@article{sunderhauf_limits_2018,
  title = {The limits and potentials of deep learning for robotics},
  volume = {37},
  url = {https://journals.sagepub.com/doi/10.1177/0278364918770733},
  doi = {10.1177/0278364918770733},
  journal = {The International Journal of Robotics Research},
  author = {Sünderhauf, Niko and Brock, Oliver and Scheirer, Walter and Hadsell, Raia and Fox, Dieter and Leitner, Jürgen and Upcroft, Ben and Abbeel, Pieter and Burgard, Wolfram and Milford, Michael and Corke, Peter},
  year = {2018},
  pages = {405--420},
}

@misc{mandlekar_mimicgen_2023,
  title = {{MimicGen}: {A} {Data} {Generation} {System} for {Scalable} {Robot} {Learning} using {Human} {Demonstrations}},
  url = {http://arxiv.org/abs/2310.17596},
  publisher = {arXiv},
  author = {Mandlekar, Ajay and Nasiriany, Soroush and Wen, Bowen and Akinola, Iretiayo and Narang, Yashraj and Fan, Linxi and Zhu, Yuke and Fox, Dieter},
  year = {2023},
}

@misc{kareer_egomimic_2024,
  author = {Kareer, Simar and Patel, Dhruv and Punamiya, Ryan and Mathur, Pranay and Cheng, Shuo and Wang, Chen and Hoffman, Judy and Xu, Danfei},
  booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {EgoMimic: Scaling Imitation Learning via Egocentric Video},
  year = {2025},
  volume = {},
  pages = {13226-13233},
  doi = {10.1109/ICRA55743.2025.11127989},
}

@article{damen_rescaling_2020,
  title = {Rescaling {Egocentric} {Vision}: {Collection}, {Pipeline} and {Challenges} for {EPIC}-{KITCHENS}-100},
  volume = {130},
  url = {https://link.springer.com/10.1007/s11263-021-01531-2},
  doi = {10.1007/s11263-021-01531-2},
  journal = {International Journal of Computer Vision},
  author = {Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria and Furnari, Antonino and Kazakos, Evangelos and Ma, Jian and Moltisanti, Davide and Munro, Jonathan and Perrett, Toby and Price, Will and Wray, Michael},
  year = {2022},
  pages = {33--55},
}

@misc{grauman_ego4d_2022,
  author = {Grauman, Kristen and Westbury, Andrew and Byrne, Eugene and Chavis, Zachary and Furnari, Antonino and Girdhar, Rohit and Hamburger, Jackson and Jiang, Hao and Liu, Miao and Liu, Xingyu and Martin, Miguel and Nagarajan, Tushar and Radosavovic, Ilija and Ramakrishnan, Santhosh Kumar and Ryan, Fiona and Sharma, Jayant and Wray, Michael and Xu, Mengmeng and Xu, Eric Zhongcong and Zhao, Chen and Bansal, Siddhant and Batra, Dhruv and Cartillier, Vincent and Crane, Sean and Do, Tien and Doulaty, Morrie and Erapalli, Akshay and Feichtenhofer, Christoph and Fragomeni, Adriano and Fu, Qichen and Gebreselasie, Abrham and González, Cristina and Hillis, James and Huang, Xuhua and Huang, Yifei and Jia, Wenqi and Khoo, Weslie and Koláĭ, Jáchym and Kottur, Satwik and Kumar, Anurag and Landini, Federico and Li, Chao and Li, Yanghao and Li, Zhenqiang and Mangalam, Karttikeya and Modhugu, Raghava and Munro, Jonathan and Murrell, Tullie and Nishiyasu, Takumi and Price, Will and Puentes, Paola Ruiz and Ramazanova, Merey and Sari, Leda and Somasundaram, Kiran and Southerland, Audrey and Sugano, Yusuke and Tao, Ruijie and Vo, Minh and Wang, Yuchen and Wu, Xindi and Yagi, Takuma and Zhao, Ziwei and Zhu, Yunyi and Arbeláez, Pablo and Crandall, David and Damen, Dima and Farinella, Giovanni Maria and Fuegen, Christian and Ghanem, Bernard and Ithapu, Vamsi Krishna and Jawahar, C. V. and Joo, Hanbyul and Kitani, Kris and Li, Haizhou and Newcombe, Richard and Oliva, Aude and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Shi, Jianbo and Shou, Mike Zheng and Torralba, Antonio and Torresani, Lorenzo and Yan, Mingfei and Malik, Jitendra},
  booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Ego4D: Around the World in 3,000 Hours of Egocentric Video},
  year = {2022},
  volume = {},
  pages = {18973-18990},
  doi = {10.1109/CVPR52688.2022.01842},
}

@inproceedings{su_interformer_2026,
  author = {Su, Yuejiao and Wang, Yi and Yao, Lei and Cui, Yawen and Chau, Lap-Pui},
  booktitle = {International Conference on Learning Representations},
  pages = {126126--126147},
  title = {Interaction-aware Representation Modeling With Co-Occurrence Consistency for Egocentric Hand-Object Parsing},
  volume = {2026},
  year = {2026},
}

@misc{nair_r3m_2022,
  title = {{R3M}: {A} {Universal} {Visual} {Representation} for {Robot} {Manipulation}},
  url = {http://arxiv.org/abs/2203.12601},
  publisher = {arXiv},
  author = {Nair, Suraj and Rajeswaran, Aravind and Kumar, Vikash and Finn, Chelsea and Gupta, Abhinav},
  year = {2022},
}

@misc{ye_latent_2025,
  title = {Latent {Action} {Pretraining} from {Videos}},
  url = {http://arxiv.org/abs/2410.11758},
  publisher = {arXiv},
  author = {Ye, Seonghyeon and Jang, Joel and Jeon, Byeongguk and Joo, Sejune and Yang, Jianwei and Peng, Baolin and Mandlekar, Ajay and Tan, Reuben and Chao, Yu-Wei and Lin, Bill Yuchen and Liden, Lars and Lee, Kimin and Gao, Jianfeng and Zettlemoyer, Luke and Fox, Dieter and Seo, Minjoon},
  year = {2025},
}

@misc{hoque_egodex_2026,
  title = {{EgoDex}: {Learning} {Dexterous} {Manipulation} from {Large}-{Scale} {Egocentric} {Video}},
  url = {http://arxiv.org/abs/2505.11709},
  publisher = {arXiv},
  author = {Hoque, Ryan and Huang, Peide and Yoon, David J. and Sivapurapu, Mouli and Zhang, Jian},
  year = {2026},
}

@misc{robomimic,
  title = {What Matters in Learning from Offline Human Demonstrations for Robot Manipulation},
  author = {Ajay Mandlekar and Danfei Xu and Josiah Wong and Soroush Nasiriany and Chen Wang and Rohun Kulkarni and Li Fei-Fei and Silvio Savarese and Yuke Zhu and Roberto Martín-Martín},
  year = {2021},
  eprint = {2108.03298},
  url = {https://arxiv.org/abs/2108.03298},
}

@misc{roboturk,
  author = {Ajay Mandlekar and
                  Jonathan Booher and
                  Max Spero and
                  Albert Tung and
                  Anchit Gupta and
                  Yuke Zhu and
                  Animesh Garg and
                  Silvio Savarese and
                  Li Fei{-}Fei},
  title = {Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic
                  Manipulation Dataset through Human Reasoning and Dexterity},
  booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and
                  Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019},
  pages = {1048--1055},
  publisher = {{IEEE}},
  year = {2019},
  doi = {10.1109/IROS40897.2019.8968114},
}

@misc{correia_survey_2023,
  title = {A survey of demonstration learning},
  journal = {Robotics and Autonomous Systems},
  volume = {182},
  pages = {104812},
  year = {2024},
  doi = {https://doi.org/10.1016/j.robot.2024.104812},
  url = {https://www.sciencedirect.com/science/article/pii/S0921889024001969},
  author = {André Correia and Luís A. Alexandre},
}

@article{eze_learning_2025,
  author = {Eze, Chrisantus and Crick, Christopher},
  journal = {IEEE Access},
  title = {Learning by Watching: A Review of Video-Based Learning Approaches for Robot Manipulation},
  year = {2025},
  volume = {13},
  pages = {184071-184109},
  doi = {10.1109/ACCESS.2025.3624723},
}

@misc{ma_robot_2026,
  title = {Robot {Learning} from {Human} {Videos}: {A} {Survey}},
  url = {https://arxiv.org/abs/2604.27621},
  publisher = {arXiv},
  author = {Ma, Junyi and Zhang, Erhang and Yang, Haoran and Li, Ditao and Xu, Chenyang and Wang, Guangming and Wang, Hesheng},
  year = {2026},
}

@misc{ye_data_2026,
  title = {Data {Pyramid} for {Embodied} {Manipulation}: {A} {Survey}},
  url = {http://arxiv.org/abs/2607.24744},
  publisher = {arXiv},
  author = {Ye, Yifan and Fu, Yankai and Lv, Yaoxu and Hou, Bohan and Cen, Jun and Kong, Lingdong and Zheng, Duo and Chen, Tianxing and Liu, Jiaming and Cao, Ziang and Lou, Yunfan and Chow, Wei and Sun, Xian and Wang, Yingshuo and Ge, Kuangzhi and Chi, Xiaowei and Zhang, Xidong and Pang, Zhibo and Zhong, Yiwu and Han, Sirui and Lu, Zhihe and Yuan, Weihao and Chen, Qifeng and Wang, Michael Yu and Mu, Yao and Liu, Ziwei and Yang, Jianfei and Luo, Ping and Zhang, Shanghang},
  year = {2026},
}

@article{zheng_survey_2025,
  title = {A {Survey} of {Embodied} {Learning} for {Object}-centric {Robotic} {Manipulation}},
  volume = {22},
  url = {https://link.springer.com/10.1007/s11633-025-1542-8},
  doi = {10.1007/s11633-025-1542-8},
  journal = {Machine Intelligence Research},
  author = {Zheng, Ying and Yao, Lei and Su, Yuejiao and Zhang, Yi and Wang, Yi and Zhao, Sicheng and Zhang, Yiyi and Chau, Lap-Pui},
  year = {2025},
  pages = {588--626},
}

@inproceedings{feng_human_2026,
  title = {From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data},
  author = {Feng, Zhiyuan and Li, Qixiu and Liang, Huizhi and Yang, Rushuai and Shen, Yichao and Du, Zhiying and Zhang, Zhaowei and Deng, Yu and Zhao, Li and Zhao, Hao and Lu, Zongqing and Mees, Oier and Pollefeys, Marc and Yang, Jiaolong and Guo, Baining},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  pages = {7845--7854},
  year = {2026},
  doi = {10.24963/ijcai.2026/871},
}

@article{mccarthy_towards_2025,
  title = {Towards {Generalist} {Robot} {Learning} from {Internet} {Video}: {A} {Survey}},
  volume = {83},
  url = {https://jair.org/index.php/jair/article/view/17400},
  doi = {10.1613/jair.1.17400},
  journal = {Journal of Artificial Intelligence Research},
  author = {McCarthy, Robert and C.H. Tan, Daniel and Schmidt, Dominik and Acero, Fernando and Herr, Nathan and Du, Yilun and G. Thuruthel, Thomas and Li, Zhibin},
  year = {2025},
}

@misc{zheng_video_2026,
  title = {From {Video} to {Control}: {A} {Survey} of {Learning} {Manipulation} {Interfaces} from {Temporal} {Visual} {Data}},
  url = {http://arxiv.org/abs/2604.04974},
  publisher = {arXiv},
  author = {Zheng, Linfang and Ouyang, Zikai and Wang, Chen and Pan, Jia and Zhang, Wei},
  year = {2026},
}

@misc{zhu_mass_2026,
  title = {MASS: Mesh-inellipse Aligned Deformable Surfel Splatting for Hand Reconstruction and Rendering from Egocentric Monocular Video},
  author = {Haoyu Zhu and Yi Zhang and Lei Yao and Lap-pui Chau and Yi Wang},
  year = {2026},
  eprint = {2604.08943},
  url = {https://arxiv.org/abs/2604.08943},
}

@inproceedings{rong_frankmocap_2021,
  author = {Rong, Yu and Shiratori, Takaaki and Joo, Hanbyul},
  booktitle = {2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
  title = {FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration},
  year = {2021},
  volume = {},
  pages = {1749-1759},
  doi = {10.1109/ICCVW54120.2021.00201},
}

@inproceedings{pavlakos_reconstructing_2024,
  author = {Pavlakos, Georgios and Shan, Dandan and Radosavovic, Ilija and Kanazawa, Angjoo and Fouhey, David and Malik, Jitendra},
  booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Reconstructing Hands in 3D with Transformers},
  year = {2024},
  volume = {},
  pages = {9826-9836},
  doi = {10.1109/CVPR52733.2024.00938},
}

@misc{potamias_wilor_2025,
  author = {Potamias, Rolandos Alexandros and Zhang, Jinglei and Deng, Jiankang and Zafeiriou, Stefanos},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild},
  year = {2025},
  volume = {},
  pages = {12242-12254},
  doi = {10.1109/CVPR52734.2025.01143},
}

@misc{zhang_hawor_2025,
  author = {Zhang, Jinglei and Deng, Jiankang and Ma, Chao and Potamias, Rolandos Alexandros},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {{ HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos }},
  year = {2025},
  volume = {},
  pages = {1805-1815},
  doi = {10.1109/CVPR52734.2025.00175},
  publisher = {IEEE Computer Society},
}

@misc{xie_egohandicl_2026,
  title = {{EgoHandICL}: {Egocentric} {3D} {Hand} {Reconstruction} with {In}-{Context} {Learning}},
  url = {https://arxiv.org/abs/2601.19850},
  publisher = {arXiv},
  author = {Xie, Binzhu and Qiu, Shi and Zhang, Sicheng and Wang, Yinqiao and Xu, Hao and Naseer, Muzammal and Fu, Chi-Wing and Heng, Pheng-Ann},
  year = {2026},
}

@misc{bae_hand-4dgs_2026,
  title = {Hand-{4DGS}: {Feed}-{Forward} {3D} {Gaussian} {Splatting} for {4D} {Hand} {Reconstruction} from {Egocentric} {Videos}},
  url = {http://arxiv.org/abs/2606.19156},
  publisher = {arXiv},
  author = {Bae, Jeongmin and Kim, Seoha and Pollefeys, Marc and Rad, Mahdi and Uh, Youngjung and Kwon, Taein},
  year = {2026},
}

@misc{hara_eventegohands_2025,
  author = {Hara, Ryosei and Ikeda, Wataru and Hatano, Masashi and Isogawa, Mariko},
  booktitle = {2025 IEEE International Conference on Image Processing (ICIP)},
  title = {EventEgoHands: Event-Based Egocentric 3D Hand Mesh Reconstruction},
  year = {2025},
  volume = {},
  pages = {1199-1204},
  doi = {10.1109/ICIP55913.2025.11084751},
}

@misc{wang_egoev-handpose_2026,
  title = {{EgoEV}-{HandPose}: {Egocentric} {3D} {Hand} {Pose} {Estimation} and {Gesture} {Recognition} with {Stereo} {Event} {Cameras}},
  url = {https://arxiv.org/abs/2605.12297},
  publisher = {arXiv},
  author = {Wang, Luming and Shi, Hao and Zhai, Jiajun and Yang, Kailun and Wang, Kaiwei},
  year = {2026},
}

@misc{ye_whole_2026,
  title = {{WHOLE}: {World}-{Grounded} {Hand}-{Object} {Lifted} from {Egocentric} {Videos}},
  url = {http://arxiv.org/abs/2602.22209},
  publisher = {arXiv},
  author = {Ye, Yufei and Li, Jiaman and Rong, Ryan and Liu, C. Karen},
  year = {2026},
}

