@misc{ScalingBFM2026,
  title={Scaling Behavior Foundation Model for Humanoid Robots},
  author={Zeng, Weishuai and Yin, Kangning and Niu, Xiaojie and Lu, Shunlin and Zhong, Weixiang and Chen, Jiahe and Jia, Feiyu and Chen, Xiao and Wang, Zirui and Xu, Furui and Zhou, Ming and Li, Kailin and Zhang, Weinan and Wang, He and Yi, Li and Lin, Dahua and Pang, Jiangmiao and Wang, Jingbo},
  year={2026},
  eprint={2607.15163},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2607.15163},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/03_全身运动控制基础/2026__Scaling-BFM__Scaling-Behavior-Foundation-Model-for-Humanoid-Robots__arXiv-2607.15163v1.pdf:application/pdf}
}

@misc{EFMQIPO2025,
  title={Energy-Weighted Flow Matching for Offline Reinforcement Learning},
  author={Zhang, Shiyuan and Zhang, Weitong and Gu, Quanquan},
  year={2025},
  eprint={2503.04975},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2503.04975},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2025__EFM-QIPO__Energy-Weighted-Flow-Matching-for-Offline-Reinforcement-Learning__arXiv-2503.04975v1.pdf:application/pdf}
}

@misc{pi052025,
  title={$\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization},
  author={Intelligence, Physical and Black, Kevin and Brown, Noah and Darpinian, James and Dhabalia, Karan and Driess, Danny and Esmail, Adnan and Equi, Michael and Finn, Chelsea and Fusai, Niccolo and Galliker, Manuel Y. and Ghosh, Dibya and Groom, Lachy and Hausman, Karol and Ichter, Brian and Jakubczak, Szymon and Jones, Tim and Ke, Liyiming and LeBlanc, Devin and Levine, Sergey and Li-Bell, Adrian and Mothukuri, Mohith and Nair, Suraj and Pertsch, Karl and Ren, Allen Z. and Shi, Lucy Xiaoyang and Smith, Laura and Springenberg, Jost Tobias and Stachowicz, Kyle and Tanner, James and Vuong, Quan and Walke, Homer and Walling, Anna and Wang, Haohuan and Yu, Lili and Zhilinsky, Ury},
  year={2025},
  eprint={2504.16054},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2504.16054},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/05_VLA与生成策略基础/2025__pi-0.5__pi-0-5-a-Vision-Language-Action-Model-with-Open-World-Generalization__arXiv-2504.16054v1.pdf:application/pdf}
}

@misc{FPO2025,
  title={Flow Matching Policy Gradients},
  author={McAllister, David and Ge, Songwei and Yi, Brent and Kim, Chung Min and Weber, Ethan and Choi, Hongsuk and Feng, Haiwen and Kanazawa, Angjoo},
  year={2025},
  eprint={2507.21053},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2507.21053},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/03_Diffusion与Flow策略优化/2025__FPO__Flow-Matching-Policy-Gradients__arXiv-2507.21053v2.pdf:application/pdf}
}

@misc{RL1002025,
  title={RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning},
  author={Lei, Kun and Li, Huanyu and Yu, Dongjie and Wei, Zhenyu and Guo, Lingxiao and Jiang, Zhennan and Wang, Ziyu and Liang, Shiyu and Xu, Huazhe},
  year={2025},
  eprint={2510.14830},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2510.14830},
  note={Local PDF v4; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/04_真机在线学习与干预/2025__RL-100__Performant-Robotic-Manipulation-with-Real-World-Reinforcement-Learning__arXiv-2510.14830v4.pdf:application/pdf}
}

@misc{pistar06RECAP2025,
  title={$\pi^{*}_{0.6}$: a VLA That Learns From Experience},
  author={Intelligence, Physical and Amin, Ali and Aniceto, Raichelle and Balakrishna, Ashwin and Black, Kevin and Conley, Ken and Connors, Grace and Darpinian, James and Dhabalia, Karan and DiCarlo, Jared and Driess, Danny and Equi, Michael and Esmail, Adnan and Fang, Yunhao and Finn, Chelsea and Glossop, Catherine and Godden, Thomas and Goryachev, Ivan and Groom, Lachy and Hancock, Hunter and Hausman, Karol and Hussein, Gashon and Ichter, Brian and Jakubczak, Szymon and Jen, Rowan and Jones, Tim and Katz, Ben and Ke, Liyiming and Kuchi, Chandra and Lamb, Marinda and LeBlanc, Devin and Levine, Sergey and Li-Bell, Adrian and Lu, Yao and Mano, Vishnu and Mothukuri, Mohith and Nair, Suraj and Pertsch, Karl and Ren, Allen Z. and Sharma, Charvi and Shi, Lucy Xiaoyang and Smith, Laura and Springenberg, Jost Tobias and Stachowicz, Kyle and Stoeckle, Will and Swerdlow, Alex and Tanner, James and Torne, Marcel and Vuong, Quan and Walling, Anna and Wang, Haohuan and Williams, Blake and Yoo, Sukwon and Yu, Lili and Zhilinsky, Ury and Zhou, Zhiyuan},
  year={2025},
  eprint={2511.14759},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2511.14759},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2025__pi-star-0.6-RECAP__pi-0-6-a-VLA-That-Learns-From-Experience__arXiv-2511.14759v2.pdf:application/pdf}
}

