% Embodied AI Radar - curated papers (448 entries), built from arXiv metadata (CC0).
% https://hu-zlatan.github.io/embodied-ai-radar/

@misc{brohan2022rt,
  title = {{RT-1: Robotics Transformer for Real-World Control at Scale}},
  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 Alex Herzog and Jasmine Hsu and Julian Ibarz and Brian Ichter and Alex Irpan and Tomas Jackson and Sally Jesmonth and Nikhil J 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 Ryoo and Grecia Salazar and Pannag 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 Vuong and Fei Xia and Ted Xiao and Peng Xu and Sichun Xu and Tianhe Yu and others},
  year = {2022},
  eprint = {2212.06817},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2212.06817},
}

@misc{brohan2023rt,
  title = {{RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control}},
  author = {Anthony Brohan and Noah Brown and Justice Carbajal and Yevgen Chebotar and Xi Chen and Krzysztof Choromanski and Tianli Ding and Danny Driess and Avinava Dubey and Chelsea Finn and Pete Florence and Chuyuan Fu and Montse Gonzalez Arenas and Keerthana Gopalakrishnan and Kehang Han and Karol Hausman and Alexander Herzog and Jasmine Hsu and Brian Ichter and Alex Irpan and Nikhil Joshi and Ryan Julian and Dmitry Kalashnikov and Yuheng Kuang and Isabel Leal and Lisa Lee and Tsang-Wei Edward Lee and Sergey Levine and Yao Lu and Henryk Michalewski and Igor Mordatch and Karl Pertsch and Kanishka Rao and Krista Reymann and Michael Ryoo and Grecia Salazar and Pannag Sanketi and Pierre Sermanet and Jaspiar Singh and Anikait Singh and Radu Soricut and Huong Tran and Vincent Vanhoucke and Quan Vuong and Ayzaan Wahid and Stefan Welker and Paul Wohlhart and Jialin Wu and Fei Xia and Ted Xiao and others},
  year = {2023},
  eprint = {2307.15818},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2307.15818},
}

@misc{team2024octo,
  title = {{Octo: An Open-Source Generalist Robot Policy}},
  author = {Octo Model Team and Dibya Ghosh and Homer Walke and Karl Pertsch and Kevin Black and Oier Mees and Sudeep Dasari and Joey Hejna and Tobias Kreiman and Charles Xu and Jianlan Luo and You Liang Tan and Lawrence Yunliang Chen and Pannag Sanketi and Quan Vuong and Ted Xiao and Dorsa Sadigh and Chelsea Finn and Sergey Levine},
  year = {2024},
  eprint = {2405.12213},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2405.12213},
}

@misc{kim2024openvla,
  title = {{OpenVLA: An Open-Source Vision-Language-Action Model}},
  author = {Moo Jin Kim and Karl Pertsch and Siddharth Karamcheti and Ted Xiao and Ashwin Balakrishna and Suraj Nair and Rafael Rafailov and Ethan Foster and Grace Lam and Pannag Sanketi and Quan Vuong and Thomas Kollar and Benjamin Burchfiel and Russ Tedrake and Dorsa Sadigh and Sergey Levine and Percy Liang and Chelsea Finn},
  year = {2024},
  eprint = {2406.09246},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2406.09246},
}

@misc{kim2025fine,
  title = {{Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success}},
  author = {Moo Jin Kim and Chelsea Finn and Percy Liang},
  year = {2025},
  eprint = {2502.19645},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.19645},
}

@misc{black2024vision,
  title = {{$π_0$: A Vision-Language-Action Flow Model for General Robot Control}},
  author = {Kevin Black and Noah Brown and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Lucy Xiaoyang Shi and James Tanner and Quan Vuong and Anna Walling and Haohuan Wang and Ury Zhilinsky},
  year = {2024},
  eprint = {2410.24164},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2410.24164},
}

@misc{intelligence2025vision,
  title = {{$π_{0.5}$: a Vision-Language-Action Model with Open-World Generalization}},
  author = {Physical Intelligence and Kevin Black and Noah Brown and James Darpinian and Karan Dhabalia and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Manuel Y. Galliker and Dibya Ghosh and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and James Tanner and Quan Vuong and Homer Walke and Anna Walling and Haohuan Wang and Lili Yu and Ury Zhilinsky},
  year = {2025},
  eprint = {2504.16054},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2504.16054},
}

@misc{pertsch2025fast,
  title = {{FAST: Efficient Action Tokenization for Vision-Language-Action Models}},
  author = {Karl Pertsch and Kyle Stachowicz and Brian Ichter and Danny Driess and Suraj Nair and Quan Vuong and Oier Mees and Chelsea Finn and Sergey Levine},
  year = {2025},
  eprint = {2501.09747},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2501.09747},
}

@misc{liu2024rdt,
  title = {{RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation}},
  author = {Songming Liu and Lingxuan Wu and Bangguo Li and Hengkai Tan and Huayu Chen and Zhengyi Wang and Ke Xu and Hang Su and Jun Zhu},
  year = {2024},
  eprint = {2410.07864},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.07864},
}

@misc{nvidia2025gr,
  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},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.14734},
}

@misc{shukor2025smolvla,
  title = {{SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics}},
  author = {Mustafa Shukor and Dana Aubakirova and Francesco Capuano and Pepijn Kooijmans and Steven Palma and Adil Zouitine and Michel Aractingi and Caroline Pascal and Martino Russi and Andres Marafioti and Simon Alibert and Matthieu Cord and Thomas Wolf and Remi Cadene},
  year = {2025},
  eprint = {2506.01844},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2506.01844},
}

@misc{team2025gemini,
  title = {{Gemini Robotics: Bringing AI into the Physical World}},
  author = {Gemini Robotics Team and Saminda Abeyruwan and Joshua Ainslie and Jean-Baptiste Alayrac and Montserrat Gonzalez Arenas and Travis Armstrong and Ashwin Balakrishna and Robert Baruch and Maria Bauza and Michiel Blokzijl and Steven Bohez and Konstantinos Bousmalis and Anthony Brohan and Thomas Buschmann and Arunkumar Byravan and Serkan Cabi and Ken Caluwaerts and Federico Casarini and Oscar Chang and Jose Enrique Chen and Xi Chen and Hao-Tien Lewis Chiang and Krzysztof Choromanski and David D'Ambrosio and Sudeep Dasari and Todor Davchev and Coline Devin and Norman Di Palo and Tianli Ding and Adil Dostmohamed and Danny Driess and Yilun Du and Debidatta Dwibedi and Michael Elabd and Claudio Fantacci and Cody Fong and Erik Frey and Chuyuan Fu and Marissa Giustina and Keerthana Gopalakrishnan and Laura Graesser and Leonard Hasenclever and Nicolas Heess and Brandon Hernaez and Alexander Herzog and R. Alex Hofer and Jan Humplik and Atil Iscen and Mithun George Jacob and Deepali Jain and others},
  year = {2025},
  eprint = {2503.20020},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.20020},
}