@misc{fu_egograsp_2026,
  title = {{EgoGrasp}: {World}-{Space} {Hand}-{Object} {Interaction} {Estimation} from {Egocentric} {Videos}},
  url = {https://arxiv.org/abs/2601.01050},
  publisher = {arXiv},
  author = {Fu, Hongming and Wang, Wenjia and Qiao, Xiaozhen and Potamias, Rolandos Alexandros and Komura, Taku and Yang, Shuo and Liu, Zheng and Zhao, Bo},
  year = {2026},
}

@misc{wang_egoinfinity_2026,
  title = {{EgoInfinity}: {A} {Web}-{Scale} {4D} {Hand}-{Object} {Interaction} {Data} {Engine} for {Any}-{View} {Robot} {Retargeting} and {Video}-to-{Action} {Robot} {Learning}},
  url = {https://arxiv.org/abs/2606.17385},
  publisher = {arXiv},
  author = {Wang, Gaotian and Ren, Kejia and Morgan, Andrew and Chen, Yiting and Qian, Howard H. and Chanrungmaneekul, Podshara and Hang, Kaiyu},
  year = {2026},
}

@misc{bharadhwaj_zero-shot_2023,
  title = {Zero-{Shot} {Robot} {Manipulation} from {Passive} {Human} {Videos}},
  url = {http://arxiv.org/abs/2302.02011},
  publisher = {arXiv},
  author = {Bharadhwaj, Homanga and Gupta, Abhinav and Tulsiani, Shubham and Kumar, Vikash},
  year = {2023},
}

@inproceedings{wang_dexcap_2024,
  author = {Chen Wang AND Haochen Shi AND Weizhuo Wang AND Ruohan Zhang AND Li Fei-Fei AND Karen Liu},
  title = {{DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2024},
  doi = {10.15607/RSS.2024.XX.043},
}

@misc{malate_smooth_2026,
  title = {Smooth {Operator}: {A} {Real}-{Time} {Sampling}-{Based} {Algorithm} for {Kinematic} {Hand} {Retargeting}},
  url = {https://arxiv.org/abs/2607.07491},
  publisher = {arXiv},
  author = {Malate, Robert Jomar and Bauer, Erik and Bacuieti, Norica and Charalambous, Stefanos and Nava, Elvis and Katzschmann, Robert K. and Forrai, Benedek},
  year = {2026},
}

@misc{wu_toporetarget_2026,
  title = {{TopoRetarget}: {Interaction}-{Preserving} {Retargeting} for {Dexterous} {Manipulation}},
  url = {https://arxiv.org/abs/2606.16272},
  publisher = {arXiv},
  author = {Wu, Jielin and Yao, Shenzhe and He, Guanqi and Liu, Xiaohan and Zeng, Zhaoqing and Jiang, Xiangrui and Yang, Han and Zhang, Wentao and Zhao, Hang},
  year = {2026},
}

@misc{lai_objretarget_2026,
  title = {{ObjRetarget}: {An} {Object}-{Aware} {Motion} {Retargeting} {Framework} with {Anthropomorphic} {Arm} {Constraints} and {Polyhedral} {Hand} {Modeling}},
  url = {https://arxiv.org/abs/2607.03828},
  publisher = {arXiv},
  author = {Lai, Yuanchuan and Gao, Qing and Liang, Ziyan and Hu, Junjie and Ju, Zhaojie},
  year = {2026},
}

@misc{ren_c2dex_2026,
  title = {{C2Dex}: {Contact}-{Consistent} {Reconstruction} and {Retargeting} for {Dexterous} {Manipulation} from {Monocular} {Video}},
  url = {https://arxiv.org/abs/2608.07045},
  publisher = {arXiv},
  author = {Ren, Jie and Jiang, Zhehao and Yang, Yinhong and Jia, Haorui and Jiang, Han and Li, Ben and Yao, Yao and Lin, Cheng and Shen, Qiu and Bing, Zhenshan and Long, Xiao-Xiao and Cao, Xun},
  year = {2026},
}

@misc{pan_spider_2026,
  title = {{SPIDER}: {Scalable} {Physics}-{Informed} {Dexterous} {Retargeting}},
  url = {http://arxiv.org/abs/2511.09484},
  publisher = {arXiv},
  author = {Pan, Chaoyi and Wang, Changhao and Qi, Haozhi and Liu, Zixi and Bharadhwaj, Homanga and Sharma, Akash and Wu, Tingfan and Shi, Guanya and Malik, Jitendra and Hogan, Francois},
  year = {2026},
}

@misc{paliwal_as_2026,
  title = {Do as {I} {Do}: {Dexterous} {Manipulation} {Data} from {Everyday} {Human} {Videos}},
  url = {http://arxiv.org/abs/2606.19333},
  publisher = {arXiv},
  author = {Paliwal, Bhawna and Etukuru, Haritheja and Liang, William and Abbeel, Pieter and Shafiullah, Nur Muhammad Mahi and Malik, Jitendra},
  year = {2026},
}

@misc{chen_dexterous_2026,
  title = {Dexterous {Manipulation} {Policies} from {RGB} {Human} {Videos} via {3D} {Hand}-{Object} {Trajectory} {Reconstruction}},
  url = {https://arxiv.org/abs/2602.09013},
  publisher = {arXiv},
  author = {Chen, Hongyi and Dong, Tony and Wu, Tiancheng and Wang, Liquan and Jangir, Yash and Niu, Yaru and Ye, Yufei and Bharadhwaj, Homanga and Erickson, Zackory and Ichnowski, Jeffrey},
  year = {2026},
}

@misc{mu_deximit_2026,
  author = {Juncheng Mu AND Sizhe Yang AND Yiming Bao AND Hojin Bae AND Tianming Wei AND Linning Xu AND Boyi Li AND Huazhe Xu AND Jiangmiao Pang},
  title = {{DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2026},
  doi = {10.15607/RSS.2026.XXII.003},
}

@misc{chen_vividex_2025,
  author = {Chen, Zerui and Chen, Shizhe and Arlaud, Etienne and Laptev, Ivan and Schmid, Cordelia},
  booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {ViViDex: Learning Vision-Based Dexterous Manipulation from Human Videos},
  year = {2025},
  volume = {},
  pages = {3336-3343},
  doi = {10.1109/ICRA55743.2025.11127358},
}

@article{kerr_robot_nodate,
  title = {Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction},
  author = {Kerr, Justin and Kim, Chung Min and Wu, Mingxuan and Yi, Brent and Wang, Qianqian and Goldberg, Ken and Kanazawa, Angjoo},
  booktitle = {Proceedings of The 8th Conference on Robot Learning},
  pages = {587--603},
  year = {2025},
  volume = {270},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v270/kerr25a.html},
}

@misc{mandi_dexmachina_2025,
  title = {{DexMachina}: {Functional} {Retargeting} for {Bimanual} {Dexterous} {Manipulation}},
  url = {http://arxiv.org/abs/2505.24853},
  publisher = {arXiv},
  author = {Mandi, Zhao and Hou, Yifan and Fox, Dieter and Narang, Yashraj and Mandlekar, Ajay and Song, Shuran},
  year = {2025},
}

@misc{freeman_warped_2026,
  title = {{WARPED}: {Wrist}-{Aligned} {Rendering} for {Robot} {Policy} {Learning} from {Egocentric} {Human} {Demonstrations}},
  url = {http://arxiv.org/abs/2604.10809},
  publisher = {arXiv},
  author = {Freeman, Harry and Kim, Chung Hee and Kantor, George},
  year = {2026},
}

@misc{lepert_phantom_2026,
  title = {Phantom: {Training} {Robots} {Without} {Robots} {Using} {Only} {Human} {Videos}},
  url = {http://arxiv.org/abs/2503.00779},
  publisher = {arXiv},
  author = {Lepert, Marion and Fang, Jiaying and Bohg, Jeannette},
  year = {2026},
}

@misc{lepert_masquerade_2025,
  title = {Masquerade: {Learning} from {In}-the-wild {Human} {Videos} using {Data}-{Editing}},
  url = {http://arxiv.org/abs/2508.09976},
  publisher = {arXiv},
  author = {Lepert, Marion and Fang, Jiaying and Bohg, Jeannette},
  year = {2025},
}

@misc{liu_egoengine_2026,
  title = {{EgoEngine}: {From} {Egocentric} {Human} {Videos} to {High}-{Fidelity} {Dexterous} {Robot} {Demonstrations}},
  url = {https://arxiv.org/abs/2606.12604},
  publisher = {arXiv},
  author = {Liu, Yangcen and Cheng, Shuo and Yin, Xinchen and Shin, Woo Chul and Cueva, Alfred and Yang, Yiran and Chen, Zhenyang and Zhang, Chuye and Xu, Danfei},
  year = {2026},
}

@misc{kolomiets_agenticfocus_2026,
  title = {{AgenticFocus}: {Object}-{Preserving} {Mixed} {Reality} {Synthesis} from {Human} {FPV} {Video} for {Dexterous} {Humanoid} {Learning}},
  url = {http://arxiv.org/abs/2607.08857},
  publisher = {arXiv},
  author = {Kolomiets, Iaroslav and Cabrera, Miguel Altamirano and Lykov, Artem and Sam, Jeffrin and Iarchuk, Dmitrii and Mahmoud, Yara and Zinniatullina, Daniia and Konenkov, Mikhail and Tsetserukou, Dzmitry},
  year = {2026},
}

@misc{fan_robopaint_2026,
  title = {{RoboPaint}: {From} {Human} {Demonstration} to {Any} {Robot} and {Any} {View}},
  url = {http://arxiv.org/abs/2602.05325},
  publisher = {arXiv},
  author = {Fan, Jiacheng and Zhao, Zhiyue and Zhang, Yiqian and Chen, Chao and Wang, Peide and Zhang, Hengdi and Cheng, Zhengxue},
  year = {2026},
}

@misc{wang_ego2robot_2026,
  title = {{Ego2Robot}: {Scalable} {Robot} {Data} {Synthesis} from {Egocentric} {Human} {Data}},
  url = {http://arxiv.org/abs/2608.02580},
  publisher = {arXiv},
  author = {Wang, Ye and Lin, Pei and Chen, Xiong-Hui and Yuan, Haoqi and Liang, Zhixuan and Huang, Yiyang and Chen, Anzhe and Lei, Zixing and Zhang, Jie and Zhang, Tao and Li, Haoyang and Zhang, Tong and Xiao, Chenxi and Jiao, Ziyuan and Jin, Qin},
  year = {2026},
}

@misc{ren_motion_2025,
  author = {Ren, Juntao and Sundaresan, Priya and Sadigh, Dorsa and Choudhury, Sanjiban and Bohg, Jeannette},
  booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learning},
  year = {2025},
  volume = {},
  pages = {8802-8810},
  doi = {10.1109/ICRA55743.2025.11128834},
}

@misc{wen2024anypointtrajectorymodelingpolicy,
  title = {Any-point Trajectory Modeling for Policy Learning},
  author = {Chuan Wen and Xingyu Lin and John So and Kai Chen and Qi Dou and Yang Gao and Pieter Abbeel},
  year = {2024},
  eprint = {2401.00025},
  url = {https://arxiv.org/abs/2401.00025},
}

@misc{bharadhwaj2024track2actpredictingpointtracks,
  title = {Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation},
  author = {Homanga Bharadhwaj and Roozbeh Mottaghi and Abhinav Gupta and Shubham Tulsiani},
  year = {2024},
  eprint = {2405.01527},
  url = {https://arxiv.org/abs/2405.01527},
}

@ARTICLE{ma_unihand_2026,
  author = {Ma, Junyi and Bao, Wentao and Xu, Jingyi and Sun, Guanzhong and Zheng, Yu and Zhang, Erhang and Chen, Xieyuanli and Wang, Hesheng},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title = {Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views},
  year = {2026},
  volume = {48},
  pages = {11758-11775},
  doi = {10.1109/TPAMI.2026.3692504},
}

@misc{yuan_motiontrans_2025,
  title = {{MotionTrans}: {Human} {VR} {Data} {Enable} {Motion}-{Level} {Learning} for {Robotic} {Manipulation} {Policies}},
  url = {http://arxiv.org/abs/2509.17759},
  publisher = {arXiv},
  author = {Yuan, Chengbo and Zhou, Rui and Liu, Mengzhen and Hu, Yingdong and Wang, Shengjie and Yi, Li and Wen, Chuan and Zhang, Shanghang and Gao, Yang},
  year = {2025},
}

@misc{tang_functo_2025,
  title = {{FUNCTO}: {Function}-{Centric} {One}-{Shot} {Imitation} {Learning} for {Tool} {Manipulation}},
  url = {http://arxiv.org/abs/2502.11744},
  publisher = {arXiv},
  author = {Tang, Chao and Xiao, Anxing and Deng, Yuhong and Hu, Tianrun and Dong, Wenlong and Zhang, Hanbo and Hsu, David and Zhang, Hong},
  year = {2025},
}

@misc{cheng_human2any_2026,
  title = {{Human2Any}: {Human}-to-{Robot} {Transfer} via {Constraint}-{Aware} {Compositional} {Planning}},
  url = {http://arxiv.org/abs/2606.28813},
  publisher = {arXiv},
  author = {Cheng, Shuo and Zhang, Chuye and Cueva, Alfred and Garrett, Caelan and Mandlekar, Ajay and Xu, Danfei},
  year = {2026},
}

@misc{wang_humanego_2026,
  title = {{HumanEgo}: {Zero}-{Shot} {Robot} {Learning} from {Minutes} of {Human} {Egocentric} {Videos}},
  url = {http://arxiv.org/abs/2605.24934},
  publisher = {arXiv},
  author = {Wang, Zhi and He, Botao and Yu, Kelin and Lee, Seungjae and Gao, Ruohan and Huang, Furong and Aloimonos, Yiannis},
  year = {2026},
}

@misc{yang_egovla_2025,
  title = {{EgoVLA}: {Learning} {Vision}-{Language}-{Action} {Models} from {Egocentric} {Human} {Videos}},
  url = {http://arxiv.org/abs/2507.12440},
  publisher = {arXiv},
  author = {Yang, Ruihan and Yu, Qinxi and Wu, Yecheng and Yan, Rui and Li, Borui and Cheng, An-Chieh and Zou, Xueyan and Fang, Yunhao and Cheng, Xuxin and Qiu, Ri-Zhao and Yin, Hongxu and Liu, Sifei and Han, Song and Lu, Yao and Wang, Xiaolong},
  year = {2025},
}

@misc{li_scalable_2025,
  title = {Scalable {Vision}-{Language}-{Action} {Model} {Pretraining} for {Robotic} {Manipulation} with {Real}-{Life} {Human} {Activity} {Videos}},
  url = {http://arxiv.org/abs/2510.21571},
  publisher = {arXiv},
  author = {Li, Qixiu and Deng, Yu and Liang, Yaobo and Luo, Lin and Zhou, Lei and Yao, Chengtang and Zeng, Lingqi and Feng, Zhiyuan and Liang, Huizhi and Xu, Sicheng and Zhang, Yizhong and Chen, Xi and Chen, Hao and Sun, Lily and Chen, Dong and Yang, Jiaolong and Guo, Baining},
  year = {2025},
}

@misc{luo_being-h0_2025,
  title = {Being-{H0}: {Vision}-{Language}-{Action} {Pretraining} from {Large}-{Scale} {Human} {Videos}},
  url = {http://arxiv.org/abs/2507.15597},
  publisher = {arXiv},
  author = {Luo, Hao and Feng, Yicheng and Zhang, Wanpeng and Zheng, Sipeng and Wang, Ye and Yuan, Haoqi and Liu, Jiazheng and Xu, Chaoyi and Jin, Qin and Lu, Zongqing},
  year = {2025},
}