@misc{BORA2026,
  title={BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models},
  author={Chen, Zhongxi and Han, Yifan and Shao, Yanming and Liu, Huanming and Xu, Congsheng and Chen, Xiaoyu and Mu, Yao and Lian, Wenzhao},
  year={2026},
  eprint={2605.30226},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.30226},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__BORA__Bridging-Offline-Reinforcement-Learning-and-Online-Residual-Adaptation-for-Real-World-Dext__arXiv-2605.30226v2.pdf:application/pdf}
}

@misc{QVGM2026,
  title={Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies},
  author={Wang, Ziqian and Zhang, Rui and Liu, Yitian and Mao, Xingjian and Wang, Minqian and Mu, Yao},
  year={2026},
  eprint={2606.08015},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.08015},
  note={Local PDF v5; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__Q-VGM__Q-Guided-Value-Gradient-Matching-for-Offline-to-Online-RL-of-Flow-Matching-VLA-Policies__arXiv-2606.08015v5.pdf:application/pdf}
}

@misc{RLToken2026,
  title={RL Token: Bootstrapping Online RL with Vision-Language-Action Models},
  author={Xu, Charles and Springenberg, Jost Tobias and Equi, Michael and Amin, Ali and Esmail, Adnan and Levine, Sergey and Ke, Liyiming},
  year={2026},
  eprint={2604.23073},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2604.23073},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__RL-Token__Bootstrapping-Online-RL-with-Vision-Language-Action-Models__arXiv-2604.23073v2.pdf:application/pdf}
}

@misc{RoboReward2026,
  title={RoboReward: General-Purpose Vision-Language Reward Models for Robotics},
  author={Lee, Tony and Wagenmaker, Andrew and Pertsch, Karl and Liang, Percy and Levine, Sergey and Finn, Chelsea},
  year={2026},
  eprint={2601.00675},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2601.00675},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/05_奖励模型/2026__RoboReward__General-Purpose-Vision-Language-Reward-Models-for-Robotics__arXiv-2601.00675v2.pdf:application/pdf}
}

@misc{VLARL2025,
  title={VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning},
  author={Lu, Guanxing and Guo, Wenkai and Zhang, Chubin and Zhou, Yuheng and Jiang, Haonan and Gao, Zifeng and Tang, Yansong and Wang, Ziwei},
  year={2025},
  eprint={2505.18719},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2505.18719},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2025__VLA-RL__Towards-Masterful-and-General-Robotic-Manipulation-with-Scalable-Reinforcement-Learning__arXiv-2505.18719v1.pdf:application/pdf}
}

@misc{EgoPi2026,
  title={Ego-Pi: VLA Fine-Tuning for Ego-Centric Human and Robot Data},
  author={Kim, Ji Woong and Wang, Ke and Fu, Zipeng and Chen, Sirui and Zhao, Cong and Lai, Jeff and Finn, Chelsea},
  year={2026},
  eprint={2606.08107},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.08107},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/01_人类数据与遥操作/2026__Ego-Pi__VLA-Fine-Tuning-for-Ego-Centric-Human-and-Robot-Data__arXiv-2606.08107v1.pdf:application/pdf}
}

@misc{EgoScale2026,
  title={EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data},
  author={Zheng, Ruijie and Niu, Dantong and Xie, Yuqi and Wang, Jing and Xu, Mengda and Jiang, Yunfan and Castañeda, Fernando and Hu, Fengyuan and Tan, You Liang and Fu, Letian and Darrell, Trevor and Huang, Furong and Zhu, Yuke and Xu, Danfei and Fan, Linxi},
  year={2026},
  eprint={2602.16710},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2602.16710},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/01_人类数据与遥操作/2026__EgoScale__Scaling-Dexterous-Manipulation-with-Diverse-Egocentric-Human-Data__arXiv-2602.16710v1.pdf:application/pdf}
}

@misc{DexVLA2025,
  title={DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control},
  author={Wen, Junjie and Zhu, Yichen and Li, Jinming and Tang, Zhibin and Shen, Chaomin and Feng, Feifei},
  year={2025},
  eprint={2502.05855},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2502.05855},
  note={Local PDF v3; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/05_VLA与生成策略基础/2025__DexVLA__Vision-Language-Model-with-Plug-In-Diffusion-Expert-for-General-Robot-Control__arXiv-2502.05855v3.pdf:application/pdf}
}

@misc{DexVLASeedSharedAutonomy2025,
  title={End-to-End Dexterous Arm-Hand VLA Policies via Shared Autonomy: VR Teleoperation Augmented by Autonomous Hand VLA Policy for Efficient Data Collection},
  author={Cui, Yu and Zhang, Yujian and Tao, Lina and Li, Yang and Yi, Xinyu and Li, Zhibin},
  year={2025},
  eprint={2511.00139},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2511.00139},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/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:application/pdf}
}