@misc{driess2023palm,
  title = {{PaLM-E: An Embodied Multimodal Language Model}},
  author = {Danny Driess and Fei Xia and Mehdi S. M. Sajjadi and Corey Lynch and Aakanksha Chowdhery and Brian Ichter and Ayzaan Wahid and Jonathan Tompson and Quan Vuong and Tianhe Yu and Wenlong Huang and Yevgen Chebotar and Pierre Sermanet and Daniel Duckworth and Sergey Levine and Vincent Vanhoucke and Karol Hausman and Marc Toussaint and Klaus Greff and Andy Zeng and Igor Mordatch and Pete Florence},
  year = {2023},
  eprint = {2303.03378},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2303.03378},
}

@misc{reed2022generalist,
  title = {{A Generalist Agent}},
  author = {Scott Reed and Konrad Zolna and Emilio Parisotto and Sergio Gomez Colmenarejo and Alexander Novikov and Gabriel Barth-Maron and Mai Gimenez and Yury Sulsky and Jackie Kay and Jost Tobias Springenberg and Tom Eccles and Jake Bruce and Ali Razavi and Ashley Edwards and Nicolas Heess and Yutian Chen and Raia Hadsell and Oriol Vinyals and Mahyar Bordbar and Nando de Freitas},
  year = {2022},
  eprint = {2205.06175},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2205.06175},
}

@misc{marrie2026reki,
  title = {{REKI: Registering Knowledge in VLAs}},
  author = {Juliette Marrie and Paul Pacaud and Adrien Ramanana Rahary and Shizhe Chen and Moritz Böhle},
  year = {2026},
  eprint = {2610.22178},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.22178},
}

@misc{sun2026ltm,
  title = {{LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models}},
  author = {Qixin Sun and WenLong Gao and Xiansheng Chen and Zhongyuan Wang and Si Liu and Pengwei Wang},
  year = {2026},
  eprint = {2610.21362},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.21362},
}

@misc{xu2026fastvla,
  title = {{FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action Models}},
  author = {Jiuyi Xu and Chengyuan Qian and Zhengzhong Tu and Yang Sui and Yangming Shi},
  year = {2026},
  eprint = {2610.22146},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.22146},
}

@misc{du2026nestedvla,
  title = {{NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models}},
  author = {Guodong Du and Wanyu Lin},
  year = {2026},
  eprint = {2610.23271},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23271},
}

@misc{li2024cogact,
  title = {{CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation}},
  author = {Qixiu Li and Yaobo Liang and Zeyu Wang and Lin Luo and Xi Chen and Mozheng Liao and Fangyun Wei and Yu Deng and Sicheng Xu and Yizhong Zhang and Xiaofan Wang and Bei Liu and Jianlong Fu and Jianmin Bao and Dong Chen and Yuanchun Shi and Jiaolong Yang and Baining Guo},
  year = {2024},
  eprint = {2411.19650},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2411.19650},
}

@misc{team2025robobrain,
  title = {{RoboBrain 2.0 Technical Report}},
  author = {BAAI RoboBrain Team and Mingyu Cao and Huajie Tan and Yuheng Ji and Xiansheng Chen and Minglan Lin and Zhiyu Li and Zhou Cao and Pengwei Wang and Enshen Zhou and Yi Han and Yingbo Tang and Xiangqi Xu and Wei Guo and Yaoxu Lyu and Yijie Xu and Jiayu Shi and Mengfei Du and Cheng Chi and Mengdi Zhao and Xiaoshuai Hao and Junkai Zhao and Xiaojie Zhang and Shanyu Rong and Huaihai Lyu and Zhengliang Cai and Yankai Fu and Ning Chen and Bolun Zhang and Lingfeng Zhang and Shuyi Zhang and Dong Liu and Xi Feng and Songjing Wang and Xiaodan Liu and Yance Jiao and Mengsi Lyu and Zhuo Chen and Chenrui He and Yulong Ao and Xue Sun and Zheqi He and Jingshu Zheng and Xi Yang and Donghai Shi and Kunchang Xie and Bochao Zhang and Shaokai Nie and Chunlei Men and Yonghua Lin and others},
  year = {2025},
  eprint = {2507.02029},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2507.02029},
}

@misc{lu2026vla,
  title = {{VLA-$Δ$: Learning Physical State Transition for Vision-Language-Action Models}},
  author = {Qi Lu and Jiarun Li and Ce Zhang and Miao Pan and Yi Pan and Xu Wang and Wenqi Zhang and Xuhong Zhang},
  year = {2026},
  eprint = {2610.21306},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.21306},
}

@misc{pham2026mambaact,
  title = {{MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action Models}},
  author = {Khuyen Pham and Tran Nguyen Le and Edoardo Fazzari and Cesare Stefanini},
  year = {2026},
  eprint = {2610.22951},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.22951},
}

@misc{shi2025hi,
  title = {{Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models}},
  author = {Lucy Xiaoyang Shi and Brian Ichter and Michael Equi and Liyiming Ke and Karl Pertsch and Quan Vuong and James Tanner and Anna Walling and Haohuan Wang and Niccolo Fusai and Adrian Li-Bell and Danny Driess and Lachy Groom and Sergey Levine and Chelsea Finn},
  year = {2025},
  eprint = {2502.19417},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.19417},
}

@misc{jiang2022vima,
  title = {{VIMA: General Robot Manipulation with Multimodal Prompts}},
  author = {Yunfan Jiang and Agrim Gupta and Zichen Zhang and Guanzhi Wang and Yongqiang Dou and Yanjun Chen and Li Fei-Fei and Anima Anandkumar and Yuke Zhu and Linxi Fan},
  year = {2022},
  eprint = {2210.03094},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2210.03094},
}

@misc{hong2026condensevla,
  title = {{CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA}},
  author = {Feiyang Hong and Yujie Wei and Bo Zhao and Xiu Su and Hongxun Yao and Shuo Yang},
  year = {2026},
  eprint = {2610.25927},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.25927},
}