@misc{qiu_humanoid_2025,
  title = {Humanoid {Policy} {\textasciitilde} {Human} {Policy}},
  url = {https://arxiv.org/abs/2503.13441},
  publisher = {arXiv},
  author = {Qiu, Ri-Zhao and Yang, Shiqi and Cheng, Xuxin and Chawla, Chaitanya and Li, Jialong and He, Tairan and Yan, Ge and Yoon, David J. and Hoque, Ryan and Paulsen, Lars and Yang, Ge and Zhang, Jian and Yi, Sha and Shi, Guanya and Wang, Xiaolong},
  year = {2025},
}

@misc{cai_-n-_2025,
  title = {In-{N}-{On}: {Scaling} {Egocentric} {Manipulation} with in-the-wild and on-task {Data}},
  url = {https://arxiv.org/abs/2511.15704},
  publisher = {arXiv},
  author = {Cai, Xiongyi and Qiu, Ri-Zhao and Chen, Geng and Wei, Lai and Liu, Isabella and Huang, Tianshu and Cheng, Xuxin and Wang, Xiaolong},
  year = {2025},
}

@misc{yin_mivla_2025,
  title = {{MiVLA}: {Towards} {Generalizable} {Vision}-{Language}-{Action} {Model} with {Human}-{Robot} {Mutual} {Imitation} {Pre}-training},
  url = {https://arxiv.org/abs/2512.15411},
  publisher = {arXiv},
  author = {Yin, Zhenhan and Wang, Xuanhan and Jiang, Jiahao and Deng, Kaiyuan and Chen, Pengqi and Li, Shuangle and Liu, Chong and Xu, Xing and Song, Jingkuan and Gao, Lianli and Shen, Heng Tao},
  year = {2025},
}

@misc{luo_being-h05_2026,
  title = {Being-{H0}.5: {Scaling} {Human}-{Centric} {Robot} {Learning} for {Cross}-{Embodiment} {Generalization}},
  url = {http://arxiv.org/abs/2601.12993},
  publisher = {arXiv},
  author = {Luo, Hao and Wang, Ye and Zhang, Wanpeng and Zheng, Sipeng and Xi, Ziheng and Xu, Chaoyi and Xu, Haiweng and Yuan, Haoqi and Zhang, Chi and Wang, Yiqing and Feng, Yicheng and Lu, Zongqing},
  year = {2026},
}

@misc{li_ace-ego-0_2026,
  title = {{ACE}-{Ego}-0: {Unifying} {Egocentric} {Human} and {Robotic} {Data} for {VLA} {Pretraining}},
  url = {http://arxiv.org/abs/2606.17200},
  publisher = {arXiv},
  author = {Li, Hao and Zhao, Ganlong and Liu, Yufei and Hou, Haotian and Ye, Guoquan and Fang, Tongyan and Liu, Chunxiao and Huang, Siyuan and Liu, Jianbo and Wang, Xiaogang and Li, Hongsheng},
  year = {2026},
}

@misc{zhang_unidex_2026,
  title = {{UniDex}: {A} {Robot} {Foundation} {Suite} for {Universal} {Dexterous} {Hand} {Control} from {Egocentric} {Human} {Videos}},
  url = {http://arxiv.org/abs/2603.22264},
  publisher = {arXiv},
  author = {Zhang, Gu and Xu, Qicheng and Zhang, Haozhe and Ma, Jianhan and He, Long and Bao, Yiming and Ping, Zeyu and Yuan, Zhecheng and Lu, Chenhao and Yuan, Chengbo and Liang, Tianhai and Tian, Xiaoyu and Shao, Maanping and Zhang, Feihong and Ding, Mingyu and Gao, Yang and Zhao, Hao and Zhao, Hang and Xu, Huazhe},
  year = {2026},
}

@misc{yuan2026qwenrobotmaniptechnicalreportalignment,
  title = {Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models},
  author = {Haoqi Yuan and Zhixuan Liang and Anzhe Chen and Ye Wang and Haoyang Li and Pei Lin and Yiyang Huang and Zixing Lei and Tong Zhang and Jiazhao Zhang and Jie Zhang and Jingyang Fan and Gengze Zhou and Qihang Peng and Chenxu Lv and Xiaoyue Chen and An Yang and Fei Huang and Junyang Lin and Dayiheng Liu and Jingren Zhou and Chenfei Wu and Xiong-Hui Chen},
  year = {2026},
  eprint = {2606.17846},
  url = {https://arxiv.org/abs/2606.17846},
}

@misc{huang2026zevaegoegocentricmidtrainingincontext,
  title = {Zeva-Ego: Egocentric Mid-Training with In-Context Causal Learning for Robot Manipulation},
  author = {Bingjia Huang and Xin Ding and Fu Chen and Kun Li and Wei Sun and Hao Wu and Yunxin Liu and Ting Cao},
  year = {2026},
  eprint = {2609.24411},
  url = {https://arxiv.org/abs/2609.24411},
}

@misc{punamiya_egobridge_2025,
  title = {{EgoBridge}: {Domain} {Adaptation} for {Generalizable} {Imitation} from {Egocentric} {Human} {Data}},
  url = {https://arxiv.org/abs/2509.19626},
  publisher = {arXiv},
  author = {Punamiya, Ryan and Patel, Dhruv and Aphiwetsa, Patcharapong and Kuppili, Pranav and Zhu, Lawrence Y. and Kareer, Simar and Hoffman, Judy and Xu, Danfei},
  year = {2025},
}

@InProceedings{yao_hammer_2026,
  author = {Yao, Lei and Chen, Yong and Su, Yuejiao and Wang, Yi and Liu, Moyun and Chau, Lap-Pui},
  title = {HAMMER: Harnessing MLLMs via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  pages = {23805-23815},
}

@misc{so100_grasp_cup,
  title = {Mtitg/so100\_grasp\_cup},
  url = {https://huggingface.co/datasets/mtitg/so100_grasp_cup},
  journal = {Datasets at Hugging Face},
  author = {Tanigaki, Motoi},
}

@misc{han_fsag_2026,
  title = {{FSAG}: {Enhancing} {Human}-to-{Dexterous}-{Hand} {Finger}-{Specific} {Affordance} {Grounding} via {Diffusion} {Models}},
  url = {http://arxiv.org/abs/2601.08246},
  publisher = {arXiv},
  author = {Han, Yifan and Peng, Yichuan and Yi, Pengfei and Li, Junyan and Wang, Hanqing and Zhang, Gaojing and Liu, Qi Peng and Lian, Wenzhao},
  year = {2026},
}

@misc{xiao_robopca_2026,
  title = {{RoboPCA}: {Pose}-centered {Affordance} {Learning} from {Human} {Demonstrations} for {Robot} {Manipulation}},
  url = {http://arxiv.org/abs/2603.07691},
  publisher = {arXiv},
  author = {Xiao, Zhanqi and Wang, Ruiping and Chen, Xilin},
  year = {2026},
}

@misc{chen_vidbot_2025,
  author = {Chen, Hanzhi and Sun, Boyang and Zhang, Anran and Pollefeys, Marc and Leutenegger, Stefan},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation},
  year = {2025},
  volume = {},
  pages = {27661-27672},
  doi = {10.1109/CVPR52734.2025.02576},
}

@misc{han_bridgeact_2026,
  title = {{BridgeACT}: {Bridging} {Human} {Demonstrations} to {Robot} {Actions} via {Unified} {Tool}-{Target} {Affordances}},
  url = {http://arxiv.org/abs/2604.23249},
  publisher = {arXiv},
  author = {Han, Yifan and Liu, Jianxiang and Zhang, Haoyu and Gu, Yuqi and Guo, Yunhan and Lian, Wenzhao},
  year = {2026},
}

@inproceedings{srirama_hrp_2024,
  author = {Mohan Kumar Srirama AND Sudeep Dasari AND Shikhar Bahl AND Abhinav Gupta},
  title = {{HRP: Human affordances for Robotic Pre-training}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2024},
  doi = {10.15607/RSS.2024.XX.068},
}

@misc{chen_dexmani_2026,
  title = {{DexMani}: {Human}-{Derived} {Manipulability} {Guidance} for {Dexterous} {Rotation}},
  url = {http://arxiv.org/abs/2608.00554},
  publisher = {arXiv},
  author = {Chen, Xiaoyang and Luo, Shengcheng and Guo, Haoran and Jiang, Jiaming and Li, Wanlin and Jiao, Ziyuan and Xiao, Chenxi},
  year = {2026},
}

@inproceedings{bahl_affordances_2023,
  author = {Bahl, Shikhar and Mendonca, Russell and Chen, Lili and Jain, Unnat and Pathak, Deepak},
  booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Affordances from Human Videos as a Versatile Representation for Robotics},
  year = {2023},
  volume = {},
  pages = {01-13},
  doi = {10.1109/CVPR52729.2023.01324},
}

@inproceedings{bharadhwaj_visual_2023,
  author = {Bharadhwaj, Homanga and Gupta, Abhinav and Tulsiani, Shubham},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {Visual Affordance Prediction for Guiding Robot Exploration},
  year = {2023},
  volume = {},
  pages = {3029-3036},
  doi = {10.1109/ICRA48891.2023.10161288},
}

@inproceedings{borja-diaz_affordance_2022,
  author = {Borja-Diaz, Jessica and Mees, Oier and Kalweit, Gabriel and Hermann, Lukas and Boedecker, Joschka and Burgard, Wolfram},
  booktitle = {2022 International Conference on Robotics and Automation (ICRA)},
  title = {Affordance Learning from Play for Sample-Efficient Policy Learning},
  year = {2022},
  volume = {},
  pages = {6372-6378},
  doi = {10.1109/ICRA46639.2022.9811889},
}

@misc{mees_grounding_2023,
  author = {Mees, Oier and Borja-Diaz, Jessica and Burgard, Wolfram},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {Grounding Language with Visual Affordances over Unstructured Data},
  year = {2023},
  volume = {},
  pages = {11576-11582},
  doi = {10.1109/ICRA48891.2023.10160396},
}

@misc{liu_affordance2action_2026,
  title = {{Affordance2Action}: {Task}-{Conditioned} {Scene}-level {Affordance} {Grounding} for {Real}-{Time} {Manipulation}},
  url = {http://arxiv.org/abs/2606.04172},
  publisher = {arXiv},
  author = {Liu, Litao and Han, Yifan and Yi, Pengfei and Yu, Wenbo and Wang, Hanqing and Du, Haoran and Yuan, Enze and Yuan, Zilin and Feng, Ruiding and Liu, Michael and Zhang, Qi and Yu, Jingjin},
  year = {2026},
}

@misc{punamiya_egoverse_2026,
  author = {Ryan Punamiya AND Simar Kareer AND Zeyi Liu AND Joshua Citron AND Ri-Zhao Qiu AND Xiongyi Cai AND Alexey Gavryushin AND Jiaqi Chen AND Davide Liconti AND Lawrence Y. Zhu AND Patcharapong Aphiwetsa AND Baoyu Li AND Aniketh Cheluva AND Pranav Kuppili AND Yangcen Liu AND Dhruv Patel AND Aidan Gao AND Ryan Co AND Hye-Young Chung AND Renee Zbizika AND Jinyun Liu AND Xiaomeng Xu AND Haoyu Xiong AND Geng Chen AND Sebastiano Oliani AND Wenkai Xuan AND Chenyu Yang AND Xi Wang AND James Fort AND Richard Newcombe AND Josh Gao AND Jason Chong AND Garrett Matsuda AND Aseem Doriwala AND Robert K. Katzschmann AND Marc Pollefeys AND Xiaolong Wang AND Shuran Song AND Judy Hoffman AND Danfei Xu},
  title = {{EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2026},
  doi = {10.15607/RSS.2026.XXII.092},
}

@inproceedings{chen_learning_2021,
  author = {Annie S. Chen AND Suraj Nair AND Chelsea Finn},
  title = {{Learning Generalizable Robotic Reward Functions from “In-The-Wild” Human Videos}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2021},
  doi = {10.15607/RSS.2021.XVII.012},
}

@misc{zakka2021xirlcrossembodimentinversereinforcement,
  title = {XIRL: Cross-embodiment Inverse Reinforcement Learning},
  author = {Kevin Zakka and Andy Zeng and Pete Florence and Jonathan Tompson and Jeannette Bohg and Debidatta Dwibedi},
  year = {2021},
  eprint = {2106.03911},
  url = {https://arxiv.org/abs/2106.03911},
}

@misc{yang2024rank2rewardlearningshapedreward,
  title = {Rank2Reward: Learning Shaped Reward Functions from Passive Video},
  author = {Daniel Yang and Davin Tjia and Jacob Berg and Dima Damen and Pulkit Agrawal and Abhishek Gupta},
  year = {2024},
  eprint = {2404.14735},
  url = {https://arxiv.org/abs/2404.14735},
}

@misc{ma_vip_2023,
  title = {{VIP}: {Towards} {Universal} {Visual} {Reward} and {Representation} via {Value}-{Implicit} {Pre}-{Training}},
  url = {http://arxiv.org/abs/2210.00030},
  publisher = {arXiv},
  author = {Ma, Yecheng Jason and Sodhani, Shagun and Jayaraman, Dinesh and Bastani, Osbert and Kumar, Vikash and Zhang, Amy},
  year = {2023},
}

@misc{ma_liv_2023,
  title = {{LIV}: {Language}-{Image} {Representations} and {Rewards} for {Robotic} {Control}},
  url = {http://arxiv.org/abs/2306.00958},
  publisher = {arXiv},
  author = {Ma, Yecheng Jason and Liang, William and Som, Vaidehi and Kumar, Vikash and Zhang, Amy and Bastani, Osbert and Jayaraman, Dinesh},
  year = {2023},
}

@incollection{huang_diffusion_2024,
  author = {Huang, Tao
    and Jiang, Guangqi
    and Ze, Yanjie
    and Xu, Huazhe},
  title = {Diffusion Reward: Learning Rewards via Conditional Video Diffusion},
  booktitle = {Computer Vision -- ECCV 2024},
  year = {2025},
  publisher = {Springer Nature Switzerland},
  pages = {478--495},
  url = {https://arxiv.org/abs/2312.14134},
}

@misc{verghese_human_2026,
  title = {Human {Preference} {Modeling} {Using} {Visual} {Motion} {Prediction} {Improves} {Robot} {Skill} {Learning} from {Egocentric} {Human} {Video}},
  url = {http://arxiv.org/abs/2602.11393},
  publisher = {arXiv},
  author = {Verghese, Mrinal and Atkeson, Christopher G.},
  year = {2026},
}

@misc{dan_x-sim_2025,
  title = {X-{Sim}: {Cross}-{Embodiment} {Learning} via {Real}-to-{Sim}-to-{Real}},
  url = {https://arxiv.org/abs/2505.07096},
  publisher = {arXiv},
  author = {Dan, Prithwish and Kedia, Kushal and Chao, Angela and Duan, Edward Weiyi and Pace, Maximus Adrian and Ma, Wei-Chiu and Choudhury, Sanjiban},
  year = {2025},
}

@inproceedings{smith_avid_2020,
  author = {Laura Smith AND Nikita Dhawan AND Marvin Zhang AND Pieter Abbeel AND Sergey Levine},
  title = {{AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2020},
  doi = {10.15607/RSS.2020.XVI.024},
}