@misc{GRDexter2025,
  title={GR-Dexter Technical Report},
  author={Wen, Ruoshi and Chen, Guangzeng and Cui, Zhongren and Du, Min and Gou, Yang and Han, Zhigang and Huang, Liqun and Lei, Mingyu and Li, Yunfei and Li, Zhuohang and Liu, Wenlei and Liu, Yuxiao and Ma, Xiao and Niu, Hao and Ouyang, Yutao and Ren, Zeyu and Shi, Haixin and Xu, Wei and Zhang, Haoxiang and Zhang, Jiajun and Zhang, Xiao and Zheng, Liwei and Zhong, Weiheng and Zhou, Yifei and Zhu, Zhengming and Li, Hang},
  year={2025},
  eprint={2512.24210},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2512.24210},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/2025__GR-Dexter__Technical-Report__arXiv-2512.24210v2.pdf:application/pdf}
}

@misc{LingBotVA2026,
  title={Causal World Modeling for Robot Control},
  author={Li, Lin and Zhang, Qihang and Luo, Yiming and Yang, Shuai and Wang, Ruilin and Han, Fei and Yu, Mingrui and Gao, Zelin and Xue, Nan and Zhu, Xing and Shen, Yujun and Xu, Yinghao},
  year={2026},
  eprint={2601.21998},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2601.21998},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/06_世界动作模型/2026__LingBot-VA__Causal-World-Modeling-for-Robot-Control__arXiv-2601.21998v2.pdf:application/pdf}
}

@misc{DreamZero2026,
  title={World Action Models are Zero-shot Policies},
  author={Ye, Seonghyeon and Ge, Yunhao and Zheng, Kaiyuan and Gao, Shenyuan and Yu, Sihyun and Kurian, George and Indupuru, Suneel and Tan, You Liang and Zhu, Chuning and Xiang, Jiannan and Malik, Ayaan and Lee, Kyungmin and Liang, William and Ranawaka, Nadun and Gu, Jiasheng and Xu, Yinzhen and Wang, Guanzhi and Hu, Fengyuan and Narayan, Avnish and Bjorck, Johan and Wang, Jing and Kim, Gwanghyun and Niu, Dantong and Zheng, Ruijie and Xie, Yuqi and Wu, Jimmy and Wang, Qi and Julian, Ryan and Xu, Danfei and Du, Yilun and Chebotar, Yevgen and Reed, Scott and Kautz, Jan and Zhu, Yuke and Fan, Linxi "Jim" and Jang, Joel},
  year={2026},
  eprint={2602.15922},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2602.15922},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/06_世界动作模型/2026__DreamZero__World-Action-Models-are-Zero-shot-Policies__arXiv-2602.15922v1.pdf:application/pdf}
}

@misc{SkillVLA2026,
  title={SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse},
  author={Zhai, Xuanran and Huang, Zekai and Wu, Longyan and Zhao, Qianyou and Yu, Qiaojun and Ren, Jieji and Hao, Ce and Soh, Harold},
  year={2026},
  eprint={2603.03836},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2603.03836},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/2026__SkillVLA__Tackling-Combinatorial-Diversity-in-Dual-Arm-Manipulation-via-Skill-Reuse__arXiv-2603.03836v1.pdf:application/pdf}
}

@misc{MoDEVLAIMCopilot2026,
  title={Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-of-Dexterous-Experts VLA},
  author={Tang, Tutian and Ji, Xingyu and Xing, Wanli and Hao, Ce and Xu, Wenqiang and Shao, Lin and Lu, Cewu and Yu, Qiaojun and Pang, Jiangmiao and Zhang, Kaifeng},
  year={2026},
  eprint={2603.08122},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2603.08122},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/2026__MoDE-VLA-IMCopilot__Towards-Human-Like-Manipulation-through-RL-Augmented-Teleoperation-and-Mixture-of-Dexterous-Exp__arXiv-2603.08122v1.pdf:application/pdf}
}

@misc{MotuBrain2026,
  title={Motubrain: An Advanced World Action Model for Robot Control},
  author={Motubrain Team and Xiang, Chendong and Bao, Fan and Liu, Haitian and Tan, Hengkai and Bi, Hongzhe and Li, James and Liu, Jiabao and Pang, Jingrui and Jing, Kiro and Liu, Louis and Cai, Mengchen and Cui, Rongxu and Zhao, Ruowen and Wang, Runqing and Huang, Shuhe and Feng, Yao and Rong, Yinze and Wang, Zeyuan and Zhu, Jun},
  year={2026},
  eprint={2604.27792},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2604.27792},
  note={Local PDF v5; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/06_世界动作模型/2026__MotuBrain__An-Advanced-World-Action-Model-for-Robot-Control__arXiv-2604.27792v5.pdf:application/pdf}
}

@misc{Dexora2026,
  title={Dexora: Open-source VLA for High-DoF Bimanual Dexterity},
  author={Zhang, Zongzheng and Pang, Jingrui and Yang, Zhuo and Li, Kun and Liao, Minwen and Zhang, Saining and Chi, Guoxuan and Guo, Jinbang and Gao, Huan-ang and Shi, Modi and Ge, Dongyun and Mu, Yao and Gu, Jiayuan and Chen, Rui and Dong, Hao and Xu, Huazhe and Yi, Li and Zhu, Yixin and Zhao, Hang and Wang, Pengwei and Zhang, Shanghang and Yao, Guocai and Chen, Jianyu and Li, Hongyang and Zhao, Hao},
  year={2026},
  eprint={2605.18722},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.18722},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/2026__Dexora__Open-source-VLA-for-High-DoF-Bimanual-Dexterity__arXiv-2605.18722v1.pdf:application/pdf}
}