@misc{cheang2025gr,
  title = {{GR-3 Technical Report}},
  author = {Chilam Cheang and Sijin Chen and Zhongren Cui and Yingdong Hu and Liqun Huang and Tao Kong and Hang Li and Yifeng Li and Yuxiao Liu and Xiao Ma and Hao Niu and Wenxuan Ou and Wanli Peng and Zeyu Ren and Haixin Shi and Jiawen Tian and Hongtao Wu and Xin Xiao and Yuyang Xiao and Jiafeng Xu and Yichu Yang},
  year = {2025},
  eprint = {2507.15493},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2507.15493},
}

@misc{bu2025univla,
  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},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.06111},
}

@misc{qu2025spatialvla,
  title = {{SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model}},
  author = {Delin Qu and Haoming Song and Qizhi Chen and Yuanqi Yao and Xinyi Ye and Yan Ding and Zhigang Wang and JiaYuan Gu and Bin Zhao and Dong Wang and Xuelong Li},
  year = {2025},
  eprint = {2501.15830},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2501.15830},
}

@misc{keller2026post,
  title = {{Post-hoc Epistemic Uncertainty for Vision-Language-Action Policies}},
  author = {Johannes Keller and Albrecht M. Bloße and Adrian Lindenmeyer and Thomas Neumuth and Daniel Schneider},
  year = {2026},
  eprint = {2610.29730},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29730},
}

@misc{sujit2026when,
  title = {{When One Step Is Enough: An Empirical Study of Euler Integration in Flow-Matching Policies}},
  author = {Shivakanth Sujit and Luca Nunziante and Rousslan Fernand Julien Dossa and Kai Arulkumaran},
  year = {2026},
  eprint = {2610.30735},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30735},
}

@misc{he2026vla,
  title = {{VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse}},
  author = {Sicheng He and Yi Pan and Qiuting Yu and Jiaming Huang and Qi Lu and Shuyan Wu and Hongyan Feng and Xuanyu Liu and Jun Zhang and Jie Zhang and Wenqi Zhang and Xuhong Zhang and Jianwei Yin},
  year = {2026},
  eprint = {2610.25043},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2610.25043},
}

@misc{sensenova2026has,
  title = {{Has GPT-6-Astra Achieved Embodied Intelligence?}},
  author = {SenseNova and Joint Research Team and Zhongang Cai and Ziang Cao and Tailai Chen and Han Chong Chua and Linjun Dai and Hanming Deng and Hokin Deng and Haiwen Diao and Chenjing Ding and Weichen Fan and Xiao Fu and Zerui Gong and Chenyang Gu and Zexin He and Zhi Hou and Bo Li and Qinyue Li and Quanzhou Li and Xiaowan Li and Zhichao Liao and Dahua Lin and Zilong Lin and Bo Liu and Chunxiao Liu and Pengfei Liu and Tianqi Liu and Ziwei Liu and Chen Change Loy and Lewei Lu and Jiapeng Luo and Yuexiao Ma and Liang Pan and Xingang Pan and Oscar Qian and Ziyi Shang and Yuyao Shao and Dawei Su and Dacheng Tao and Qingyi Tao and Quan Wang and Ruisi Wang and Xiaogang Wang and Ziyi Wang and Beichen Wen and Donghao Wu and Jiaxu Wu and Silei Wu and Xiaoming Wu and others},
  year = {2026},
  eprint = {2610.22471},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.22471},
}

@misc{ma2024survey,
  title = {{A Survey on Vision-Language-Action Models for Embodied AI}},
  author = {Yueen Ma and Zixing Song and Yuzheng Zhuang and Jianye Hao and Irwin King},
  year = {2024},
  eprint = {2405.14093},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2405.14093},
}

@misc{firoozi2023foundation,
  title = {{Foundation Models in Robotics: Applications, Challenges, and the Future}},
  author = {Roya Firoozi and Johnathan Tucker and Stephen Tian and Anirudha Majumdar and Jiankai Sun and Weiyu Liu and Yuke Zhu and Shuran Song and Ashish Kapoor and Karol Hausman and Brian Ichter and Danny Driess and Jiajun Wu and Cewu Lu and Mac Schwager},
  year = {2023},
  eprint = {2312.07843},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2312.07843},
}

@misc{liu2024aligning,
  title = {{Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI}},
  author = {Yang Liu and Weixing Chen and Yongjie Bai and Xiaodan Liang and Guanbin Li and Wen Gao and Liang Lin},
  year = {2024},
  eprint = {2407.06886},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2407.06886},
}

@misc{wang2026wave,
  title = {{WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction}},
  author = {Haomin Wang and Anqiong Ji and Ke Wang and Zhongshan Liu and Ru Ying and Ran Zheng and Zhipeng Zhang},
  year = {2026},
  eprint = {2610.18568},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.18568},
}

@misc{liu2026morphact,
  title = {{MorphAct: Robot Policies Morphing with the Worlds They Act In}},
  author = {Ziyan Liu and Jiting Liu and Weihong Zhong and Wenda Yu and Yeqiu Chen and Jason Li and Xiaojiang Peng and Shuyuan Hu and Kai Wang and Bo Zhao},
  year = {2026},
  eprint = {2610.20019},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.20019},
}

@misc{wang2026carryon,
  title = {{CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance}},
  author = {Zixuan Wang and Yuqi Liu and Yuxin Chen and Sengqiao Yang and Jinhui Ye and Pengguang Chen and Changsheng Lu and Shu Liu and Bei Yu and Jiaya Jia},
  year = {2026},
  eprint = {2610.21453},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.21453},
}

@misc{qin2026towards,
  title = {{Towards Agentic Robots: Model, Data, Environment, and Harness}},
  author = {Chonghan Qin and Dongming Wu and Kaituo Feng and Jiaxu Wang and Xinlei Yu and Peiwen Sun and Yijia Fan and Xilin He and Bingao Chen and Weitong Lian and Ryan Ji and Wenqi Ren and Xiaobin Hu and Dahua Lin and Yu-Gang Jiang and Xiangyu Yue},
  year = {2026},
  eprint = {2610.20442},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.20442},
}

@misc{chen2026multimodal,
  title = {{Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use}},
  author = {Yanzhe Chen and Ziyi Yang and Jifeng Zhu and Qiming Huang and Ruihe An and Peiyao Xu and Hesen Yang and Runda Liu and Chang Gong and Zhijun Cao and Zechen Bai and Wenzheng Zeng and Yiqi Lin and Guoqiang Liang and Kevin Yuchen Ma and Kevin Qinghong Lin and Mike Zheng Shou},
  year = {2026},
  eprint = {2610.30108},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30108},
}