@misc{wang_vlm_2024,
  author = {Wang, Beichen and Zhang, Juexiao and Dong, Shuwen and Fang, Irving and Feng, Chen},
  booktitle = {2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model},
  year = {2025},
  volume = {},
  pages = {17215-17222},
  doi = {10.1109/IROS60139.2025.11246682},
}

@misc{ma_egoloc_2025,
  author = {Ma, Junyi and Zhang, Erhang and Zheng, Yin-Dong and Xie, Yuchen and Zhou, Yixuan and Wang, Hesheng},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  title = {EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos},
  year = {2026},
  volume = {},
  pages = {1-18},
  doi = {10.1109/TPAMI.2026.3717912},
}

@misc{liang_robometer_2026,
  author = {Anthony Liang AND Yigit Korkmaz AND Jiahui Zhang AND Minyoung Hwang AND Abrar Anwar AND Sidhant Kaushik AND Aditya Shah AND Alex S. Huang AND Luke Zettlemoyer AND Dieter Fox AND Yu Xiang AND Anqi Li AND Andreea Bobu AND Abhishek Gupta AND Stephen Tu AND Erdem Biyik AND Jesse Zhang},
  title = {{Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2026},
  doi = {10.15607/RSS.2026.XXII.140},
}

@misc{feng_procvlm_2026,
  title = {{ProcVLM}: {Learning} {Procedure}-{Grounded} {Progress} {Rewards} for {Robotic} {Manipulation}},
  url = {http://arxiv.org/abs/2605.08774},
  publisher = {arXiv},
  author = {Feng, Youhe and Shi, Hansen and Li, Haoyang and Guo, Xinlei and Wang, Yang and Zhang, Chengyang and Zhang, Jinkai and Zhang, Xiaohan and Tang, Jie and Zhang, Jing},
  year = {2026},
}

@misc{huang_rynnvalue_2026,
  title = {{RynnValue}: {Scaling} {Robotic} {Value} {Foundation} {Models} with {Temporal} {Distance}},
  url = {http://arxiv.org/abs/2608.09853},
  publisher = {arXiv},
  author = {Huang, Dongchi and Zhang, Hongyin and Hou, Bohan and Huang, Siteng and Su, Zhian and Guo, Hang and Lu, Tong and Xu, Zhaofeng and Tang, Jiahao and Yang, Jianfei and Wang, Donglin and Peng, Peixi and Chen, Mingxiu and Zhao, Deli and Li, Xin},
  year = {2026},
}

@misc{wu_large_2026,
  title = {Large {Reward} {Models}: {Generalizable} {Online} {Robot} {Reward} {Generation} with {Vision}-{Language} {Models}},
  url = {http://arxiv.org/abs/2603.16065},
  publisher = {arXiv},
  author = {Wu, Yanru and Yuan, Weiduo and Qi, Ang and Guizilini, Vitor and Mao, Jiageng and Wang, Yue},
  year = {2026},
}

@misc{zhang_prts_2026,
  title = {{PRTS}: {A} {Primitive} {Reasoning} and {Tasking} {System} via {Contrastive} {Representations}},
  url = {http://arxiv.org/abs/2604.27472},
  publisher = {arXiv},
  author = {Zhang, Yang and Zhao, Jiangyuan and Fan, Chenyou and Yan, Fangzheng and Li, Tian and Tang, Haitong and Fu, Sen and Wu, Xuan'er and Weng, Qizhen and Zhang, Weinan and Li, Xiu and Zhang, Chi and Bai, Chenjia and Li, Xuelong},
  year = {2026},
}

@misc{sa_valueformer_2026,
  title = {ValueFormer: Stage-Aware Value Labels for Online Failure Detection and VLA Post-Training},
  author = {Inkyu Sa and Konstantin Stulov and Rajat Bhageria},
  year = {2026},
  eprint = {2608.02958},
  url = {https://arxiv.org/abs/2608.02958},
}

@misc{shang_theia_2024,
  title = {Theia: {Distilling} {Diverse} {Vision} {Foundation} {Models} for {Robot} {Learning}},
  url = {http://arxiv.org/abs/2407.20179},
  publisher = {arXiv},
  author = {Shang, Jinghuan and Schmeckpeper, Karl and May, Brandon B. and Minniti, Maria Vittoria and Kelestemur, Tarik and Watkins, David and Herlant, Laura},
  year = {2024},
}

@misc{shao_x-distill_2026,
  author = {Shao, Maanping and Zhang, Feihong and Zhang, Gu and Cheng, Baiye and Xue, Zhengrong and Xu, Huazhe},
  journal = {IEEE Robotics and Automation Letters},
  title = {X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning},
  year = {2026},
  volume = {11},
  pages = {10672-10679},
  doi = {10.1109/LRA.2026.3711479},
}

@inproceedings{fang_rh20t_2024,
  author = {Fang, Hao-Shu and Fang, Hongjie and Tang, Zhenyu and Liu, Jirong and Wang, Chenxi and Wang, Junbo and Zhu, Haoyi and Lu, Cewu},
  booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot},
  year = {2024},
  volume = {},
  pages = {653-660},
  doi = {10.1109/ICRA57147.2024.10611615},
}

@misc{sermanet_time-contrastive_2018,
  author = {Sermanet, Pierre and Lynch, Corey and Chebotar, Yevgen and Hsu, Jasmine and Jang, Eric and Schaal, Stefan and Levine, Sergey and Brain, Google},
  booktitle = {2018 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {Time-Contrastive Networks: Self-Supervised Learning from Video},
  year = {2018},
  volume = {},
  pages = {1134-1141},
  doi = {10.1109/ICRA.2018.8462891},
}

@inproceedings{dwibedi_temporal_2019,
  author = {Dwibedi, Debidatta and Aytar, Yusuf and Tompson, Jonathan and Sermanet, Pierre and Zisserman, Andrew},
  booktitle = {2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Temporal Cycle-Consistency Learning},
  year = {2019},
  volume = {},
  pages = {1801-1810},
  doi = {10.1109/CVPR.2019.00190},
}

@misc{zhang_provable_2025,
  title = {Provable {Ordering} and {Continuity} in {Vision}-{Language} {Pretraining} for {Generalizable} {Embodied} {Agents}},
  url = {http://arxiv.org/abs/2502.01218},
  publisher = {arXiv},
  author = {Zhang, Zhizhen and Zhu, Lei and Fang, Zhen and Huang, Zi and Luo, Yadan},
  year = {2025},
}

@misc{xiong2025ag2x2robustagentagnosticvisual,
  title = {Ag2x2: Robust Agent-Agnostic Visual Representations for Zero-Shot Bimanual Manipulation},
  author = {Ziyin Xiong and Yinghan Chen and Puhao Li and Yixin Zhu and Tengyu Liu and Siyuan Huang},
  year = {2025},
  eprint = {2507.19817},
  url = {https://arxiv.org/abs/2507.19817},
}

@ARTICLE{9084270,
  author = {Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria and Fidler, Sanja and Furnari, Antonino and Kazakos, Evangelos and Moltisanti, Davide and Munro, Jonathan and Perrett, Toby and Price, Will and Wray, Michael},
  journal = {IEEE Transactions on Pattern Analysis \& Machine Intelligence},
  title = {{ The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines }},
  year = {2021},
  volume = {43},
  pages = {4125-4141},
  doi = {10.1109/TPAMI.2020.2991965},
  url = {https://doi.ieeecomputersociety.org/10.1109/TPAMI.2020.2991965},
  publisher = {IEEE Computer Society},
}

@inproceedings{he_masked_2021,
  author = {He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Dollár, Piotr and Girshick, Ross},
  booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Masked Autoencoders Are Scalable Vision Learners},
  year = {2022},
  volume = {},
  pages = {15979-15988},
  doi = {10.1109/CVPR52688.2022.01553},
}

@misc{radosavovic_real-world_2022,
  title = {Real-{World} {Robot} {Learning} with {Masked} {Visual} {Pre}-training},
  url = {http://arxiv.org/abs/2210.03109},
  publisher = {arXiv},
  author = {Radosavovic, Ilija and Xiao, Tete and James, Stephen and Abbeel, Pieter and Malik, Jitendra and Darrell, Trevor},
  year = {2022},
}

@inproceedings{majumdar_where_2023,
  author = {Majumdar, Arjun and Yadav, Karmesh and Arnaud, Sergio and Ma, Jason and Chen, Claire and Silwal, Sneha and Jain, Aryan and Berges, Vincent-Pierre and Wu, Tingfan and Vakil, Jay and Abbeel, Pieter and Malik, Jitendra and Batra, Dhruv and Lin, Yixin and Maksymets, Oleksandr and Rajeswaran, Aravind and Meier, Franziska},
  booktitle = {Advances in Neural Information Processing Systems},
  doi = {10.52202/075280-0031},
  pages = {655--677},
  publisher = {Curran Associates, Inc.},
  title = {Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?},
  volume = {36},
  year = {2023},
}

@misc{yang_self-supervised_2022,
  title = {Self-supervised {Video} {Representation} {Learning} with {Motion}-{Aware} {Masked} {Autoencoders}},
  url = {http://arxiv.org/abs/2210.04154},
  publisher = {arXiv},
  author = {Yang, Haosen and Huang, Deng and Wen, Bin and Wu, Jiannan and Yao, Hongxun and Jiang, Yi and Zhu, Xiatian and Yuan, Zehuan},
  year = {2022},
}

@misc{yang_spatiotemporal_2024,
  title = {Spatiotemporal {Predictive} {Pre}-training for {Robotic} {Motor} {Control}},
  url = {http://arxiv.org/abs/2403.05304},
  publisher = {arXiv},
  author = {Yang, Jiange and Liu, Bei and Fu, Jianlong and Pan, Bocheng and Wu, Gangshan and Wang, Limin},
  year = {2024},
}

@misc{qian_3d-mvp_2025,
  author = {Qian, Shengyi and Mo, Kaichun and Blukis, Valts and Fouhey, David F. and Fox, Dieter and Goyal, Ankit},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {3D-MVP: 3D Multiview Pretraining for Manipulation},
  year = {2025},
  volume = {},
  pages = {22530-22539},
  doi = {10.1109/CVPR52734.2025.02098},
}

@misc{dong_embodiedmae_2025,
  title = {{EmbodiedMAE}: {A} {Unified} {3D} {Multi}-{Modal} {Representation} for {Robot} {Manipulation}},
  url = {http://arxiv.org/abs/2505.10105},
  publisher = {arXiv},
  author = {Dong, Zibin and Ni, Fei and Yuan, Yifu and Li, Yinchuan and Hao, Jianye},
  year = {2025},
}

@misc{lin_egocentric_2022,
  title = {Egocentric {Video}-{Language} {Pretraining}},
  url = {http://arxiv.org/abs/2206.01670},
  publisher = {arXiv},
  author = {Lin, Kevin Qinghong and Wang, Alex Jinpeng and Soldan, Mattia and Wray, Michael and Yan, Rui and Xu, Eric Zhongcong and Gao, Difei and Tu, Rongcheng and Zhao, Wenzhe and Kong, Weijie and Cai, Chengfei and Wang, Hongfa and Damen, Dima and Ghanem, Bernard and Liu, Wei and Shou, Mike Zheng},
  year = {2022},
}

@inproceedings{zhao_learning_2022,
  author = {Zhao, Yue and Misra, Ishan and Krähenbühl, Philipp and Girdhar, Rohit},
  booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Learning Video Representations from Large Language Models},
  year = {2023},
  volume = {},
  pages = {6586-6597},
  doi = {10.1109/CVPR52729.2023.00637},
}

@inproceedings{li_decisionnce_2024,
  author = {Li, Jianxiong and Zheng, Jinliang and Zheng, Yinan and Mao, Liyuan and Hu, Xiao and Cheng, Sijie and Niu, Haoyi and Liu, Jihao and Liu, Yu and Liu, Jingjing and Zhang, Ya-Qin and Zhan, Xianyuan},
  title = {DecisionNCE: embodied multimodal representations via implicit preference learning},
  year = {2024},
  publisher = {PMLR},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  url = {https://arxiv.org/abs/2402.18137},
}

@inproceedings{karamcheti_language-driven_2023,
  author = {Siddharth Karamcheti AND Suraj Nair AND Annie S Chen AND Thomas Kollar AND Chelsea Finn AND Dorsa Sadigh AND Percy Liang},
  title = {{Language-Driven Representation Learning for Robotics}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2023},
  doi = {10.15607/RSS.2023.XIX.032},
}

@INPROCEEDINGS{zeng_learning_2024,
  author = {Jia Zeng AND Qingwen Bu AND Bangjun Wang AND Wenke Xia AND Li Chen AND Hao Dong AND Haoming Song AND Dong Wang AND Di Hu AND Ping Luo AND Heming Cui AND Bin Zhao AND Xuelong Li AND Yu Qiao AND Hongyang Li},
  title = {{Learning Manipulation by Predicting Interaction}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2024},
  doi = {10.15607/RSS.2024.XX.123},
}

@misc{xu_egocentric_2025,
  title = {Do {Egocentric} {Video}-{Language} {Models} {Truly} {Understand} {Hand}-{Object} {Interactions}?},
  url = {http://arxiv.org/abs/2405.17719},
  publisher = {arXiv},
  author = {Xu, Boshen and Wang, Ziheng and Du, Yang and Song, Zhinan and Zheng, Sipeng and Jin, Qin},
  year = {2025},
}

@misc{xu_egodtm_2025,
  title = {{EgoDTM}: {Towards} {3D}-{Aware} {Egocentric} {Video}-{Language} {Pretraining}},
  url = {http://arxiv.org/abs/2503.15470},
  publisher = {arXiv},
  author = {Xu, Boshen and Mei, Yuting and Liu, Xinbi and Zheng, Sipeng and Jin, Qin},
  year = {2025},
}

@misc{wang_qwen-vla_2026,
  title = {Qwen-{VLA}: {Unifying} {Vision}-{Language}-{Action} {Modeling} across {Tasks}, {Environments}, and {Robot} {Embodiments}},
  url = {http://arxiv.org/abs/2605.30280},
  publisher = {arXiv},
  author = {Wang, Qiuyue and Li, Mingsheng and Guan, Jian and Ye, Jinhui and Xie, Sicheng and Liu, Yitao and Chen, Junhao and Liang, Zhixuan and Zhang, Jie and Hu, Xintong and Huang, Xuhong and Lin, Pei and Lin, Junyang and Liu, Dayiheng and Bai, Shuai and Zhou, Jingren and Zhang, Jiazhao and Yuan, Haoqi and Zhou, Gengze and Yin, Hang and Wang, Ye and Huang, Yiyang and Lei, Zixing and Peng, Wujian and Chen, Delin and Zheng, Yingming and Fan, Jingyang and Zhuang, Xianwei and Zhou, Xin and Li, Haoyang and Chen, Anzhe and Zhang, Tong and Liu, Xuejing and Sun, Yuchong and Chen, Ruizhe and Li, Zhaohai and Lü, Chenxu and Yang, Zhibo and Yu, Tao and Chen, Xionghui},
  year = {2026},
}

@misc{gao_dreamdojo_2026,
  title = {{DreamDojo}: {A} {Generalist} {Robot} {World} {Model} from {Large}-{Scale} {Human} {Videos}},
  url = {http://arxiv.org/abs/2602.06949},
  publisher = {arXiv},
  author = {Gao, Shenyuan and Liang, William and Zheng, Kaiyuan and Malik, Ayaan and Ye, Seonghyeon and Yu, Sihyun and Tseng, Wei-Cheng and Dong, Yuzhu and Mo, Kaichun and Lin, Chen-Hsuan and Ma, Qianli and Nah, Seungjun and Magne, Loic and Xiang, Jiannan and Xie, Yuqi and Zheng, Ruijie and Niu, Dantong and Tan, You Liang and Zentner, K. R. and Kurian, George and Indupuru, Suneel and Jannaty, Pooya and Gu, Jinwei and Zhang, Jun and Malik, Jitendra and Abbeel, Pieter and Liu, Ming-Yu and Zhu, Yuke and Jang, Joel and Fan, Linxi "Jim"},
  year = {2026},
}