@misc{DSRL2025,
  title={Steering Your Diffusion Policy with Latent Space Reinforcement Learning},
  author={Wagenmaker, Andrew and Nakamoto, Mitsuhiko and Zhang, Yunchu and Park, Seohong and Yagoub, Waleed and Nagabandi, Anusha and Gupta, Abhishek and Levine, Sergey},
  year={2025},
  eprint={2506.15799},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2506.15799},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/03_Diffusion与Flow策略优化/2025__DSRL__Steering-Your-Diffusion-Policy-with-Latent-Space-Reinforcement-Learning__arXiv-2506.15799v2.pdf:application/pdf}
}

@misc{ACTALOHA2023,
  title={Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware},
  author={Zhao, Tony Z. and Kumar, Vikash and Levine, Sergey and Finn, Chelsea},
  year={2023},
  eprint={2304.13705},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2304.13705},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/01_ACT与模仿学习/2023__ACT-ALOHA__Learning-Fine-Grained-Bimanual-Manipulation-with-Low-Cost-Hardware__arXiv-2304.13705v1.pdf:application/pdf}
}

@misc{MobileALOHA2024,
  title={Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation},
  author={Fu, Zipeng and Zhao, Tony Z. and Finn, Chelsea},
  year={2024},
  eprint={2401.02117},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2401.02117},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/01_ACT与模仿学习/2024__Mobile-ALOHA__Learning-Bimanual-Mobile-Manipulation-with-Low-Cost-Whole-Body-Teleoperation__arXiv-2401.02117v1.pdf:application/pdf}
}

@misc{DiffusionPolicy2023,
  title={Diffusion Policy: Visuomotor Policy Learning via Action Diffusion},
  author={Chi, Cheng and Xu, Zhenjia and Feng, Siyuan and Cousineau, Eric and Du, Yilun and Burchfiel, Benjamin and Tedrake, Russ and Song, Shuran},
  year={2023},
  eprint={2303.04137},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2303.04137},
  note={Local PDF v5; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/05_VLA与生成策略基础/2023__Diffusion-Policy__Visuomotor-Policy-Learning-via-Action-Diffusion__arXiv-2303.04137v5.pdf:application/pdf}
}

@misc{OpenVLA2024,
  title={OpenVLA: An Open-Source Vision-Language-Action Model},
  author={Kim, Moo Jin and Pertsch, Karl and Karamcheti, Siddharth and Xiao, Ted and Balakrishna, Ashwin and Nair, Suraj and Rafailov, Rafael and Foster, Ethan and Lam, Grace and Sanketi, Pannag and Vuong, Quan and Kollar, Thomas and Burchfiel, Benjamin and Tedrake, Russ and Sadigh, Dorsa and Levine, Sergey and Liang, Percy and Finn, Chelsea},
  year={2024},
  eprint={2406.09246},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2406.09246},
  note={Local PDF v3; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/05_VLA与生成策略基础/2024__OpenVLA__An-Open-Source-Vision-Language-Action-Model__arXiv-2406.09246v3.pdf:application/pdf}
}

@misc{pi02024,
  title={$\pi_0$: A Vision-Language-Action Flow Model for General Robot Control},
  author={Black, Kevin and Brown, Noah and Driess, Danny and Esmail, Adnan and Equi, Michael and Finn, Chelsea and Fusai, Niccolo and Groom, Lachy and Hausman, Karol and Ichter, Brian and Jakubczak, Szymon and Jones, Tim and Ke, Liyiming and Levine, Sergey and Li-Bell, Adrian and Mothukuri, Mohith and Nair, Suraj and Pertsch, Karl and Shi, Lucy Xiaoyang and Tanner, James and Vuong, Quan and Walling, Anna and Wang, Haohuan and Zhilinsky, Ury},
  year={2024},
  eprint={2410.24164},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2410.24164},
  note={Local PDF v4; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/05_VLA与生成策略基础/2024__pi-0__A-Vision-Language-Action-Flow-Model-for-General-Robot-Control__arXiv-2410.24164v4.pdf:application/pdf}
}

@misc{OpenVLAOFT2025,
  title={Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success},
  author={Kim, Moo Jin and Finn, Chelsea and Liang, Percy},
  year={2025},
  eprint={2502.19645},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2502.19645},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/05_VLA与生成策略基础/2025__OpenVLA-OFT__Fine-Tuning-Vision-Language-Action-Models-Optimizing-Speed-and-Success__arXiv-2502.19645v2.pdf:application/pdf}
}

@misc{DexUMI2025,
  title={DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation},
  author={Xu, Mengda and Zhang, Han and Hou, Yifan and Xu, Zhenjia and Fan, Linxi and Veloso, Manuela and Song, Shuran},
  year={2025},
  eprint={2505.21864},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2505.21864},
  note={Local PDF v3; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/01_人类数据与遥操作/2025__DexUMI__Using-Human-Hand-as-the-Universal-Manipulation-Interface-for-Dexterous-Manipulation__arXiv-2505.21864v3.pdf:application/pdf}
}