@misc{lee2025molmoact,
  title = {{MolmoAct: Action Reasoning Models that can Reason in Space}},
  author = {Jason Lee and Jiafei Duan and Haoquan Fang and Yuquan Deng and Shuo Liu and Boyang Li and Bohan Fang and Jieyu Zhang and Yi Ru Wang and Sangho Lee and Winson Han and Wilbert Pumacay and Angelica Wu and Rose Hendrix and Karen Farley and Eli VanderBilt and Ali Farhadi and Dieter Fox and Ranjay Krishna},
  year = {2025},
  eprint = {2508.07917},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2508.07917},
}

@misc{deng2025graspvla,
  title = {{GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data}},
  author = {Shengliang Deng and Mi Yan and Songlin Wei and Haixin Ma and Yuxin Yang and Jiayi Chen and Zhiqi Zhang and Taoyu Yang and Xuheng Zhang and Wenhao Zhang and Heming Cui and Zhizheng Zhang and He Wang},
  year = {2025},
  eprint = {2505.03233},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.03233},
}

@misc{intelligence2025vla,
  title = {{π*0.6: a VLA That Learns From Experience}},
  author = {Physical Intelligence and Ali Amin and Raichelle Aniceto and Ashwin Balakrishna and Kevin Black and Ken Conley and Grace Connors and James Darpinian and Karan Dhabalia and Jared DiCarlo and Danny Driess and Michael Equi and Adnan Esmail and Yunhao Fang and Chelsea Finn and Catherine Glossop and Thomas Godden and Ivan Goryachev and Lachy Groom and Hunter Hancock and Karol Hausman and Gashon Hussein and Brian Ichter and Szymon Jakubczak and Rowan Jen and Tim Jones and Ben Katz and Liyiming Ke and Chandra Kuchi and Marinda Lamb and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Yao Lu and Vishnu Mano and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Charvi Sharma and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and Will Stoeckle and Alex Swerdlow and James Tanner and Marcel Torne and Quan Vuong and Anna Walling and others},
  year = {2025},
  eprint = {2511.14759},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2511.14759},
}

@misc{zheng2025x,
  title = {{X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model}},
  author = {Jinliang Zheng and Jianxiong Li and Zhihao Wang and Dongxiu Liu and Xirui Kang and Yuchun Feng and Yinan Zheng and Jiayin Zou and Yilun Chen and Jia Zeng and Ya-Qin Zhang and Jiangmiao Pang and Jingjing Liu and Tai Wang and Xianyuan Zhan},
  year = {2025},
  eprint = {2510.10274},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2510.10274},
}

@misc{chen2025internvla,
  title = {{InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy}},
  author = {Xinyi Chen and Yilun Chen and Yanwei Fu and Ning Gao and Jiaya Jia and Weiyang Jin and Hao Li and Yao Mu and Jiangmiao Pang and Yu Qiao and Yang Tian and Bin Wang and Bolun Wang and Fangjing Wang and Hanqing Wang and Tai Wang and Ziqin Wang and Xueyuan Wei and Chao Wu and Shuai Yang and Jinhui Ye and Junqiu Yu and Jia Zeng and Jingjing Zhang and Jinyu Zhang and Shi Zhang and Feng Zheng and Bowen Zhou and Yangkun Zhu},
  year = {2025},
  eprint = {2510.13778},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2510.13778},
}

@misc{yang2025magma,
  title = {{Magma: A Foundation Model for Multimodal AI Agents}},
  author = {Jianwei Yang and Reuben Tan and Qianhui Wu and Ruijie Zheng and Baolin Peng and Yongyuan Liang and Yu Gu and Mu Cai and Seonghyeon Ye and Joel Jang and Yuquan Deng and Lars Liden and Jianfeng Gao},
  year = {2025},
  eprint = {2502.13130},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2502.13130},
}

@misc{luo2025being,
  title = {{Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos}},
  author = {Hao Luo and Yicheng Feng and Wanpeng Zhang and Sipeng Zheng and Ye Wang and Haoqi Yuan and Jiazheng Liu and Chaoyi Xu and Qin Jin and Zongqing Lu},
  year = {2025},
  eprint = {2507.15597},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2507.15597},
}

@misc{zhai2025igniting,
  title = {{Igniting VLMs toward the Embodied Space}},
  author = {Andy Zhai and Brae Liu and Bruno Fang and Chalse Cai and Ellie Ma and Ethan Yin and Hao Wang and Hugo Zhou and James Wang and Lights Shi and Lucy Liang and Make Wang and Qian Wang and Roy Gan and Ryan Yu and Shalfun Li and Starrick Liu and Sylas Chen and Vincent Chen and Zach Xu},
  year = {2025},
  eprint = {2509.11766},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2509.11766},
}

@misc{wang2024scaling,
  title = {{Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers}},
  author = {Lirui Wang and Xinlei Chen and Jialiang Zhao and Kaiming He},
  year = {2024},
  eprint = {2409.20537},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2409.20537},
}

@misc{ye2024latent,
  title = {{Latent Action Pretraining from Videos}},
  author = {Seonghyeon Ye and Joel Jang and Byeongguk Jeon and Sejune Joo and Jianwei Yang and Baolin Peng and Ajay Mandlekar and Reuben Tan and Yu-Wei Chao and Bill Yuchen Lin and Lars Liden and Kimin Lee and Jianfeng Gao and Luke Zettlemoyer and Dieter Fox and Minjoon Seo},
  year = {2024},
  eprint = {2410.11758},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.11758},
}

@misc{li2025hamster,
  title = {{HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation}},
  author = {Yi Li and Yuquan Deng and Jesse Zhang and Joel Jang and Marius Memmel and Raymond Yu and Caelan Reed Garrett and Fabio Ramos and Dieter Fox and Anqi Li and Abhishek Gupta and Ankit Goyal},
  year = {2025},
  eprint = {2502.05485},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.05485},
}

@misc{zhen2024d,
  title = {{3D-VLA: A 3D Vision-Language-Action Generative World Model}},
  author = {Haoyu Zhen and Xiaowen Qiu and Peihao Chen and Jincheng Yang and Xin Yan and Yilun Du and Yining Hong and Chuang Gan},
  year = {2024},
  eprint = {2403.09631},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2403.09631},
}