@misc{schmidt2024learningactactions,
  title = {Learning to Act without Actions},
  author = {Dominik Schmidt and Minqi Jiang},
  year = {2024},
  eprint = {2312.10812},
  url = {https://arxiv.org/abs/2312.10812},
}

@misc{bruce2024geniegenerativeinteractiveenvironments,
  title = {Genie: Generative Interactive Environments},
  author = {Jake Bruce and Michael Dennis and Ashley Edwards and Jack Parker-Holder and Yuge Shi and Edward Hughes and Matthew Lai and Aditi Mavalankar and Richie Steigerwald and Chris Apps and Yusuf Aytar and Sarah Bechtle and Feryal Behbahani and Stephanie Chan and Nicolas Heess and Lucy Gonzalez and Simon Osindero and Sherjil Ozair and Scott Reed and Jingwei Zhang and Konrad Zolna and Jeff Clune and Nando de Freitas and Satinder Singh and Tim Rocktäschel},
  year = {2024},
  eprint = {2402.15391},
  url = {https://arxiv.org/abs/2402.15391},
}

@misc{chen2025motolatentmotiontoken,
  title = {Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos},
  author = {Yi Chen and Yuying Ge and Weiliang Tang and Yizhuo Li and Yixiao Ge and Mingyu Ding and Ying Shan and Xihui Liu},
  year = {2025},
  eprint = {2412.04445},
  url = {https://arxiv.org/abs/2412.04445},
}

@misc{chen_igor_2024,
  title = {{IGOR}: {Image}-{GOal} {Representations} are the {Atomic} {Control} {Units} for {Foundation} {Models} in {Embodied} {AI}},
  url = {http://arxiv.org/abs/2411.00785},
  publisher = {arXiv},
  author = {Chen, Xiaoyu and Guo, Junliang and He, Tianyu and Zhang, Chuheng and Zhang, Pushi and Yang, Derek Cathera and Zhao, Li and Bian, Jiang},
  year = {2024},
}

@misc{kim_uniskill_2025,
  title = {{UniSkill}: {Imitating} {Human} {Videos} via {Cross}-{Embodiment} {Skill} {Representations}},
  url = {http://arxiv.org/abs/2505.08787},
  publisher = {arXiv},
  author = {Kim, Hanjung and Kang, Jaehyun and Kang, Hyolim and Cho, Meedeum and Kim, Seon Joo and Lee, Youngwoon},
  year = {2025},
}

@misc{wang_mimicplay_2023,
  title = {{MimicPlay}: {Long}-{Horizon} {Imitation} {Learning} by {Watching} {Human} {Play}},
  url = {http://arxiv.org/abs/2302.12422},
  publisher = {arXiv},
  author = {Wang, Chen and Fan, Linxi and Sun, Jiankai and Zhang, Ruohan and Fei-Fei, Li and Xu, Danfei and Zhu, Yuke and Anandkumar, Anima},
  year = {2023},
}

@misc{collins_amplify_2025,
  title = {{AMPLIFY}: {Actionless} {Motion} {Priors} for {Robot} {Learning} from {Videos}},
  url = {http://arxiv.org/abs/2506.14198},
  publisher = {arXiv},
  author = {Collins, Jeremy A. and Cheng, Loránd and Aneja, Kunal and Wilcox, Albert and Joffe, Benjamin and Garg, Animesh},
  year = {2025},
}

@misc{bu2025univlalearningacttaskcentric,
  title = {UniVLA: Learning to Act Anywhere with Task-centric Latent Actions},
  author = {Qingwen Bu and Yanting Yang and Jisong Cai and Shenyuan Gao and Guanghui Ren and Maoqing Yao and Ping Luo and Hongyang Li},
  year = {2025},
  eprint = {2505.06111},
  url = {https://arxiv.org/abs/2505.06111},
}

@misc{lee_mvp-lam_2026,
  title = {{MVP}-{LAM}: {Learning} {Action}-{Centric} {Latent} {Action} via {Cross}-{Viewpoint} {Reconstruction}},
  url = {https://arxiv.org/abs/2602.03668},
  publisher = {arXiv},
  author = {Lee, Jung Min and Lee, Dohyeok and Ju, Seokhun and Cho, Taehyun and Koo, Jin Woo and Zhao, Li and Hong, Sangwoo and Lee, Jungwoo},
  year = {2026},
}

@misc{xu_motion-focused_2026,
  title = {Motion-{Focused} {Latent} {Action} {Enables} {Cross}-{Embodiment} {VLA} {Training} from {Human} {EgoVideos}},
  url = {http://arxiv.org/abs/2606.18955},
  publisher = {arXiv},
  author = {Xu, Runze and Zhang, Yiluo and Wang, Jian and Wang, Yu and Yu, Jincheng},
  year = {2026},
}

@misc{dai_conla_2026,
  title = {{ConLA}: {Contrastive} {Latent} {Action} {Learning} from {Human} {Videos} for {Robotic} {Manipulation}},
  url = {http://arxiv.org/abs/2602.00557},
  publisher = {arXiv},
  author = {Dai, Weisheng and Lan, Kai and Zhou, Jianyi and Zhao, Bo and Su, Xiu and Tong, Junwen and Guan, Weili and Yang, Shuo},
  year = {2026},
}

@misc{govind_unilact_2026,
  title = {{UniLACT}: {Depth}-{Aware} {RGB} {Latent} {Action} {Learning} for {Vision}-{Language}-{Action} {Models}},
  url = {http://arxiv.org/abs/2602.20231},
  publisher = {arXiv},
  author = {Govind, Manish Kumar and Reilly, Dominick and Wang, Pu and Das, Srijan},
  year = {2026},
}

@misc{nvidia2025gr00tn1openfoundation,
  title = {GR00T N1: An Open Foundation Model for Generalist Humanoid Robots},
  author = {NVIDIA and : and Johan Bjorck and Fernando Castañeda and Nikita Cherniadev and Xingye Da and Runyu Ding and Linxi "Jim" Fan and Yu Fang and Dieter Fox and Fengyuan Hu and Spencer Huang and Joel Jang and Zhenyu Jiang and Jan Kautz and Kaushil Kundalia and Lawrence Lao and Zhiqi Li and Zongyu Lin and Kevin Lin and Guilin Liu and Edith Llontop and Loic Magne and Ajay Mandlekar and Avnish Narayan and Soroush Nasiriany and Scott Reed and You Liang Tan and Guanzhi Wang and Zu Wang and Jing Wang and Qi Wang and Jiannan Xiang and Yuqi Xie and Yinzhen Xu and Zhenjia Xu and Seonghyeon Ye and Zhiding Yu and Ao Zhang and Hao Zhang and Yizhou Zhao and Ruijie Zheng and Yuke Zhu},
  year = {2025},
  eprint = {2503.14734},
  url = {https://arxiv.org/abs/2503.14734},
}

@misc{chen_villa-x_2025,
  title = {villa-{X}: {Enhancing} {Latent} {Action} {Modeling} in {Vision}-{Language}-{Action} {Models}},
  url = {http://arxiv.org/abs/2507.23682},
  publisher = {arXiv},
  author = {Chen, Xiaoyu and Wei, Hangxing and Zhang, Pushi and Zhang, Chuheng and Wang, Kaixin and Guo, Yanjiang and Yang, Rushuai and Wang, Yucen and Xiao, Xinquan and Zhao, Li and Chen, Jianyu and Bian, Jiang},
  year = {2025},
}

@misc{zhang_clap_2026,
  title = {{CLAP}: {Contrastive} {Latent} {Action} {Pretraining} for {Learning} {Vision}-{Language}-{Action} {Models} from {Human} {Videos}},
  url = {http://arxiv.org/abs/2601.04061},
  publisher = {arXiv},
  author = {Zhang, Chubin and Wang, Jianan and Gao, Zifeng and Su, Yue and Dai, Tianru and Zhou, Cai and Lu, Jiwen and Tang, Yansong},
  year = {2026},
}

@misc{zhu_harp-vla_2026,
  title = {{HARP}-{VLA}: {Human}-{Robot} {Aligned} {Representation} {Learning} for {Vision}-{Language}-{Action} {Model}},
  url = {https://arxiv.org/abs/2605.31234},
  publisher = {arXiv},
  author = {Zhu, Xiang and Yuan, Puzhen and Liu, Yichen and Chen, Jianyu},
  year = {2026},
}

@inproceedings{liu_hoi4d_2024,
  author = {Liu, Yunze and Liu, Yun and Jiang, Che and Lyu, Kangbo and Wan, Weikang and Shen, Hao and Liang, Boqiang and Fu, Zhoujie and Wang, He and Yi, Li},
  booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction},
  year = {2022},
  volume = {},
  pages = {20981-20990},
  doi = {10.1109/CVPR52688.2022.02034},
}

@misc{jawaid_openego_2025,
  title = {{OpenEgo}: {A} {Large}-{Scale} {Multimodal} {Egocentric} {Dataset} for {Dexterous} {Manipulation}},
  url = {http://arxiv.org/abs/2509.05513},
  publisher = {arXiv},
  author = {Jawaid, Ahad and Xiang, Yu},
  year = {2025},
}

@misc{wu_unleashing_2023,
  title = {Unleashing {Large}-{Scale} {Video} {Generative} {Pre}-training for {Visual} {Robot} {Manipulation}},
  url = {http://arxiv.org/abs/2312.13139},
  publisher = {arXiv},
  author = {Wu, Hongtao and Jing, Ya and Cheang, Chilam and Chen, Guangzeng and Xu, Jiafeng and Li, Xinghang and Liu, Minghuan and Li, Hang and Kong, Tao},
  year = {2023},
}

@misc{cheang_gr-2_2024,
  title = {{GR}-2: {A} {Generative} {Video}-{Language}-{Action} {Model} with {Web}-{Scale} {Knowledge} for {Robot} {Manipulation}},
  url = {http://arxiv.org/abs/2410.06158},
  publisher = {arXiv},
  author = {Cheang, Chi-Lam and Chen, Guangzeng and Jing, Ya and Kong, Tao and Li, Hang and Li, Yifeng and Liu, Yuxiao and Wu, Hongtao and Xu, Jiafeng and Yang, Yichu and Zhang, Hanbo and Zhu, Minzhao},
  year = {2024},
}

@misc{you2026affordancewamaffordanceawarejointworldaction,
  title = {AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation},
  author = {Jiadi You and Qize Yu and Yue Chen and Minghong Cai and Zhide Zhong and Yuran Wang and Bowen Ping and Jiaqi Liang and Zhenhao Shen and Haodong Yan and Yinchuan Li and Ruihai Wu and Xiaojuan Qi and Yingcong Chen},
  year = {2026},
  eprint = {2609.22332},
  url = {https://arxiv.org/abs/2609.22332},
}

@misc{zhang_ego-centric_2025,
  title = {Ego-centric {Predictive} {Model} {Conditioned} on {Hand} {Trajectories}},
  url = {http://arxiv.org/abs/2508.19852},
  publisher = {arXiv},
  author = {Zhang, Binjie and Shou, Mike Zheng},
  year = {2025},
}

@misc{jiang_rynnvla-001_2025,
  title = {{RynnVLA}-001: {Using} {Human} {Demonstrations} to {Improve} {Robot} {Manipulation}},
  url = {http://arxiv.org/abs/2509.15212},
  publisher = {arXiv},
  author = {Jiang, Yuming and Huang, Siteng and Xue, Shengke and Zhao, Yaxi and Cen, Jun and Leng, Sicong and Li, Kehan and Guo, Jiayan and Wang, Kexiang and Chen, Mingxiu and Wang, Fan and Zhao, Deli and Li, Xin},
  year = {2025},
}

@misc{routray_vipra_2026,
  title = {{ViPRA}: {Video} {Prediction} for {Robot} {Actions}},
  url = {http://arxiv.org/abs/2511.07732},
  publisher = {arXiv},
  author = {Routray, Sandeep and Pan, Hengkai and Jain, Unnat and Bahl, Shikhar and Pathak, Deepak},
  year = {2026},
}

@InProceedings{Goyal_2017_ICCV,
  author = {Goyal, Raghav and Ebrahimi Kahou, Samira and Michalski, Vincent and Materzynska, Joanna and Westphal, Susanne and Kim, Heuna and Haenel, Valentin and Fruend, Ingo and Yianilos, Peter and Mueller-Freitag, Moritz and Hoppe, Florian and Thurau, Christian and Bax, Ingo and Memisevic, Roland},
  title = {The "Something Something" Video Database for Learning and Evaluating Visual Common Sense},
  booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  year = {2017},
  url = {https://openaccess.thecvf.com/content_iccv_2017/html/Goyal_The_Something_Something_ICCV_2017_paper.html},
}

@misc{team_joyai-ra_2026,
  title = {{JoyAI}-{RA} 0.5: {Scaling} {Robot} {Manipulation} {Learning} via {Dual} {Action} {Alignment}},
  url = {http://arxiv.org/abs/2608.05674},
  publisher = {arXiv},
  author = {Team, JoyAI-RA},
  year = {2026},
}

@misc{chen_lawam_2026,
  title = {LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies},
  author = {Jialei Chen and Kai Wang and Kang Chen and Shuaihang Chen and Feng Gao and Wenhao Tang and Zhiyuan Li and Weilin Liu and Zhuyu Yao and Boxun Li and Yuanbo Xu and Chao Yu},
  year = {2026},
  eprint = {2606.15768},
  url = {https://arxiv.org/abs/2606.15768},
}

@misc{tang_world_2026,
  title = {World {Tokens}: {Enhancing} {Embodied} {Policies} with {Training}-{Time} {World} {Modeling}},
  url = {https://arxiv.org/abs/2608.09730},
  publisher = {arXiv},
  author = {Tang, Qu and Zhuang, Benhui and Yuan, Bo and Yu, Xue and Guo, Longteng and Feng, Junlan},
  year = {2026},
}

@misc{ma_humanscale_2026,
  title = {{HumanScale}: {Egocentric} {Human} {Video} {Can} {Outperform} {Real}-{Robot} {Data} for {Embodied} {Pretraining}},
  url = {http://arxiv.org/abs/2606.20521},
  publisher = {arXiv},
  author = {Ma, Juncheng and Bi, Jianxin and Deng, Yufan and Zhai, Xuanran and Zhang, Kewei and Huang, Ye and Liang, Bo and Gong, Shukai and Tu, Jiankai and Tang, Xiaotian and Li, Jiaxin and Chen, Kaiqi and Wang, Duomin and Wang, Yuqi and Kang, Bingyi and Huang, Eric and Dou, Zhiyang and Dong, Zhen and Xie, Enze and Matusik, Wojciech and Chua, Tat-Seng and Zhou, Daquan},
  year = {2026},
}

@misc{park2026learningtransferableworldactionmodels,
  title = {Learning Transferable World-Action Models from Task-Paired Human Videos},
  author = {Jeongeun Park and Taekyung Kim and Dongyoon Han and Sangdoo Yun},
  year = {2026},
  eprint = {2610.14351},
  url = {https://arxiv.org/abs/2610.14351},
}