@misc{DexCap2024,
  title={DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation},
  author={Wang, Chen and Shi, Haochen and Wang, Weizhuo and Zhang, Ruohan and Fei-Fei, Li and Liu, C. Karen},
  year={2024},
  eprint={2403.07788},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2403.07788},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/01_人类数据与遥操作/2024__DexCap__Scalable-and-Portable-Mocap-Data-Collection-System-for-Dexterous-Manipulation__arXiv-2403.07788v2.pdf:application/pdf}
}

@misc{DexMimicGen2024,
  title={DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning},
  author={Jiang, Zhenyu and Xie, Yuqi and Lin, Kevin and Xu, Zhenjia and Wan, Weikang and Mandlekar, Ajay and Fan, Linxi and Zhu, Yuke},
  year={2024},
  eprint={2410.24185},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2410.24185},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/02_仿真数据与基准/2024__DexMimicGen__Automated-Data-Generation-for-Bimanual-Dexterous-Manipulation-via-Imitation-Learnin__arXiv-2410.24185v2.pdf:application/pdf}
}

@misc{RoboTwin202025,
  title={RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation},
  author={Chen, Tianxing and Chen, Zanxin and Chen, Baijun and Cai, Zijian and Liu, Yibin and Li, Zixuan and Liang, Qiwei and Lin, Xianliang and Ge, Yiheng and Gu, Zhenyu and Deng, Weiliang and Guo, Yubin and Nian, Tian and Xie, Xuanbing and Chen, Qiangyu and Su, Kailun and Xu, Tianling and Liu, Guodong and Hu, Mengkang and Gao, Huan-ang and Wang, Kaixuan and Liang, Zhixuan and Qin, Yusen and Yang, Xiaokang and Luo, Ping and Mu, Yao},
  year={2025},
  eprint={2506.18088},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2506.18088},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/02_仿真数据与基准/2025__RoboTwin-2.0__RoboTwin-2-0-A-Scalable-Data-Generator-and-Benchmark-with-Strong-Domain-Randomization-for-Robus__arXiv-2506.18088v2.pdf:application/pdf}
}

@misc{UMI2024,
  title={Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots},
  author={Chi, Cheng and Xu, Zhenjia and Pan, Chuer and Cousineau, Eric and Burchfiel, Benjamin and Feng, Siyuan and Tedrake, Russ and Song, Shuran},
  year={2024},
  eprint={2402.10329},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2402.10329},
  note={Local PDF v3; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/04_数据采集与评测/01_人类数据与遥操作/2024__UMI__Universal-Manipulation-Interface-In-The-Wild-Robot-Teaching-Without-In-The-Wild-Robots__arXiv-2402.10329v3.pdf:application/pdf}
}

@misc{DeCAL2026,
  title={DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination},
  author={Fu, Yankai and Chen, Ning and Zhao, Junkai and Zhang, Heng and Yao, Guocai and Wang, Pengwei and Wang, Zhongyuan and Zhang, Shanghang},
  year={2026},
  eprint={2609.09119},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.09119},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/2026__DeCAL__Towards-Physically-Grounded-Dexterous-Vision-Language-Action-Models-via-Contact-Aware-Lat__arXiv-2609.09119v1.pdf:application/pdf}
}

@misc{TRex2026,
  title={T-Rex: Tactile-Reactive Dexterous Manipulation},
  author={Niu, Dantong and Liu, Zhuoyang and Wang, Zekai and Shao, Boning and Yin, Zhao-Heng and Pai, Anirudh and Sharma, Yuvan and Saravalle, Stefano and Zheng, Ruijie and Wang, Jing and Punamiya, Ryan and Xu, Mengda and Xie, Yuqi and Jiang, Yunfan and Fu, Letian and Kallidromitis, Konstantinos and Gioia, Matteo and Zhang, Junyi and Ge, Jiaxin and Feng, Haiwen and Galasso, Fabio and Zhan, Wei and Chan, David M. and Bai, Yutong and Herzig, Roei and Lei, Jiahui and Fei-Fei, Li and Goldberg, Ken and Malik, Jitendra and Abbeel, Pieter and Zhu, Yuke and Xu, Danfei and Fan, Linxi and Darrell, Trevor},
  year={2026},
  eprint={2606.17055},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.17055},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/01_双臂与灵巧手VLA/2026__T-Rex__Tactile-Reactive-Dexterous-Manipulation__arXiv-2606.17055v2.pdf:application/pdf}
}

@misc{HandintheLoop2026,
  title={Hand-in-the-Loop: Improving VLA Policies for Dexterous Manipulation via Seamless Hand-Arm Intervention},
  author={Li, Zhuohang and Huang, Liqun and Xu, Wei and Zhu, Zhengming and Lin, Nie and Ma, Xiao and Sheng, Xinjun and Wen, Ruoshi},
  year={2026},
  eprint={2605.15157},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.15157},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/04_真机在线学习与干预/2026__Hand-in-the-Loop__Improving-VLA-Policies-for-Dexterous-Manipulation-via-Seamless-Hand-Arm-Interv__arXiv-2605.15157v2.pdf:application/pdf}
}

@misc{SelfAdaptiveVLA2026,
  title={Self-Adaptive VLA for Robust Robot Deployment},
  author={Zhang, Hongxin and Lin, Chunru and Wang, Tsun-Hsuan and Xu, Zhenjia and Gan, Chuang},
  year={2026},
  eprint={2609.30092},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.30092},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__Self-Adaptive-VLA__for-Robust-Robot-Deployment__arXiv-2609.30092v1.pdf:application/pdf}
}