@misc{dang2026rynnbrain,
  title = {{RynnBrain: Open Embodied Foundation Models}},
  author = {Ronghao Dang and Jiayan Guo and Bohan Hou and Sicong Leng and Kehan Li and Xin Li and Jiangpin Liu and Yunxuan Mao and Zhikai Wang and Yuqian Yuan and Minghao Zhu and Xiao Lin and Yang Bai and Qian Jiang and Yaxi Zhao and Minghua Zeng and Junlong Gao and Yuming Jiang and Jun Cen and Siteng Huang and Liuyi Wang and Wenqiao Zhang and Chengju Liu and Jianfei Yang and Shijian Lu and Deli Zhao},
  year = {2026},
  eprint = {2602.14979},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2602.14979},
}

@misc{singh2026full,
  title = {{Full-Weight VLA Fine-Tuning Without an fp32 Master Copy Silently Erases Most Updates}},
  author = {Shubham Singh},
  year = {2026},
  eprint = {2610.31859},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31859},
}

@misc{cheang2024gr,
  title = {{GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation}},
  author = {Chi-Lam Cheang and Guangzeng Chen and Ya Jing and Tao Kong and Hang Li and Yifeng Li and Yuxiao Liu and Hongtao Wu and Jiafeng Xu and Yichu Yang and Hanbo Zhang and Minzhao Zhu},
  year = {2024},
  eprint = {2410.06158},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.06158},
}

@misc{zheng2024tracevla,
  title = {{TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies}},
  author = {Ruijie Zheng and Yongyuan Liang and Shuaiyi Huang and Jianfeng Gao and Hal Daumé and Andrey Kolobov and Furong Huang and Jianwei Yang},
  year = {2024},
  eprint = {2412.10345},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.10345},
}

@misc{lin2025onetwovla,
  title = {{OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning}},
  author = {Fanqi Lin and Ruiqian Nai and Yingdong Hu and Jiacheng You and Junming Zhao and Yang Gao},
  year = {2025},
  eprint = {2505.11917},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.11917},
}

@misc{wen2025dexvla,
  title = {{DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control}},
  author = {Junjie Wen and Yichen Zhu and Jinming Li and Zhibin Tang and Chaomin Shen and Feifei Feng},
  year = {2025},
  eprint = {2502.05855},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.05855},
}

@misc{wen2024tinyvla,
  title = {{TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation}},
  author = {Junjie Wen and Yichen Zhu and Jinming Li and Minjie Zhu and Kun Wu and Zhiyuan Xu and Ning Liu and Ran Cheng and Chaomin Shen and Yaxin Peng and Feifei Feng and Jian Tang},
  year = {2024},
  eprint = {2409.12514},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2409.12514},
}

@misc{zhou2025chatvla,
  title = {{ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model}},
  author = {Zhongyi Zhou and Yichen Zhu and Minjie Zhu and Junjie Wen and Ning Liu and Zhiyuan Xu and Weibin Meng and Ran Cheng and Yaxin Peng and Chaomin Shen and Feifei Feng},
  year = {2025},
  eprint = {2502.14420},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.14420},
}

@misc{song2025hume,
  title = {{Hume: Introducing System-2 Thinking in Visual-Language-Action Model}},
  author = {Haoming Song and Delin Qu and Yuanqi Yao and Qizhi Chen and Qi Lv and Yiwen Tang and Modi Shi and Guanghui Ren and Maoqing Yao and Bin Zhao and Dong Wang and Xuelong Li},
  year = {2025},
  eprint = {2505.21432},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.21432},
}

@misc{im2025twinvla,
  title = {{TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models}},
  author = {Hokyun Im and Euijin Jeong and Andrey Kolobov and Jianlong Fu and Youngwoon Lee},
  year = {2025},
  eprint = {2511.05275},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2511.05275},
}

@misc{wang2025vq,
  title = {{VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers}},
  author = {Yating Wang and Haoyi Zhu and Mingyu Liu and Jiange Yang and Hao-Shu Fang and Tong He},
  year = {2025},
  eprint = {2507.01016},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2507.01016},
}

@misc{team2025gigabrain,
  title = {{GigaBrain-0: A World Model-Powered Vision-Language-Action Model}},
  author = {GigaBrain Team and Angen Ye and Boyuan Wang and Chaojun Ni and Guan Huang and Guosheng Zhao and Haoyun Li and Jie Li and Jiagang Zhu and Lv Feng and Peng Li and Qiuping Deng and Runqi Ouyang and Wenkang Qin and Xinze Chen and Xiaofeng Wang and Yang Wang and Yifan Li and Yilong Li and Yiran Ding and Yuan Xu and Yun Ye and Yukun Zhou and Zhehao Dong and Zhenan Wang and Zhichao Liu and Zheng Zhu},
  year = {2025},
  eprint = {2510.19430},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2510.19430},
}

@misc{jiang2025galaxea,
  title = {{Galaxea Open-World Dataset and G0 Dual-System VLA Model}},
  author = {Tao Jiang and Tianyuan Yuan and Yicheng Liu and Chenhao Lu and Jianning Cui and Xiao Liu and Shuiqi Cheng and Jiyang Gao and Huazhe Xu and Hang Zhao},
  year = {2025},
  eprint = {2509.00576},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2509.00576},
}

@misc{tan2025roboos,
  title = {{RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration}},
  author = {Huajie Tan and Xiaoshuai Hao and Cheng Chi and Minglan Lin and Yaoxu Lyu and Mingyu Cao and Dong Liang and Zhuo Chen and Mengsi Lyu and Cheng Peng and Chenrui He and Yulong Ao and Yonghua Lin and Pengwei Wang and Zhongyuan Wang and Shanghang Zhang},
  year = {2025},
  eprint = {2505.03673},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.03673},
}

@misc{espinola2026from,
  title = {{From Reasoning to Action: Benchmarking Frontier AI Models on LIBERO-10 Robot Manipulation Tasks}},
  author = {May Espinola and Qifan Zhang and Yu Xiang},
  year = {2026},
  eprint = {2610.30051},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30051},
}

@misc{lin2026fastharness,
  title = {{FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies}},
  author = {Tao Lin and Yuxin Du and Haoxiao Wang and Zile Zhong and Bo Zhao},
  year = {2026},
  eprint = {2610.31427},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31427},
}

@misc{zhang2026vision,
  title = {{Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation}},
  author = {Lingsen Zhang and Wei Li and Jie He and Henghua Zhang and Kai Mo and Shiyong Li and Yanpeng Wang and Rui Shao},
  year = {2026},
  eprint = {2610.25874},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25874},
}

@misc{yang2026coupling,
  title = {{Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies}},
  author = {Jiabing Yang and Yuan Xu and Yixiang Chen and Qisen Ma and Peiyan Li and Kai Wang and Chenhang Cui and Tao Yu and Zichen Wen and Wen Ye and Bowen Fang and Ziheng He and Xiangnan Wu and Yingda Li and Yan Huang and Liang Wang},
  year = {2026},
  eprint = {2610.32102},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32102},
}