@misc{assran2025vjepa2selfsupervisedvideo,
  title = {V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning},
  author = {Mido Assran and Adrien Bardes and David Fan and Quentin Garrido and Russell Howes and Mojtaba and Komeili and Matthew Muckley and Ammar Rizvi and Claire Roberts and Koustuv Sinha and Artem Zholus and Sergio Arnaud and Abha Gejji and Ada Martin and Francois Robert Hogan and Daniel Dugas and Piotr Bojanowski and Vasil Khalidov and Patrick Labatut and Francisco Massa and Marc Szafraniec and Kapil Krishnakumar and Yong Li and Xiaodong Ma and Sarath Chandar and Franziska Meier and Yann LeCun and Michael Rabbat and Nicolas Ballas},
  year = {2025},
  eprint = {2506.09985},
  url = {https://arxiv.org/abs/2506.09985},
}

@misc{zhou__0-wm_2026,
  title = {$\tau_0$-{WM}: {A} {Unified} {Video}-{Action} {World} {Model} for {Robotic} {Manipulation}},
  url = {http://arxiv.org/abs/2606.01027},
  publisher = {arXiv},
  author = {Zhou, Pengfei and Chen, Shengcong and Chen, Di and Wang, Jiaxu and Jin, Rongjun and Zhu, Bingwen and Pan, Yike and Gu, Songen and Wang, Kuanning and Nan, Shufeng and Qiu, Xingyu and Qiu, Chenhao and Yang, Pu and Cai, Yunuo and Gao, Jianxiong and Li, Yifan and Fu, Yanwei and Yue, Xiangyu and Chen, Zhi and Luo, Jianlan},
  year = {2026},
}

@misc{chen_cape_2026,
  title = {{CAPE}: {Contrastive} {Action}-conditioned {Parallel} {Encoding} for {Embodied} {Planning}},
  url = {http://arxiv.org/abs/2606.07304},
  publisher = {arXiv},
  author = {Chen, Cong and Wang, Haowen and Zhang, Zhixiang and Ren, Pei and Che, Zhengping},
  year = {2026},
}

@inproceedings{khazatsky_droid_2025,
  author = {Alexander Khazatsky AND Karl Pertsch AND Suraj Nair AND Ashwin Balakrishna AND Sudeep Dasari AND Siddharth Karamcheti AND Soroush Nasiriany AND Mohan Kumar Srirama AND Lawrence Yunliang Chen AND Kirsty Ellis AND Peter David Fagan AND Joey Hejna AND Masha Itkina AND Marion Lepert AND Yecheng Jason Ma AND Patrick Tree Miller AND Jimmy Wu AND Suneel Belkhale AND Shivin Dass AND Huy Ha AND Arhan Jain AND Abraham Lee AND Youngwoon Lee AND Marius Memmel AND Sungjae Park AND Ilija Radosavovic AND Kaiyuan Wang AND Albert Zhan AND Kevin Black AND Cheng Chi AND Kyle Beltran Hatch AND Shan Lin AND Jingpei Lu AND Jean Mercat AND Abdul Rehman AND Pannag R Sanketi AND Archit Sharma AND Cody Simpson AND Quan Vuong AND Homer Rich Walke AND Blake Wulfe AND Ted Xiao AND Jonathan Heewon Yang AND Arefeh Yavary AND Tony Z. Zhao AND Christopher Agia AND Rohan Baijal AND Mateo Guaman Castro AND Daphne Chen AND Qiuyu Chen AND Trinity Chung AND Jaimyn Drake AND Ethan Paul Foster AND Jensen Gao AND David Antonio Herrera AND Minho Heo AND Kyle Hsu AND Jiaheng Hu AND Donovon Jackson AND Charlotte Le AND Yunshuang Li AND Roy Lin AND Zehan Ma AND Abhiram Maddukuri AND Suvir Mirchandani AND Daniel Morton AND Tony Nguyen AND Abigail O'Neill AND Rosario Scalise AND Derick Seale AND Victor Son AND Stephen Tian AND Emi Tran AND Andrew E. Wang AND Yilin Wu AND Annie Xie AND Jingyun Yang AND Patrick Yin AND Yunchu Zhang AND Osbert Bastani AND Glen Berseth AND Jeannette Bohg AND Ken Goldberg AND Abhinav Gupta AND Abhishek Gupta AND Dinesh Jayaraman AND Joseph J Lim AND Jitendra Malik AND Roberto Martín-Martín AND Subramanian Ramamoorthy AND Dorsa Sadigh AND Shuran Song AND Jiajun Wu AND Michael C. Yip AND Yuke Zhu AND Thomas Kollar AND Sergey Levine AND Chelsea Finn},
  title = {{DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2024},
  doi = {10.15607/RSS.2024.XX.120},
}

@misc{li_novaflow_2025,
  title = {{NovaFlow}: {Zero}-{Shot} {Manipulation} via {Actionable} {Flow} from {Generated} {Videos}},
  url = {http://arxiv.org/abs/2510.08568},
  publisher = {arXiv},
  author = {Li, Hongyu and Sun, Lingfeng and Hu, Yafei and Ta, Duy and Barry, Jennifer and Konidaris, George and Fu, Jiahui},
  year = {2025},
}

@misc{li_egocentric_2026,
  title = {Egocentric {World} {Model} for {Photorealistic} {Hand}-{Object} {Interaction} {Synthesis}},
  url = {http://arxiv.org/abs/2603.13615},
  publisher = {arXiv},
  author = {Li, Dayou and Liu, Lulin and Liu, Bangya and Zhou, Shijie and Feng, Jiu and Lu, Ziqi and Zheng, Minghui and You, Chenyu and Fan, Zhiwen},
  year = {2026},
}

@InProceedings{Banerjee_2025_CVPR,
  author = {Banerjee, Prithviraj and Shkodrani, Sindi and Moulon, Pierre and Hampali, Shreyas and Han, Shangchen and Zhang, Fan and Zhang, Linguang and Fountain, Jade and Miller, Edward and Basol, Selen and Newcombe, Richard and Wang, Robert and Engel, Jakob Julian and Hodan, Tomas},
  title = {HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  pages = {7061-7071},
  url = {https://openaccess.thecvf.com/content/CVPR2025/html/Banerjee_HOT3D_Hand_and_Object_Tracking_in_3D_from_Egocentric_Multi-View_CVPR_2025_paper.html},
}

@misc{yan_egogenesis_2026-1,
  title = {{EgoGenesis}: {Egocentric} {World}-{Action} {Modeling} with {Online} {Anchored} {Projective} {Memory} and {Action}-{3D} {RoPE}},
  url = {http://arxiv.org/abs/2607.28243},
  publisher = {arXiv},
  author = {Yan, Zexuan and Wu, Yuzhou and Ma, Yue and He, Zonghang and Yin, Kaibo and Tu, Xiaobing and Wang, Yinggui and Ren, Jinkui and Zhang, Xiantao and Wang, Shijian and Liu, Jinghong and Zhang, Linfeng},
  year = {2026},
}

@inproceedings{fan_arctic_2023,
  author = {Fan, Zicong and Taheri, Omid and Tzionas, Dimitrios and Kocabas, Muhammed and Kaufmann, Manuel and Black, Michael J. and Hilliges, Otmar},
  booktitle = {2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation},
  year = {2023},
  volume = {},
  pages = {12943-12954},
  doi = {10.1109/CVPR52729.2023.01244},
}

@inproceedings{sener_assembly101_2022,
  author = {Sener, Fadime and Chatterjee, Dibyadip and Shelepov, Daniel and He, Kun and Singhania, Dipika and Wang, Robert and Yao, Angela},
  booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities},
  year = {2022},
  volume = {},
  pages = {21064-21074},
  doi = {10.1109/CVPR52688.2022.02042},
}

@misc{peddi2024captaincook4ddatasetunderstandingerrors,
  title = {CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities},
  author = {Rohith Peddi and Shivvrat Arya and Bharath Challa and Likhitha Pallapothula and Akshay Vyas and Bhavya Gouripeddi and Jikai Wang and Qifan Zhang and Vasundhara Komaragiri and Eric Ragan and Nicholas Ruozzi and Yu Xiang and Vibhav Gogate},
  year = {2024},
  eprint = {2312.14556},
  url = {https://arxiv.org/abs/2312.14556},
}

@misc{li_egolive_2026,
  title = {{EgoLive}: {A} {Large}-{Scale} {Egocentric} {Dataset} from {Real}-{World} {Human} {Tasks}},
  url = {http://arxiv.org/abs/2604.23570},
  publisher = {arXiv},
  author = {Li, Yihang and Wei, Xuelong and Luo, Jingzhou and Xiao, Yingjing and Bai, Yibo and Zhou, Guangyuan and Zou, Teng and Gui, Chenguang and Wen, Jiajun and Zhang, He and Chen, Kangliang and Pan, Xing and Liu, Shuaiyan and Wang, Daming and An, Tao and Li, Jiayi and Jin, Shibo and Zhang, Wanwan and Wang, Tianyu and Wei, Boren and Huang, Zhixuan and Liu, Fangsheng and Li, Ruodai and Zhang, Hui and Li, Anson and Gong, Yicheng and Cao, Peng and Liang, Jiaming and Lin, Liang},
  year = {2026},
}

@misc{yoon_egoxtreme_2026,
  title = {{EgoXtreme}: {A} {Dataset} for {Robust} {Object} {Pose} {Estimation} in {Egocentric} {Views} under {Extreme} {Conditions}},
  url = {http://arxiv.org/abs/2603.25135},
  publisher = {arXiv},
  author = {Yoon, Taegyoon and Han, Yegyu and Ji, Seojin and Park, Jaewoo and Kim, Sojeong and Kwon, Taein and Kim, Hyung-Sin},
  year = {2026},
}

@inproceedings{grauman_ego-exo4d_2024,
  author = {Grauman, Kristen and Westbury, Andrew and Torresani, Lorenzo and Kitani, Kris and Malik, Jitendra and Afouras, Triantafyllos and Ashutosh, Kumar and Baiyya, Vijay and Bansal, Siddhant and Boote, Bikram and Byrne, Eugene and Chavis, Zach and Chen, Joya and Cheng, Feng and Chu, Fu-Jen and Crane, Sean and Dasgupta, Avijit and Dong, Jing and Escobar, Maria and Forigua, Cristhian and Gebreselasie, Abrham and Haresh, Sanjay and Huang, Jing and Islam, Md Mohaiminul and Jain, Suyog and Khirodkar, Rawal and Kukreja, Devansh and Liang, Kevin J and Liu, Jia-Wei and Majumder, Sagnik and Mao, Yongsen and Martin, Miguel and Mavroudi, Effrosyni and Nagarajan, Tushar and Ragusa, Francesco and Ramakrishnan, Santhosh Kumar and Seminara, Luigi and Somayazulu, Arjun and Song, Yale and Su, Shan and Xue, Zihui and Zhang, Edward and Zhang, Jinxu and Castillo, Angela and Chen, Changan and Fu, Xinzhu and Furuta, Ryosuke and González, Cristina and Gupta, Prince and Hu, Jiabo and Huang, Yifei and Huang, Yiming and Khoo, Weslie and Kumar, Anush and Kuo, Robert and Lakhavani, Sach and Liu, Miao and Luo, Mi and Luo, Zhengyi and Meredith, Brighid and Miller, Austin and Oguntola, Oluwatumininu and Pan, Xiaqing and Peng, Penny and Pramanick, Shraman and Ramazanova, Merey and Ryan, Fiona and Shan, Wei and Somasundaram, Kiran and Song, Chenan and Southerland, Audrey and Tateno, Masatoshi and Wang, Huiyu and Wang, Yuchen and Yagi, Takuma and Yan, Mingfei and Yang, Xitong and Yu, Zecheng and Zha, Shengxin Cindy and Zhao, Chen and Zhao, Ziwei and Zhu, Zhifan and Zhuo, Jeff and Arbeláez, Pablo and Bertasius, Gedas and Damen, Dima and Engel, Jakob and Maria Farinella, Giovanni and Furnari, Antonino and Ghanem, Bernard and Hoffman, Judy and Jawahar, C. V. and Newcombe, Richard and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Savva, Manolis and Shi, Jianbo and Shout, Mike Zheng and Wray, Michael},
  booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives},
  year = {2024},
  volume = {},
  pages = {19383-19400},
  doi = {10.1109/CVPR52733.2024.01834},
}

@misc{huang2025egoexolearndatasetbridgingasynchronous,
  title = {EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World},
  author = {Yifei Huang and Guo Chen and Jilan Xu and Mingfang Zhang and Lijin Yang and Baoqi Pei and Hongjie Zhang and Lu Dong and Yali Wang and Limin Wang and Yu Qiao},
  year = {2025},
  eprint = {2403.16182},
  url = {https://arxiv.org/abs/2403.16182},
}

@inproceedings{kwon_h2o_2021,
  author = {Kwon, Taein and Tekin, Bugra and Stühmer, Jan and Bogo, Federica and Pollefeys, Marc},
  booktitle = {2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
  title = {H2O: Two Hands Manipulating Objects for First Person Interaction Recognition},
  year = {2021},
  volume = {},
  pages = {10118-10128},
  doi = {10.1109/ICCV48922.2021.00998},
}

@misc{perrett_hd-epic_2025,
  author = {Perrett, Toby and Darkhalil, Ahmad and Sinha, Saptarshi and Emara, Omar and Pollard, Sam and Parida, Kranti Kumar and Liu, Kaiting and Gatti, Prajwal and Bansal, Siddhant and Flanagan, Kevin and Chalk, Jacob and Zhu, Zhifan and Guerrier, Rhodri and Abdelazim, Fahd and Zhu, Bin and Moltisanti, Davide and Wray, Michael and Doughty, Hazel and Damen, Dima},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {HD-EPIC: A Highly-Detailed Egocentric Video Dataset},
  year = {2025},
  volume = {},
  pages = {23901-23913},
  doi = {10.1109/CVPR52734.2025.02226},
}

@misc{wang2025hocapcapturedataset3d,
  title = {HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction},
  author = {Jikai Wang and Qifan Zhang and Yu-Wei Chao and Bowen Wen and Xiaohu Guo and Yu Xiang},
  year = {2025},
  eprint = {2406.06843},
  url = {https://arxiv.org/abs/2406.06843},
}

@inproceedings{wang_holoassist_2023,
  author = {Wang, Xin and Kwon, Taein and Rad, Mahdi and Pan, Bowen and Chakraborty, Ishani and Andrist, Sean and Bohus, Dan and Feniello, Ashley and Tekin, Bugra and Frujeri, Felipe Vieira and Joshi, Neel and Pollefeys, Marc},
  booktitle = {2023 IEEE/CVF International Conference on Computer Vision (ICCV)},
  title = {HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World},
  year = {2023},
  volume = {},
  pages = {20213-20224},
  doi = {10.1109/ICCV51070.2023.01854},
}

@misc{schoonbeek2023industrealdatasetprocedurestep,
  title = {IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting},
  author = {Tim J. Schoonbeek and Tim Houben and Hans Onvlee and Peter H. N. de With and Fons van der Sommen},
  year = {2023},
  eprint = {2310.17323},
  url = {https://arxiv.org/abs/2310.17323},
}

@incollection{ma_nymeria_2024,
  author = {Ma, Lingni
    and Ye, Yuting
    and Hong, Fangzhou
    and Guzov, Vladimir
    and Jiang, Yifeng
    and Postyeni, Rowan
    and Pesqueira, Luis
    and Gamino, Alexander
    and Baiyya, Vijay
    and Kim, Hyo Jin
    and Bailey, Kevin
    and Fosas, David S.
    and Liu, C. Karen
    and Liu, Ziwei
    and Engel, Jakob
    and Nardi, Renzo De
    and Newcombe, Richard},
  title = {Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild},
  booktitle = {Computer Vision -- ECCV 2024},
  year = {2025},
  publisher = {Springer Nature Switzerland},
  pages = {445--465},
  url = {https://arxiv.org/abs/2406.09905},
}