@misc{IQL2021,
  title={Offline Reinforcement Learning with Implicit Q-Learning},
  author={Kostrikov, Ilya and Nair, Ashvin and Levine, Sergey},
  year={2021},
  eprint={2110.06169},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2110.06169},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2021__IQL__Offline-Reinforcement-Learning-with-Implicit-Q-Learning__arXiv-2110.06169v1.pdf:application/pdf}
}

@misc{RLPD2023,
  title={Efficient Online Reinforcement Learning with Offline Data},
  author={Ball, Philip J. and Smith, Laura and Kostrikov, Ilya and Levine, Sergey},
  year={2023},
  eprint={2302.02948},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2302.02948},
  note={Local PDF v4; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2023__RLPD__Efficient-Online-Reinforcement-Learning-with-Offline-Data__arXiv-2302.02948v4.pdf:application/pdf}
}

@misc{CalQL2023,
  title={Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning},
  author={Nakamoto, Mitsuhiko and Zhai, Yuexiang and Singh, Anikait and Mark, Max Sobol and Ma, Yi and Finn, Chelsea and Kumar, Aviral and Levine, Sergey},
  year={2023},
  eprint={2303.05479},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2303.05479},
  note={Local PDF v4; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2023__Cal-QL__Calibrated-Offline-RL-Pre-Training-for-Efficient-Online-Fine-Tuning__arXiv-2303.05479v4.pdf:application/pdf}
}

@misc{FQL2025,
  title={Flow Q-Learning},
  author={Park, Seohong and Li, Qiyang and Levine, Sergey},
  year={2025},
  eprint={2502.02538},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2502.02538},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2025__FQL__Flow-Q-Learning__arXiv-2502.02538v2.pdf:application/pdf}
}

@misc{DPPO2024,
  title={Diffusion Policy Policy Optimization},
  author={Ren, Allen Z. and Lidard, Justin and Ankile, Lars L. and Simeonov, Anthony and Agrawal, Pulkit and Majumdar, Anirudha and Burchfiel, Benjamin and Dai, Hongkai and Simchowitz, Max},
  year={2024},
  eprint={2409.00588},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2409.00588},
  note={Local PDF v3; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/03_Diffusion与Flow策略优化/2024__DPPO__Diffusion-Policy-Policy-Optimization__arXiv-2409.00588v3.pdf:application/pdf}
}

@misc{ReinFlow2025,
  title={ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning},
  author={Zhang, Tonghe and Yu, Chao and Su, Sichang and Wang, Yu},
  year={2025},
  eprint={2505.22094},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2505.22094},
  note={Local PDF v7; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/03_Diffusion与Flow策略优化/2025__ReinFlow__Fine-tuning-Flow-Matching-Policy-with-Online-Reinforcement-Learning__arXiv-2505.22094v7.pdf:application/pdf}
}

@misc{RIPTVLA2025,
  title={Interactive Post-Training for Vision-Language-Action Models},
  author={Tan, Shuhan and Dou, Kairan and Zhao, Yue and Krähenbühl, Philipp},
  year={2025},
  eprint={2505.17016},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2505.17016},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2025__RIPT-VLA__Interactive-Post-Training-for-Vision-Language-Action-Models__arXiv-2505.17016v1.pdf:application/pdf}
}

@misc{SimpleVLARL2025,
  title={SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning},
  author={Li, Haozhan and Zuo, Yuxin and Yu, Jiale and Zhang, Yuhao and Yang, Zhaohui and Zhang, Kaiyan and Zhu, Xuekai and Zhang, Yuchen and Chen, Tianxing and Cui, Ganqu and Wang, Dehui and Luo, Dingxiang and Fan, Yuchen and Sun, Youbang and Zeng, Jia and Pang, Jiangmiao and Zhang, Shanghang and Wang, Yu and Mu, Yao and Zhou, Bowen and Ding, Ning},
  year={2025},
  eprint={2509.09674},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2509.09674},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2025__SimpleVLA-RL__Scaling-VLA-Training-via-Reinforcement-Learning__arXiv-2509.09674v1.pdf:application/pdf}
}

@misc{CORFT2025,
  title={CO-RFT: Efficient Fine-Tuning of Vision-Language-Action Models through Chunked Offline Reinforcement Learning},
  author={Huang, Dongchi and Fang, Zhirui and Zhang, Tianle and Li, Yihang and Zhao, Lin and Xia, Chunhe},
  year={2025},
  eprint={2508.02219},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2508.02219},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2025__CO-RFT__Efficient-Fine-Tuning-of-Vision-Language-Action-Models-through-Chunked-Offline-Reinforce__arXiv-2508.02219v1.pdf:application/pdf}
}

@misc{QChunking2025,
  title={Reinforcement Learning with Action Chunking},
  author={Li, Qiyang and Zhou, Zhiyuan and Levine, Sergey},
  year={2025},
  eprint={2507.07969},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2507.07969},
  note={Local PDF v4; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2025__Q-Chunking__Reinforcement-Learning-with-Action-Chunking__arXiv-2507.07969v4.pdf:application/pdf}
}

