO - 10.48550/arXiv.2609.23968 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/03_%E4%BA%BA%E5%BD%A2%E6%9C%BA%E5%99%A8%E4%BA%BA%E4%B8%8EACT/02_%E4%BB%BB%E5%8A%A1%E8%AF%AD%E8%A8%80%E5%88%B0%E5%8A%A8%E4%BD%9C%E6%8E%A5%E5%8F%A3/2026__Opt2VLA__Force-Aware-Vision-Language-Action-for-Contact-Rich-Humanoid-Whole-Body-Manipulation__arXiv-2609.23968v1.pdf KW - 力感知分层人形 VLA ER - TY - RPRT TI - Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning AU - Zhou, Zhiyuan AU - Peng, Andy AU - Xu, Charles AU - Li, Qiyang AU - Springenberg, Tobias AU - Frans, Kevin AU - Levine, Sergey PY - 2026 UR - https://arxiv.org/abs/2606.11087 DO - 10.48550/arXiv.2606.11087 L1 - file:///Users/simplemaxq/Desktop/MaRs%20Lab/%E8%AE%BA%E6%96%87%E5%BA%93/02_RL%E5%90%8E%E8%AE%AD%E7%BB%83/03_Diffusion%E4%B8%8EFlow%E7%AD%96%E7%95%A5%E4%BC%98%E5%8C%96/2026__QGF__Test-Time-Gradient-Guidance-of-Flow-Policies-in-Reinforcement-Learning__arXiv-2606.11087v1.pdf KW - Offline RL / Flow 推理时引导 ER -