@inproceedings{zhan_oakink2_2024,
  author = {Zhan, Xinyu and Yang, Lixin and Zhao, Yifei and Mao, Kangrui and Xu, Hanlin and Lin, Zenan and Li, Kailin and Lu, Cewu},
  booktitle = {2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {OakInk2 : A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion},
  year = {2024},
  volume = {},
  pages = {445-456},
  doi = {10.1109/CVPR52733.2024.00050},
}

@misc{li_open-aoe_2026,
  title = {Open-{AoE}: {An} {Open} {Egocentric} {Manipulation} {Dataset} and {Toolchain} for {Embodied} {Learning}},
  url = {http://arxiv.org/abs/2607.14183},
  publisher = {arXiv},
  author = {Li, Zishuo and Yang, Bowen and Miao, Changtao and Zhu, Kai and Chen, Hao and Guan, Qingze and Wu, Zhengxing and Zhan, Wanke and Sun, Yang and Huang, Zhiyi and Shan, Zitong and Jin, Zhenchao and Hong, Jiadong and Wang, Taowen and Feng, Yushi and Liu, You and Wang, Yibo and Yang, Yifan and Zhou, Zhaowen and Luo, Man and Cheng, Hao and Zhang, Bo and Li, Jianshu and Cai, Jiansheng and Yao, Guocai and Zhang, Jize and Lin, Chenhao and Xu, Renjing and Yu, Lequan and Shen, Chao and Shen, Chunhua and Li, Zhe},
  year = {2026},
}

@misc{ohkawa_yubi_2026,
  title = {{YUBI}: {Yielding} {Universal} {Bidigital} {Interface} for {Bimanual} {Dexterous} {Manipulation} at {Scale}},
  url = {http://arxiv.org/abs/2606.10244},
  publisher = {arXiv},
  author = {Ohkawa, Takehiko and Arima, Jumpei and Noguchi, Yuki and Tateno, Masatoshi and Sugiura, Makoto and Okubo, Takuya and Ikeuchi, Kengo and Shin, Yuma and Nishizawa, Hiroki and Kanazawa, Naoaki and Wakayama, Yuki and Fukunaga, Daiki and Makihara, Koshi and Motoda, Tomohiro and Erich, Floris and Domae, Yukiyasu and Matsushima, Tatsuya and Okumatsu, Yohishiro and Ota, Kei},
  year = {2026},
}

@inproceedings{brohan_rt-1_2023,
  author = {Anthony Brohan AND Noah Brown AND Justice Carbajal AND Yevgen Chebotar AND Joseph Dabis AND Chelsea Finn AND Keerthana Gopalakrishnan AND Karol Hausman AND Alexander Herzog AND Jasmine Hsu AND Julian Ibarz AND Brian Ichter AND Alex Irpan AND Tomas Jackson AND Sally Jesmonth AND Nikhil Joshi AND Ryan Julian AND Dmitry Kalashnikov AND Yuheng Kuang AND Isabel Leal AND Kuang-Huei Lee AND Sergey Levine AND Yao Lu AND Utsav Malla AND Deeksha Manjunath AND Igor Mordatch AND Ofir Nachum AND Carolina Parada AND Jodilyn  Peralta AND Emily Perez AND Karl Pertsch AND Jornell  Quiambao AND Kanishka Rao AND Michael S Ryoo AND Grecia  Salazar AND Pannag R Sanketi AND Kevin  Sayed AND Jaspiar  Singh AND Sumedh  Sontakke AND Austin  Stone AND Clayton  Tan AND Huong  Tran AND Vincent Vanhoucke AND Steve  Vega AND Quan H Vuong AND Fei Xia AND Ted Xiao AND Peng Xu AND Sichun Xu AND Tianhe Yu AND Brianna  Zitkovich},
  title = {{RT-1: Robotics Transformer for Real-World Control at Scale}},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2023},
  doi = {10.15607/RSS.2023.XIX.025},
}

@article{walke_bridgedata_nodate,
  title = {BridgeData V2: A Dataset for Robot Learning at Scale},
  author = {Walke, Homer Rich and Black, Kevin and Zhao, Tony Z. and Vuong, Quan and Zheng, Chongyi and Hansen-Estruch, Philippe and He, Andre Wang and Myers, Vivek and Kim, Moo Jin and Du, Max and Lee, Abraham and Fang, Kuan and Finn, Chelsea and Levine, Sergey},
  booktitle = {Proceedings of The 7th Conference on Robot Learning},
  pages = {1723--1736},
  year = {2023},
  volume = {229},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v229/walke23a.html},
}

@misc{takanami_airoa_2025,
  title = {{AIRoA} {MoMa} {Dataset}: {A} {Large}-{Scale} {Hierarchical} {Dataset} for {Mobile} {Manipulation}},
  url = {http://arxiv.org/abs/2509.25032},
  publisher = {arXiv},
  author = {Takanami, Ryosuke and Khrapchenkov, Petr and Morikuni, Shu and Arima, Jumpei and Takaba, Yuta and Maeda, Shunsuke and Okubo, Takuya and Sano, Genki and Sekioka, Satoshi and Kadoya, Aoi and Kambara, Motonari and Nishiura, Naoya and Suzuki, Haruto and Yoshimoto, Takanori and Sakamoto, Koya and Ono, Shinnosuke and Yang, Hu and Yashima, Daichi and Horo, Aoi and Motoda, Tomohiro and Chiyoma, Kensuke and Ito, Hiroshi and Fukuda, Koki and Goto, Akihito and Morinaga, Kazumi and Ikeda, Yuya and Kawada, Riko and Yoshikawa, Masaki and Kosuge, Norio and Noguchi, Yuki and Ota, Kei and Matsushima, Tatsuya and Iwasawa, Yusuke and Matsuo, Yutaka and Ogata, Tetsuya},
  year = {2025},
}

@misc{collaboration_open_2025,
  author = {O’Neill, Abby and Rehman, Abdul and Maddukuri, Abhiram and Gupta, Abhishek and Padalkar, Abhishek and Lee, Abraham and Pooley, Acorn and Gupta, Agrim and Mandlekar, Ajay and Jain, Ajinkya and Tung, Albert and Bewley, Alex and Herzog, Alex and Irpan, Alex and Khazatsky, Alexander and Rai, Anant and Gupta, Anchit and Wang, Andrew and Singh, Anikait and Garg, Animesh and Kembhavi, Aniruddha and Xie, Annie and Brohan, Anthony and Raffin, Antonin and Sharma, Archit and Yavary, Arefeh and Jain, Arhan and Balakrishna, Ashwin and Wahid, Ayzaan and Burgess-Limerick, Ben and Kim, Beomjoon and Schölkopf, Bernhard and Wulfe, Blake and Ichter, Brian and Lu, Cewu and Xu, Charles and Le, Charlotte and Finn, Chelsea and Wang, Chen and Xu, Chenfeng and Chi, Cheng and Huang, Chenguang and Chan, Christine and Agia, Christopher and Pan, Chuer and Fu, Chuyuan and Devin, Coline and Xu, Danfei and Morton, Daniel and Driess, Danny and Chen, Daphne and Pathak, Deepak and Shah, Dhruv and Büchler, Dieter and Jayaraman, Dinesh and Kalashnikov, Dmitry and Sadigh, Dorsa and Johns, Edward and Foster, Ethan and Liu, Fangchen and Ceola, Federico and Xia, Fei and Zhao, Feiyu and Stulp, Freek and Zhou, Gaoyue and Sukhatme, Gaurav S. and Salhotra, Gautam and Yan, Ge and Feng, Gilbert and Schiavi, Giulio and Berseth, Glen and Kahn, Gregory and Wang, Guanzhi and Su, Hao and Fang, Hao-Shu and Shi, Haochen and Bao, Henghui and Ben Amor, Heni and Christensen, Henrik I and Furuta, Hiroki and Walke, Homer and Fang, Hongjie and Ha, Huy and Mordatch, Igor and Radosavovic, Ilija and Leal, Isabel and Liang, Jacky and Abou-Chakra, Jad and Kim, Jaehyung and Drake, Jaimyn and Peters, Jan and Schneider, Jan and Hsu, Jasmine and Bohg, Jeannette and Bingham, Jeffrey and Wu, Jeffrey and Gao, Jensen and Hu, Jiaheng and Wu, Jiajun and Wu, Jialin and Sun, Jiankai and Luo, Jianlan and Gu, Jiayuan and Tan, Jie and Oh, Jihoon and Wu, Jimmy and Lu, Jingpei and Yang, Jingyun and Malik, Jitendra and Silvério, João and Hejna, Joey and Booher, Jonathan and Tompson, Jonathan and Yang, Jonathan and Salvador, Jordi and Lim, Joseph J. and Han, Junhyek and Wang, Kaiyuan and Rao, Kanishka and Pertsch, Karl and Hausman, Karol and Go, Keegan and Gopalakrishnan, Keerthana and Goldberg, Ken and Byrne, Kendra and Oslund, Kenneth and Kawaharazuka, Kento and Black, Kevin and Lin, Kevin and Zhang, Kevin and Ehsani, Kiana and Lekkala, Kiran and Ellis, Kirsty and Rana, Krishan and Srinivasan, Krishnan and Fang, Kuan and Singh, Kunal Pratap and Zeng, Kuo-Hao and Hatch, Kyle and Hsu, Kyle and Itti, Laurent and Chen, Lawrence Yunliang and Pinto, Lerrel and Fei-Fei, Li and Tan, Liam and Fan, Linxi Jim and Ott, Lionel and Lee, Lisa and Weihs, Luca and Chen, Magnum and Lepert, Marion and Memmel, Marius and Tomizuka, Masayoshi and Itkina, Masha and Castro, Mateo Guaman and Spero, Max and Du, Maximilian and Ahn, Michael and Yip, Michael C. and Zhang, Mingtong and Ding, Mingyu and Heo, Minho and Srirama, Mohan Kumar and Sharma, Mohit and Kim, Moo Jin and Kanazawa, Naoaki and Hansen, Nicklas and Heess, Nicolas and Joshi, Nikhil J and Suenderhauf, Niko and Liu, Ning and Di Palo, Norman and Shafiullah, Nur Muhammad Mahi and Mees, Oier and Kroemer, Oliver and Bastani, Osbert and Sanketi, Pannag R and Miller, Patrick Tree and Yin, Patrick and Wohlhart, Paul and Xu, Peng and Fagan, Peter David and Mitrano, Peter and Sermanet, Pierre and Abbeel, Pieter and Sundaresan, Priya and Chen, Qiuyu and Vuong, Quan and Rafailov, Rafael and Tian, Ran and Doshi, Ria and Martín-Martín, Roberto and Baijal, Rohan and Scalise, Rosario and Hendrix, Rose and Lin, Roy and Qian, Runjia and Zhang, Ruohan and Mendonca, Russell and Shah, Rutav and Hoque, Ryan and Julian, Ryan and Bustamante, Samuel and Kirmani, Sean and Levine, Sergey and Lin, Shan and Moore, Sherry and Bahl, Shikhar and Dass, Shivin and Sonawani, Shubham and Song, Shuran and Xu, Sichun and Haldar, Siddhant and Karamcheti, Siddharth and Adebola, Simeon and Guist, Simon and Nasiriany, Soroush and Schaal, Stefan and Welker, Stefan and Tian, Stephen and Ramamoorthy, Subramanian and Dasari, Sudeep and Belkhale, Suneel and Park, Sungjae and Nair, Suraj and Mirchandani, Suvir and Osa, Takayuki and Gupta, Tanmay and Harada, Tatsuya and Matsushima, Tatsuya and Xiao, Ted and Kollar, Thomas and Yu, Tianhe and Ding, Tianli and Davchev, Todor and Zhao, Tony Z. and Armstrong, Travis and Darrell, Trevor and Chung, Trinity and Jain, Vidhi and Vanhoucke, Vincent and Zhan, Wei and Zhou, Wenxuan and Burgard, Wolfram and Chen, Xi and Wang, Xiaolong and Zhu, Xinghao and Geng, Xinyang and Liu, Xiyuan and Liangwei, Xu and Li, Xuanlin and Lu, Yao and Ma, Yecheng Jason and Kim, Yejin and Chebotar, Yevgen and Zhou, Yifan and Zhu, Yifeng and Wu, Yilin and Xu, Ying and Wang, Yixuan and Bisk, Yonatan and Cho, Yoonyoung and Lee, Youngwoon and Cui, Yuchen and Cao, Yue and Wu, Yueh-Hua and Tang, Yujin and Zhu, Yuke and Zhang, Yunchu and Jiang, Yunfan and Li, Yunshuang and Li, Yunzhu and Iwasawa, Yusuke and Matsuo, Yutaka and Ma, Zehan and Xu, Zhuo and Cui, Zichen Jeff and Zhang, Zichen and Lin, Zipeng},
  booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {{Open X-Embodiment: Robotic Learning Datasets and RT-X Models}},
  year = {2024},
  volume = {},
  pages = {6892-6903},
  doi = {10.1109/ICRA57147.2024.10611477},
}

@misc{wu_robocoin_2026,
  title = {{RoboCOIN}: {An} {Open}-{Sourced} {Bimanual} {Robotic} {Data} {Collection} for {Integrated} {Manipulation}},
  url = {http://arxiv.org/abs/2511.17441},
  publisher = {arXiv},
  author = {Wu, Shihan and Liu, Xuecheng and Xie, Shaoxuan and Wang, Pengwei and Li, Xinghang and Yang, Bowen and Li, Zhe and Zhu, Kai and Wu, Hongyu and Liu, Yiheng and Long, Zhaoye and Xu, Runtian and Wang, Yue and Liu, Chong and Wang, Dihan and Ni, Ziqiang and Yang, Xiang and Liu, You and Feng, Ruoxuan and Zhang, Lei and Huang, Denghang and Jin, Chenghao and Yin, Anlan and Wang, Xinlong and Sun, Zhenguo and Zhao, Junkai and Du, Mengfei and Cao, Mingyu and Chen, Xiansheng and Cheng, Hongyang and Zhang, Xiaojie and Fu, Yankai and Chen, Ning and Chi, Cheng and Chen, Sixiang and Lyu, Huaihai and Hao, Xiaoshuai and Wang, Yequan and Lei, Bo and Liu, Dong and Yang, Xi and Jiao, Yance and Pan, Tengfei and Zhang, Yunyan and Wang, Songjing and Zhang, Ziqian and Liu, Xu and Zhang, Ji and Meng, Caowei and Zhang, Zhizheng and Gao, Jiyang and Wang, Song and Leng, Xiaokun and Xie, Zhiqiang and Zhou, Zhenzhen and Huang, Peng and Yang, Wu and Guo, Yandong and Zhu, Yichao and Zheng, Suibing and Cheng, Hao and Ding, Xinmin and Yue, Yang and Wang, Huanqian and Chen, Chi and Pang, Jingrui and Qian, YuXi and Geng, Haoran and Gao, Lianli and Li, Haiyuan and Fang, Bin and Huang, Gao and Yang, Yaodong and Dong, Hao and Wang, He and Zhao, Hang and Mu, Yadong and Hu, Di and Zhao, Hao and Huang, Tiejun and Zhang, Shanghang and Lin, Yonghua and Wang, Zhongyuan and Yao, Guocai},
  year = {2026},
}