@misc{AdaptiveQChunking2026,
  title={Adaptive Q-Chunking for Offline-to-Online Reinforcement Learning},
  author={Gireesh, Nandiraju and Ju, Yuanliang and Wang, He},
  year={2026},
  eprint={2605.05544},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.05544},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/01_Offline与Offline-to-Online基础/2026__Adaptive-Q-Chunking__for-Offline-to-Online-Reinforcement-Learning__arXiv-2605.05544v1.pdf:application/pdf}
}

@misc{HILSERL2024,
  title={Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning},
  author={Luo, Jianlan and Xu, Charles and Wu, Jeffrey and Levine, Sergey},
  year={2024},
  eprint={2410.21845},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2410.21845},
  note={Local PDF v3; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/04_真机在线学习与干预/2024__HIL-SERL__Precise-and-Dexterous-Robotic-Manipulation-via-Human-in-the-Loop-Reinforcement-Learning__arXiv-2410.21845v3.pdf:application/pdf}
}

@misc{LearningWhileDeploying2026,
  title={Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies},
  author={Wang, Yi and Li, Xinchen and Xie, Pengwei and Yang, Pu and Nie, Buqing and Cai, Yunuo and Zhang, Qinglin and Qu, Chendi and Wu, Jeffrey and Song, Jianheng and Ren, Xinlin and Huang, Jingshun and Pan, Mingjie and Feng, Siyuan and Chen, Zhi and Luo, Jianlan},
  year={2026},
  eprint={2605.00416},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.00416},
  note={Local PDF v4; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__Learning-While-Deploying__Fleet-Scale-Reinforcement-Learning-for-Generalist-Robot-Policies__arXiv-2605.00416v4.pdf:application/pdf}
}

@misc{OfflineSupervisionVLARL2026,
  title={Leveraging Offline Supervision for Efficient and Generalizable Reinforcement Learning in Large-Scale Vision-Language-Action Models},
  author={Poyarkov, Dmitriy and Staroverov, Aleksei and Panov, Aleksandr I.},
  year={2026},
  eprint={2607.19399},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2607.19399},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__Offline-Supervision-VLA-RL__Leveraging-Offline-Supervision-for-Efficient-and-Generalizable-Reinforcement-Learning-in-Large__arXiv-2607.19399v1.pdf:application/pdf}
}

@misc{UncertaintyGatedExploration2026,
  title={Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy},
  author={Yardımcı, Mehmet Turan and Çoğurcu, Yunus Emre},
  year={2026},
  eprint={2609.28838},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.28838},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/02_VLA后训练/2026__Uncertainty-Gated-Exploration__Noise-Suppresses-Task-Collapse-in-Online-RL-Fine-Tuning-of-a-Flow__arXiv-2609.28838v1.pdf:application/pdf}
}

@misc{SENTINEL2025,
  title={SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control},
  author={Wang, Yuxuan and Jiang, Haobin and Yao, Shiqing and Ding, Ziluo and Lu, Zongqing},
  year={2025},
  eprint={2511.19236},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2511.19236},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/02_任务语言到动作接口/2025__SENTINEL__A-Fully-End-to-End-Language-Action-Model-for-Humanoid-Whole-Body-Control__arXiv-2511.19236v1.pdf:application/pdf}
}

@misc{WholeBodyVLA2025,
  title={WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Control},
  author={Jiang, Haoran and Chen, Jin and Bu, Qingwen and Chen, Li and Shi, Modi and Zhang, Yanjie and Li, Delong and Suo, Chuanzhe and Wang, Chuang and Peng, Zhihui and Li, Hongyang},
  year={2025},
  eprint={2512.11047},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2512.11047},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/02_任务语言到动作接口/2025__WholeBodyVLA__Towards-Unified-Latent-VLA-for-Whole-Body-Loco-Manipulation-Control__arXiv-2512.11047v2.pdf:application/pdf}
}

@misc{HumanPlus2024,
  title={HumanPlus: Humanoid Shadowing and Imitation from Humans},
  author={Fu, Zipeng and Zhao, Qingqing and Wu, Qi and Wetzstein, Gordon and Finn, Chelsea},
  year={2024},
  eprint={2406.10454},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2406.10454},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/01_ACT与模仿学习/2024__HumanPlus__Humanoid-Shadowing-and-Imitation-from-Humans__arXiv-2406.10454v1.pdf:application/pdf}
}

@misc{OmniH2O2024,
  title={OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning},
  author={He, Tairan and Luo, Zhengyi and He, Xialin and Xiao, Wenli and Zhang, Chong and Zhang, Weinan and Kitani, Kris and Liu, Changliu and Shi, Guanya},
  year={2024},
  eprint={2406.08858},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2406.08858},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/03_全身运动控制基础/2024__OmniH2O__Universal-and-Dexterous-Human-to-Humanoid-Whole-Body-Teleoperation-and-Learning__arXiv-2406.08858v1.pdf:application/pdf}
}

@misc{TWIST2025,
  title={TWIST: Teleoperated Whole-Body Imitation System},
  author={Ze, Yanjie and Chen, Zixuan and Araújo, João Pedro and Cao, Zi-ang and Peng, Xue Bin and Wu, Jiajun and Liu, C. Karen},
  year={2025},
  eprint={2505.02833},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2505.02833},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/03_全身运动控制基础/2025__TWIST__Teleoperated-Whole-Body-Imitation-System__arXiv-2505.02833v1.pdf:application/pdf}
}