@misc{yao2026profiling,
  title = {{Profiling a Frontier Agent with EBench: From Direct Control to Harness with Policy}},
  author = {Yifei Yao and Yude Zou and Guanbo Jiao and Xing Gao and Ning Gao and Yukai Wang and Jiantong Chen and Zihou Zhu and Xinyu Li and Ningyu Yan and Shuai Wang and Jianming Ma and Haoyu Guo and Weinan Zhang and Chunhua Shen},
  year = {2026},
  eprint = {2610.35832},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35832},
}

@misc{wang2026robot,
  title = {{Robot-Aligned 3D Gaussian Splatting for Precise Reaching with Wrist-Camera VLA Policies}},
  author = {Zuoxu Wang and Xiao Liang},
  year = {2026},
  eprint = {2610.35626},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35626},
}

@misc{qiu2026agq,
  title = {{AGQ: Action-Guided Ultra-Low-Bit Quantization for Vision-Language-Action Models}},
  author = {Xuhong Qiu and Zhuoyu Wu and Qiawei Zheng and Wenhui Ou and Wenqi Fang and Raphaël C. -W. Phan},
  year = {2026},
  eprint = {2610.33074},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.33074},
}

@misc{zhao2026rynnvla,
  title = {{RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions}},
  author = {Haoyu Zhao and Xingyue Zhao and Zhian Su and Bohan Hou and Yinzhou Tang and Fengyi Wang and Kehan Li and Yuming Jiang and Siteng Huang and Xin Li and Zhenyu Zeng and Mingxiu Chen and Deli Zhao and Zhongyu Li},
  year = {2026},
  eprint = {2610.34356},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34356},
}

@misc{zhang2026vista,
  title = {{VISTA: Active Exploration for Self-Improvement in Embodied Agents}},
  author = {Zhang Zhang and Shengjun Zhang and Simin Huang and Min Chen and Chong Xia and Xin Fei and Yueqi Duan},
  year = {2026},
  eprint = {2610.35051},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35051},
}

@misc{liu2026echo,
  title = {{Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models}},
  author = {Yufeng Liu and Bohao Fan and Juntu Zhao and Xinyi Wang and Hang Yu and Wenzhuan Luo and Yingzhi Wang and Qinghai Li and Yingdong Hu and Junliang Guo and Richard Wang and Dequan Wang and Yang Gao and Cheng Ma},
  year = {2026},
  eprint = {2610.31569},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31569},
}

@misc{hausdorfer2026multi,
  title = {{Multi-View Latent Action Pretraining for Cross-Embodiment Robot Learning from Videos}},
  author = {Oliver Hausdörfer and Felix Minzenmay and Mani Majd and Maximilian P. Christof and Shiyuan Zhang and Angela P. Schoellig},
  year = {2026},
  eprint = {2610.27794},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27794},
}

@misc{yu2026vision,
  title = {{Vision-Language-Action or World-Action? Just Action Models}},
  author = {Yonghao Yu and Lang Huang and Runyi Li and Toshihiko Yamasaki},
  year = {2026},
  eprint = {2610.37219},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.37219},
}

@misc{jeon2026pacevla,
  title = {{PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models}},
  author = {Hojin Jeon and Jimin Lee and Taekwan Kim and Nayoung Oh and Taeyoung Kim and Myungkyu Koo and Jinmo Koo and Joonwoo Ahn and Jinwoo Shin},
  year = {2026},
  eprint = {2610.25961},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25961},
}

@misc{team2026omnibrain,
  title = {{OmniBrain-0: A Unified Agentic Model for Embodied Intelligence}},
  author = {Xiaomi Embodied Intelligence Team and Yuechen Luo and Chong He and Fang Li and Shaoqing Xu and Jingkai Wang and Menglun Su and Jiaxin Liu and Shengyin Jiang and Zhiyi Lai and Long Chen and Longlong Wang and Liang Hu and Haochen Liu and Yuncheng Jiang and Hongwei Xie and Jieming Cui and Hanbing Li and Junjie Huang and Zhixiang Duan and Hexin Zhang and Weixiang Liang and Ying Gong and Yuhan Wang and Yong Pan and Pengna Li and Kangyi Wu and Ken Deng and Kun Ma and Fuxi Wen and Zhi-xin Yang and Hangjun Ye},
  year = {2026},
  eprint = {2610.36013},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2610.36013},
}

@misc{kim2026thinkworld,
  title = {{ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning}},
  author = {Chaehyun Kim and Chi-Pin Huang and Jisoo Kim and Min-Hung Chen and Yu-Chiang Frank Wang and Seungryong Kim and Fu-En Yang},
  year = {2026},
  eprint = {2610.37666},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37666},
}

@misc{quang2026retrieve,
  title = {{Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution}},
  author = {Pham Tri Quang and Bao-Ngoc Dao and Minh Duc Nguyen and Duc-Duy Nguyen and Hung T. Ho and Linh Dang Le and Trong-Bao Ho and Thien-Loc Ha and Tan Q. Nguyen and Tuan Dam and Vu N. Duong and Daniel Sonntag and Ngan Le and Khoa D. Doan and Jan Peters and An Thai Le and Duy M. H. Nguyen and Vien Anh Ngo},
  year = {2026},
  eprint = {2610.37215},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37215},
}

@misc{wang2026pdrvla,
  title = {{PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations}},
  author = {Hanqing Wang and Zhaotian Cai and Ruichuan An and Bohan Zeng and Tao Zhang and Yilin Chen and Xu Jiang and Kaiquan Chen and Chongyang Wu and Haoran Li and Fan Yang and Mingan Lin and Wentao Zhang and Zenan Zhou and Youzheng Wu},
  year = {2026},
  eprint = {2610.37381},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37381},
}

@misc{xu2026focusvla,
  title = {{FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models}},
  author = {Huixin Xu and Ziya Yu and Peng Li},
  year = {2026},
  eprint = {2610.31423},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31423},
}

@misc{chi2023diffusion,
  title = {{Diffusion Policy: Visuomotor Policy Learning via Action Diffusion}},
  author = {Cheng Chi and Zhenjia Xu and Siyuan Feng and Eric Cousineau and Yilun Du and Benjamin Burchfiel and Russ Tedrake and Shuran Song},
  year = {2023},
  eprint = {2303.04137},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2303.04137},
}