@misc{hou_robomind_2026,
  title = {{RoboMIND} 2.0: {A} {Multimodal}, {Bimanual} {Mobile} {Manipulation} {Dataset} for {Generalizable} {Embodied} {Intelligence}},
  url = {http://arxiv.org/abs/2512.24653},
  publisher = {arXiv},
  author = {Hou, Chengkai and Wu, Kun and Liu, Jiaming and Che, Zhengping and Wu, Di and Liao, Fei and Li, Guangrun and He, Jingyang and Feng, Qiuxuan and Jin, Zhao and Gu, Chenyang and Liu, Zhuoyang and Han, Nuowei and Mi, Xiangju and Lv, Yaoxu and Fu, Yankai and Dai, Gaole and Gu, Langzhe and Li, Tao and Zhang, Yuheng and Zhang, Yixue and Wang, Xinhua and Fan, Shichao and Li, Meng and Zhao, Zhen and Liu, Ning and Xu, Zhiyuan and Ren, Pei and Ji, Junjie and Liu, Haonan and Cheng, Kuan and Zhang, Shanghang and Tang, Jian},
  year = {2026},
}

@misc{hua_vtouch_2026,
  title = {{VTouch}++: {A} {Multimodal} {Dataset} with {Vision}-{Based} {Tactile} {Enhancement} for {Bimanual} {Manipulation}},
  url = {http://arxiv.org/abs/2604.20444},
  publisher = {arXiv},
  author = {Hua, Qianxi and Li, Xinyue and Yan, Zheng and Li, Yang and Zhang, Chi and Li, Yongyao and Liu, Yufei},
  year = {2026},
}

@misc{zhang_empowering_2024,
  title = {Empowering {Embodied} {Manipulation}: {A} {Bimanual}-{Mobile} {Robot} {Manipulation} {Dataset} for {Household} {Tasks}},
  url = {http://arxiv.org/abs/2405.18860},
  publisher = {arXiv},
  author = {Zhang, Tianle and Li, Dongjiang and Li, Yihang and Zeng, Zecui and Zhao, Lin and Sun, Lei and Chen, Yue and Wei, Xuelong and Zhan, Yibing and Li, Lusong and He, Xiaodong},
  year = {2024},
}

@misc{jiang_galaxea_2025,
  title = {Galaxea {Open}-{World} {Dataset} and {G0} {Dual}-{System} {VLA} {Model}},
  url = {http://arxiv.org/abs/2509.00576},
  publisher = {arXiv},
  author = {Jiang, Tao and Yuan, Tianyuan and Liu, Yicheng and Lu, Chenhao and Cui, Jianning and Liu, Xiao and Cheng, Shuiqi and Gao, Jiyang and Xu, Huazhe and Zhao, Hang},
  year = {2025},
}

@misc{allshire_scalable_2026,
  title = {Scalable {Behavior} {Cloning} with {Open} {Data}, {Training}, and {Evaluation}},
  url = {http://arxiv.org/abs/2606.27375},
  publisher = {arXiv},
  author = {Allshire, Arthur and Singh, Himanshu Gaurav and Singh, Ritvik and Rashid, Adam and Choi, Hongsuk and McAllister, David and Yu, Justin and Chen, Yiyuan and Huang, Huang and Abbeel, Pieter and Chen, Xi and Duan, Rocky and Isola, Phillip and Malik, Jitendra and Shentu, Fred and Shi, Guanya and Wu, Philipp and Kanazawa, Angjoo},
  year = {2026},
}

@misc{agibot-world-contributors_agibot_2025,
  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 Jiaqi Zhao and Jianchao Zhu},
  booktitle = {2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  title = {AgiBot World Colosseo: A Large-Scale Manipulation Platform for Scalable and Intelligent Embodied Systems},
  year = {2025},
  volume = {},
  pages = {3549-3556},
  doi = {10.1109/IROS60139.2025.11247088},
}

@misc{zhao_humanoid_2026,
  title = {Humanoid {Everyday}: {A} {Comprehensive} {Robotic} {Dataset} for {Open}-{World} {Humanoid} {Manipulation}},
  url = {http://arxiv.org/abs/2510.08807},
  publisher = {arXiv},
  author = {Zhao, Zhenyu and Jing, Hongyi and Liu, Xiawei and Mao, Jiageng and Jha, Abha and Yang, Hanwen and Xue, Rong and Zakharov, Sergey and Guizilini, Vitor and Wang, Yue},
  year = {2026},
}

@misc{wang_robotacdex_nodate,
  title = {{RoboTacDex}: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation},
  author = {Wang, Xinyi and Li, Donghan and Chen, Zi'Ang and Yu, Chong and Xin, Chen and Ye, Peng and Sun, Yingkai and Chen, Tao},
  year = {2026},
  eprint = {2606.31836},
  url = {https://arxiv.org/abs/2606.31836},
  publisher = {arXiv},
}

@misc{lim_hrdexdb_2026,
  title = {HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments},
  author = {Jongbin Lim and Taeyun Ha and Seongho Cha and Kanghyeon Cho and Mingi Choi and Subin Jeon and Jisoo Kim and Byungjun Kim and Hanbyul Joo},
  year = {2026},
  eprint = {2604.14944},
  url = {https://arxiv.org/abs/2604.14944},
}

@InProceedings{chen_hvg3d_2026,
  author = {Chen, Mingjin and Chen, Junhao and Fan, Zhaoxin and Lee, Yujian and Dang, Zichen and Wang, Lili and Cui, Yawen and Chau, Lap-Pui and Wang, Yi},
  title = {HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  pages = {15986-15997},
}

@misc{mees_calvin_2022,
  author = {Mees, Oier and Hermann, Lukas and Rosete-Beas, Erick and Burgard, Wolfram},
  journal = {IEEE Robotics and Automation Letters},
  title = {CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks},
  year = {2022},
  volume = {7},
  pages = {7327-7334},
  doi = {10.1109/LRA.2022.3180108},
}

@misc{wang_gensim_2024,
  title = {{GenSim}: {Generating} {Robotic} {Simulation} {Tasks} via {Large} {Language} {Models}},
  url = {http://arxiv.org/abs/2310.01361},
  publisher = {arXiv},
  author = {Wang, Lirui and Ling, Yiyang and Yuan, Zhecheng and Shridhar, Mohit and Bao, Chen and Qin, Yuzhe and Wang, Bailin and Xu, Huazhe and Wang, Xiaolong},
  year = {2024},
}

@article{wang_robogen_nodate,
  author = {Wang, Yufei and Xian, Zhou and Chen, Feng and Wang, Tsun-Hsuan and Wang, Yian and Fragkiadaki, Katerina and Erickson, Zackory and Held, David and Gan, Chuang},
  title = {RoboGen: towards unleashing infinite data for automated robot learning via generative simulation},
  year = {2024},
  publisher = {JMLR.org},
  booktitle = {Proceedings of the 41st International Conference on Machine Learning},
  url = {https://arxiv.org/abs/2311.01455},
}

@misc{han_robocerebra_2025,
  title = {{RoboCerebra}: {A} {Large}-scale {Benchmark} for {Long}-horizon {Robotic} {Manipulation} {Evaluation}},
  url = {http://arxiv.org/abs/2506.06677},
  publisher = {arXiv},
  author = {Han, Songhao and Qiu, Boxiang and Liao, Yue and Huang, Siyuan and Gao, Chen and Yan, Shuicheng and Liu, Si},
  year = {2025},
}

@misc{he_nimbus_2026,
  title = {Nimbus: {A} {Unified} {Embodied} {Synthetic} {Data} {Generation} {Framework}},
  url = {http://arxiv.org/abs/2601.21449},
  publisher = {arXiv},
  author = {He, Zeyu and Zhang, Yuchang and Zhou, Yuanzhen and Tao, Miao and Li, Hengjie and Wang, Hui and Tian, Yang and Zeng, Jia and Wang, Tai and Cai, Wenzhe and Chen, Yilun and Gao, Ning and Pang, Jiangmiao},
  year = {2026},
}

@misc{moghani_softmimicgen_2026,
  title = {{SoftMimicGen}: {A} {Data} {Generation} {System} for {Scalable} {Robot} {Learning} in {Deformable} {Object} {Manipulation}},
  url = {http://arxiv.org/abs/2603.25725},
  publisher = {arXiv},
  author = {Moghani, Masoud and Azizian, Mahdi and Garg, Animesh and Zhu, Yuke and Huver, Sean and Mandlekar, Ajay},
  year = {2026},
}

@misc{garrett_skillmimicgen_2024,
  title = {{SkillMimicGen}: {Automated} {Demonstration} {Generation} for {Efficient} {Skill} {Learning} and {Deployment}},
  url = {http://arxiv.org/abs/2410.18907},
  publisher = {arXiv},
  author = {Garrett, Caelan and Mandlekar, Ajay and Wen, Bowen and Fox, Dieter},
  year = {2024},
}

@misc{mu_robotwin_2025,
  title = {{RoboTwin}: {Dual}-{Arm} {Robot} {Benchmark} with {Generative} {Digital} {Twins} (early version)},
  url = {http://arxiv.org/abs/2409.02920},
  publisher = {arXiv},
  author = {Mu, Yao and Chen, Tianxing and Peng, Shijia and Chen, Zanxin and Gao, Zeyu and Zou, Yude and Lin, Lunkai and Xie, Zhiqiang and Luo, Ping},
  year = {2025},
}

@misc{zhang_robosnap_2026,
  title = {{RoboSnap}: {One}-{Shot} {Real}-to-{Sim} {Scene} {Generation} for {Generalizable} {Robot} {Learning} and {Evaluation}},
  url = {http://arxiv.org/abs/2607.06699},
  publisher = {arXiv},
  author = {Zhang, Shujie and Yi, Jingkun and Zhong, Weipeng and Zhou, Zirui and Zhu, Yangkun and Wang, Hanqing and Xu, Xudong and Zhang, Weinan and Shen, Chunhua},
  year = {2026},
}

@misc{guo_worlds_2026,
  title = {Worlds in {One} {Demo}: {A} {Synthetic} {Data} {Engine} for {Learning} {Open}-{World} {Mobile} {Manipulation}},
  url = {http://arxiv.org/abs/2607.13154},
  publisher = {arXiv},
  author = {Guo, Lingxiao and Li, Huanyu and Shi, Guanya},
  year = {2026},
}

@misc{zhao_taste-rob_2025,
  author = {Zhao, Hongxiang and Liu, Xingchen and Xu, Mutian and Hao, Yiming and Chen, Weikai and Han, Xiaoguang},
  booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  title = {TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation},
  year = {2025},
  volume = {},
  pages = {27683-27693},
  doi = {10.1109/CVPR52734.2025.02578},
}

@misc{hao_egosim_2026,
  title = {{EgoSim}: {Egocentric} {World} {Simulator} for {Embodied} {Interaction} {Generation}},
  url = {http://arxiv.org/abs/2604.01001},
  publisher = {arXiv},
  author = {Hao, Jinkun and Jia, Mingda and Wang, Ruiyan and Zhu, Hongrui and Cao, Jiafei and Liu, Xihui and Yi, Ran and Ma, Lizhuang and Pang, Jiangmiao and Xu, Xudong},
  year = {2026},
}

@misc{xu_egodemogen_2026,
  title = {{EgoDemoGen}: {Egocentric} {Demonstration} {Generation} for {Viewpoint} {Generalization} in {Robotic} {Manipulation}},
  url = {http://arxiv.org/abs/2509.22578},
  publisher = {arXiv},
  author = {Xu, Yuan and Yang, Jiabing and Wang, Xiaofeng and Chen, Yixiang and Zhu, Zheng and Fang, Bowen and Huang, Guan and Chen, Xinze and Ye, Yun and Zhang, Qiang and Li, Peiyan and Wu, Xiangnan and Wang, Kai and Zhan, Bing and Lu, Shuo and Liu, Jing and Liu, Nianfeng and Huang, Yan and Wang, Liang},
  year = {2026},
}

@misc{sedlacek_realm_2025,
  author = {Sedlacek, Martin and Yefanov, Pavlo and Ponimatkin, Georgy and Bardhan, Jai and Pilc, Simon and Fourmy, Mederic and Kazakos, Evangelos and Snoek, Cees G. M. and Sivic, Josef and Petrik, Vladimir},
  journal = {IEEE Robotics and Automation Letters},
  title = {REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation},
  year = {2026},
  volume = {11},
  pages = {8315-8322},
  doi = {10.1109/LRA.2026.3692088},
}

@misc{yang_handedit_2026,
  title = {{HandEdit}: {A} {Unified} {Benchmark} for {Egocentric} {Human}-to-{Robot} {Dexterous} {Hand} {Image} {Editing}},
  url = {http://arxiv.org/abs/2608.12122},
  publisher = {arXiv},
  author = {Yang, Zhenjie and Jiao, Xingyu and Zhong, Guopeng and Yang, Shuzhe and Che, Shi and Wu, Chao and Jiang, Chenyu and Zhang, Dongjie and Zhang, Yideng and Zhang, Zheng and Jiang, Muyun and Su, Haisheng and Jin, Shuang and Zhang, Donghang and Yang, Chao and Chen, Li and Li, Hongyang and Wu, Zuxuan and Jiang, Yu-Gang and Jia, Xiaosong and Yan, Junchi},
  year = {2026},
}

@misc{chen2026volophysicalorchestratoropenvocabulary,
  title = {VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation},
  author = {Siyi Chen and Hugo Hadfield and Alex Zook and Mikaela Angelina Uy and Chan Hee Song and Erwin Coumans and Xuning Yang and Faisal Ladhak and Qing Qu and Stan Birchfield and Jonathan Tremblay and Valts Blukis},
  year = {2026},
  eprint = {2606.07723},
  url = {https://arxiv.org/abs/2606.07723},
}

@misc{li2026roboclawagenticframeworkscalable,
  title = {RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks},
  author = {Ruiying Li and Yunlang Zhou and YuYao Zhu and Kylin Chen and Jingyuan Wang and Sukai Wang and Kongtao Hu and Minhui Yu and Bowen Jiang and Zhan Su and Jiayao Ma and Xin He and Yongjian Shen and Yang Yang and Guanghui Ren and Maoqing Yao and Wenhao Wang and Yao Mu},
  year = {2026},
  eprint = {2603.11558},
  url = {https://arxiv.org/abs/2603.11558},
}

@misc{cheng2026incontextrobotlearningvlm,
  title = {In-Context Robot Learning with VLM Agents},
  author = {Dongzhou Cheng and Taoran Yi and Ye Fang and Xingwu Zhang and Fan Feng and Yixuan Li and Gengxiong Zhuang and Rongze Wang and Shuai Yang and Wei Song and Weizhi Xue and Minyan Wu and Jie Gui and Jiaqi Wang and Tong Wu},
  year = {2026},
  eprint = {2609.19138},
  url = {https://arxiv.org/abs/2609.19138},
}

@misc{liu2026robotaembedunifiedvlaembeddings,
  title = {Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution},
  author = {Yunze Liu and Jing Wang and Shenrui Wu and Wenkun He and Guanqi Zhan and Xianzheng Ma and Junyu Chen and Wenhang Ge and Haozhan Tang and Yuchao Gu and Zhuoyang Zhang and Zekai Wang and Dantong Niu and Zhen Dong and Yuke Zhu and Trevor Darrell and Linxi "Jim" Fan and Song Han and Han Cai},
  year = {2026},
  eprint = {2610.19495},
  url = {https://arxiv.org/abs/2610.19495},
}

@misc{li_egoprocevqa_2026,
  title = {EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent},
  author = {Junlong Li and Junxi Li and Yuxiang Yang and Wenbin Zou and Lap-Pui Chau and Yi Wang},
  year = {2026},
  eprint = {2607.13792},
  url = {https://arxiv.org/abs/2607.13792},
}