@misc{TWIST22025,
  title={TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System},
  author={Ze, Yanjie and Zhao, Siheng and Wang, Weizhuo and Kanazawa, Angjoo and Duan, Rocky and Abbeel, Pieter and Shi, Guanya and Wu, Jiajun and Liu, C. Karen},
  year={2025},
  eprint={2511.02832},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2511.02832},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/03_全身运动控制基础/2025__TWIST2__Scalable-Portable-and-Holistic-Humanoid-Data-Collection-System__arXiv-2511.02832v1.pdf:application/pdf}
}

@misc{GR00TN12025,
  title={GR00T N1: An Open Foundation Model for Generalist Humanoid Robots},
  author={NVIDIA and : and Bjorck, Johan and Castañeda, Fernando and Cherniadev, Nikita and Da, Xingye and Ding, Runyu and Fan, Linxi "Jim" and Fang, Yu and Fox, Dieter and Hu, Fengyuan and Huang, Spencer and Jang, Joel and Jiang, Zhenyu and Kautz, Jan and Kundalia, Kaushil and Lao, Lawrence and Li, Zhiqi and Lin, Zongyu and Lin, Kevin and Liu, Guilin and Llontop, Edith and Magne, Loic and Mandlekar, Ajay and Narayan, Avnish and Nasiriany, Soroush and Reed, Scott and Tan, You Liang and Wang, Guanzhi and Wang, Zu and Wang, Jing and Wang, Qi and Xiang, Jiannan and Xie, Yuqi and Xu, Yinzhen and Xu, Zhenjia and Ye, Seonghyeon and Yu, Zhiding and Zhang, Ao and Zhang, Hao and Zhao, Yizhou and Zheng, Ruijie and Zhu, Yuke},
  year={2025},
  eprint={2503.14734},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2503.14734},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/02_任务语言到动作接口/2025__GR00T-N1__An-Open-Foundation-Model-for-Generalist-Humanoid-Robots__arXiv-2503.14734v2.pdf:application/pdf}
}

@misc{TANGO2026,
  title={TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model},
  author={Li, Anqi and Chen, Yuxin and Li, Zhaobo and Cao, Zhuo and Ren, Junli and Tomizuka, Masayoshi and Shah, Dhruv},
  year={2026},
  eprint={2609.09158},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.09158},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/02_任务语言到动作接口/2026__TANGO__Humanoid-Navigation-in-Cluttered-Environments-with-a-Whole-Body-Vision-Language-Action-Mo__arXiv-2609.09158v1.pdf:application/pdf}
}

@misc{TACT2025,
  title={TACT: Humanoid Whole-body Contact Manipulation through Deep Imitation Learning with Tactile Modality},
  author={Murooka, Masaki and Hoshi, Takahiro and Fukumitsu, Kensuke and Masuda, Shimpei and Hamze, Marwan and Sasaki, Tomoya and Morisawa, Mitsuharu and Yoshida, Eiichi},
  year={2025},
  eprint={2506.15146},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2506.15146},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/01_ACT与模仿学习/2025__TACT__Humanoid-Whole-body-Contact-Manipulation-through-Deep-Imitation-Learning-with-Tactile-Moda__arXiv-2506.15146v1.pdf:application/pdf}
}

@misc{FetchMan2026,
  title={FetchMan: Learning Visual Humanoid Loco-Manipulation Policies from Simulated Experiences},
  author={Rayyan, Omar and Li, Zhi and Argus, Max and Jiang, Yuxin and Yu, Chang and Jiang, Chenfanfu and Cui, Yuchen},
  year={2026},
  eprint={2608.17027},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2608.17027},
  note={Local PDF v2; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/02_任务语言到动作接口/2026__FetchMan__Learning-Visual-Humanoid-Loco-Manipulation-Policies-from-Simulated-Experiences__arXiv-2608.17027v2.pdf:application/pdf}
}

@misc{Opt2VLA2026,
  title={Opt2VLA: Force-Aware Vision-Language-Action for Contact-Rich Humanoid Whole-Body Manipulation},
  author={Liu, Fukang and Chen, Yipu and Jang, Jaehwi and Xu, Danfei and Kira, Zsolt and Zhao, Ye},
  year={2026},
  eprint={2609.23968},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2609.23968},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/03_人形机器人与ACT/02_任务语言到动作接口/2026__Opt2VLA__Force-Aware-Vision-Language-Action-for-Contact-Rich-Humanoid-Whole-Body-Manipulation__arXiv-2609.23968v1.pdf:application/pdf}
}

@misc{QGF2026,
  title={Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning},
  author={Zhou, Zhiyuan and Peng, Andy and Xu, Charles and Li, Qiyang and Springenberg, Tobias and Frans, Kevin and Levine, Sergey},
  year={2026},
  eprint={2606.11087},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.11087},
  note={Local PDF v1; checked 2026-10-02},
  file={:/Users/simplemaxq/Desktop/MaRs Lab/论文库/02_RL后训练/03_Diffusion与Flow策略优化/2026__QGF__Test-Time-Gradient-Guidance-of-Flow-Policies-in-Reinforcement-Learning__arXiv-2606.11087v1.pdf:application/pdf}
}