@misc{zhao2023learning,
  title = {{Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware}},
  author = {Tony Z. Zhao and Vikash Kumar and Sergey Levine and Chelsea Finn},
  year = {2023},
  eprint = {2304.13705},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2304.13705},
}

@misc{fu2024mobile,
  title = {{Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation}},
  author = {Zipeng Fu and Tony Z. Zhao and Chelsea Finn},
  year = {2024},
  eprint = {2401.02117},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2401.02117},
}

@misc{ze2024d,
  title = {{3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations}},
  author = {Yanjie Ze and Gu Zhang and Kangning Zhang and Chenyuan Hu and Muhan Wang and Huazhe Xu},
  year = {2024},
  eprint = {2403.03954},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.03954},
}

@misc{chi2024universal,
  title = {{Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots}},
  author = {Cheng Chi and Zhenjia Xu and Chuer Pan and Eric Cousineau and Benjamin Burchfiel and Siyuan Feng and Russ Tedrake and Shuran Song},
  year = {2024},
  eprint = {2402.10329},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2402.10329},
}

@misc{wang2024dexcap,
  title = {{DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation}},
  author = {Chen Wang and Haochen Shi and Weizhuo Wang and Ruohan Zhang and Li Fei-Fei and C. Karen Liu},
  year = {2024},
  eprint = {2403.07788},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.07788},
}

@misc{openai2018learning,
  title = {{Learning Dexterous In-Hand Manipulation}},
  author = {OpenAI and Marcin Andrychowicz and Bowen Baker and Maciek Chociej and Rafal Jozefowicz and Bob McGrew and Jakub Pachocki and Arthur Petron and Matthias Plappert and Glenn Powell and Alex Ray and Jonas Schneider and Szymon Sidor and Josh Tobin and Peter Welinder and Lilian Weng and Wojciech Zaremba},
  year = {2018},
  eprint = {1808.00177},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1808.00177},
}

@misc{openai2019solving,
  title = {{Solving Rubik's Cube with a Robot Hand}},
  author = {OpenAI and Ilge Akkaya and Marcin Andrychowicz and Maciek Chociej and Mateusz Litwin and Bob McGrew and Arthur Petron and Alex Paino and Matthias Plappert and Glenn Powell and Raphael Ribas and Jonas Schneider and Nikolas Tezak and Jerry Tworek and Peter Welinder and Lilian Weng and Qiming Yuan and Wojciech Zaremba and Lei Zhang},
  year = {2019},
  eprint = {1910.07113},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1910.07113},
}

@misc{chen2022visual,
  title = {{Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes}},
  author = {Tao Chen and Megha Tippur and Siyang Wu and Vikash Kumar and Edward Adelson and Pulkit Agrawal},
  year = {2022},
  eprint = {2211.11744},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2211.11744},
}

@misc{huang2023voxposer,
  title = {{VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models}},
  author = {Wenlong Huang and Chen Wang and Ruohan Zhang and Yunzhu Li and Jiajun Wu and Li Fei-Fei},
  year = {2023},
  eprint = {2307.05973},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2307.05973},
}

@misc{nair2022r,
  title = {{R3M: A Universal Visual Representation for Robot Manipulation}},
  author = {Suraj Nair and Aravind Rajeswaran and Vikash Kumar and Chelsea Finn and Abhinav Gupta},
  year = {2022},
  eprint = {2203.12601},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2203.12601},
}

@misc{jedlicki2026can,
  title = {{Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?}},
  author = {Jack B. Jedlicki and Amish Sethi and Heng Yang},
  year = {2026},
  eprint = {2610.17350},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.17350},
}

@misc{bronars2026blind,
  title = {{Blind Precise Assembly: Proprioceptive Sim-to-Real Peg-in-Hole for Diverse Parts}},
  author = {Antonia Bronars and Younghyo Park and Kushal Kedia and Pulkit Agrawal},
  year = {2026},
  eprint = {2610.23849},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23849},
}

@misc{huang2026beyond,
  title = {{Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations}},
  author = {Bo-Ruei Huang and Daniel Seita and Erdem Bıyık},
  year = {2026},
  eprint = {2610.17802},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.17802},
}

@misc{gao2026hexashell,
  title = {{HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents}},
  author = {Hongcheng Gao and Alex Zhou and Jay Zhu and Zelin Zheng and Shijia Ge and Xiping Li and Di Wu and Yazhe Wang and Jianshu Zeng and Xuan Shangguan and Yongli Wang and Yexing Wan and Lingyu He and Zhiqi Jia and Sihang Wu and Xiao He},
  year = {2026},
  eprint = {2610.23479},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23479},
}

@misc{wang2022dexgraspnet,
  title = {{DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation}},
  author = {Ruicheng Wang and Jialiang Zhang and Jiayi Chen and Yinzhen Xu and Puhao Li and Tengyu Liu and He Wang},
  year = {2022},
  eprint = {2210.02697},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2210.02697},
}

@misc{shafiullah2023bringing,
  title = {{On Bringing Robots Home}},
  author = {Nur Muhammad Mahi Shafiullah and Anant Rai and Haritheja Etukuru and Yiqian Liu and Ishan Misra and Soumith Chintala and Lerrel Pinto},
  year = {2023},
  eprint = {2311.16098},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2311.16098},
}

@misc{xiong2026modex,
  title = {{MoDex: Towards Universal Multi-Object Dexterous Grasping}},
  author = {Jing Xiong and Jiale Xie and Haoqi Yuan and Chaoyi Xu and Zongqing Lu},
  year = {2026},
  eprint = {2610.23888},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23888},
}

@misc{hu2026learn,
  title = {{Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning}},
  author = {Shuyuan Hu and Deng-Ke Wu and Yifan Jin and Qianhang Luo and Mingchen Ju and Kai Ye and Bo Zhao},
  year = {2026},
  eprint = {2610.26507},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.26507},
}

@misc{zeng2020transporter,
  title = {{Transporter Networks: Rearranging the Visual World for Robotic Manipulation}},
  author = {Andy Zeng and Pete Florence and Jonathan Tompson and Stefan Welker and Jonathan Chien and Maria Attarian and Travis Armstrong and Ivan Krasin and Dan Duong and Ayzaan Wahid and Vikas Sindhwani and Johnny Lee},
  year = {2020},
  eprint = {2010.14406},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2010.14406},
}

@misc{shridhar2021cliport,
  title = {{CLIPort: What and Where Pathways for Robotic Manipulation}},
  author = {Mohit Shridhar and Lucas Manuelli and Dieter Fox},
  year = {2021},
  eprint = {2109.12098},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.12098},
}

@misc{shridhar2022perceiver,
  title = {{Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation}},
  author = {Mohit Shridhar and Lucas Manuelli and Dieter Fox},
  year = {2022},
  eprint = {2209.05451},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2209.05451},
}

@misc{goyal2023rvt,
  title = {{RVT: Robotic View Transformer for 3D Object Manipulation}},
  author = {Ankit Goyal and Jie Xu and Yijie Guo and Valts Blukis and Yu-Wei Chao and Dieter Fox},
  year = {2023},
  eprint = {2306.14896},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2306.14896},
}

@misc{huang2024rekep,
  title = {{ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation}},
  author = {Wenlong Huang and Chen Wang and Yunzhu Li and Ruohan Zhang and Li Fei-Fei},
  year = {2024},
  eprint = {2409.01652},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2409.01652},
}

@misc{sundermeyer2021contact,
  title = {{Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes}},
  author = {Martin Sundermeyer and Arsalan Mousavian and Rudolph Triebel and Dieter Fox},
  year = {2021},
  eprint = {2103.14127},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2103.14127},
}

@misc{fang2022anygrasp,
  title = {{AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains}},
  author = {Hao-Shu Fang and Chenxi Wang and Hongjie Fang and Minghao Gou and Jirong Liu and Hengxu Yan and Wenhai Liu and Yichen Xie and Cewu Lu},
  year = {2022},
  eprint = {2212.08333},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2212.08333},
}

@misc{sun2026donic,
  title = {{DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations}},
  author = {Mingze Sun and Ziang Cao and Yuan Fei and Qiankuan Tao and Zihan Wang and Tianqi Liu and Junhao Chen and Haiwen Diao and Fangzhou Hong and Zhaoxi Chen and Ziwei Liu},
  year = {2026},
  eprint = {2610.29997},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29997},
}

@misc{du2026from,
  title = {{From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation}},
  author = {Tingwen Du and Haoyu Guo and Hanxue Zhang and Xuanxu Wang and Junting Dong and Chao Gao and Mingfei Han and Tao Lu and Mulin Yu and Chunhua Shen and Xiaojun Chang and Zhihui Li},
  year = {2026},
  eprint = {2610.29560},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29560},
}

@misc{kareer2024egomimic,
  title = {{EgoMimic: Scaling Imitation Learning via Egocentric Video}},
  author = {Simar Kareer and Dhruv Patel and Ryan Punamiya and Pranay Mathur and Shuo Cheng and Chen Wang and Judy Hoffman and Danfei Xu},
  year = {2024},
  eprint = {2410.24221},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.24221},
}

@misc{tian2024predictive,
  title = {{Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation}},
  author = {Yang Tian and Sizhe Yang and Jia Zeng and Ping Wang and Dahua Lin and Hao Dong and Jiangmiao Pang},
  year = {2024},
  eprint = {2412.15109},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.15109},
}

@misc{zhong2025dexgraspvla,
  title = {{DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping}},
  author = {Yifan Zhong and Xuchuan Huang and Ruochong Li and Ceyao Zhang and Zhang Chen and Tianrui Guan and Fanlian Zeng and Ka Num Lui and Yuyao Ye and Yitao Liang and Yaodong Yang and Yuanpei Chen},
  year = {2025},
  eprint = {2502.20900},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.20900},
}

@misc{tan2026forca,
  title = {{FORCA: A Force-Aware Coding Agent for Contact-Rich Robot Manipulation}},
  author = {Xiao Tan and Yixuan Wang and Zhexi Wang and Wenzhen Yuan},
  year = {2026},
  eprint = {2610.31841},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31841},
}

@misc{xiang2026contactbench,
  title = {{ContactBench 1.0: A Benchmark for Everyday Contact-Rich Robotic Manipulation}},
  author = {Jingyi Xiang and Yixuan Wang and Jeannette Bohg and Wenzhen Yuan},
  year = {2026},
  eprint = {2610.24512},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.24512},
}

@misc{yang2026cowboy,
  title = {{COWBOY: A Scalable Sim-to-Real Framework for Learning Contextual Whole-Body Manipulation}},
  author = {Jiahui Yang and Jason Jingzhou Liu and Ray Muxin Liu and Andrew E. Wang and Kenneth Shaw and Deepak Pathak and Ruslan Salakhutdinov},
  year = {2026},
  eprint = {2610.28948},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28948},
}

@misc{xu2026scaling,
  title = {{Scaling Dexterous Manipulation via Action Representation Pretraining}},
  author = {Yanjinghao Xu and Jiexin Zhang and Huan Zhao and Jianjia Mo and Zhenghao Yin and Dingkang Liang and Xiang Bai and Han Ding},
  year = {2026},
  eprint = {2610.34453},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34453},
}

@misc{adalibieke2026adadextrack,
  title = {{AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking}},
  author = {Jianibieke Adalibieke and Qianwei Han and Xueyi Liu and Yuzhe Qin and Li Yi},
  year = {2026},
  eprint = {2610.33852},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.33852},
}

@misc{yang2026adapolicy,
  title = {{AdaPolicy: Action-Driven Anticipatory Robot Policies via Next-Chunk Prediction}},
  author = {Fan Yang and Yuting Su and Chen Zhao and Fugui Fan and Peiguang Jing},
  year = {2026},
  eprint = {2610.34280},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34280},
}

@misc{saha2026long,
  title = {{Long-Horizon Multi-Object Rearrangement via Distilled Tree Search over Continuous Actions}},
  author = {Kallol Saha and Yining Hong and Amber Li and Yejin Choi and Maxim Likhachev and David Held},
  year = {2026},
  eprint = {2610.25785},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25785},
}

@misc{strong2026real,
  title = {{Real2Sem2Real: 3D Semantic Augmentations for Robot Learning from a Single Human RGB Demonstration}},
  author = {Matthew Strong and Ankush K. Dhawan and Julien Poffet and Giuse Pham and Jinho So and Monroe Kennedy},
  year = {2026},
  eprint = {2610.28880},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28880},
}

@misc{chuang2026pushing,
  title = {{Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well}},
  author = {Ian Chuang and Hiya Shah and Vamsi Chilamkur and Iman Soltani and Claire Tomlin},
  year = {2026},
  eprint = {2610.37652},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37652},
}

@misc{dai2026card,
  title = {{CARD: Contact-Anchored Retargeting for Dexterous Manipulation}},
  author = {Cunxi Dai and Botao He and Francois R Hogan and Wei Pan and Rao Fu and Wen-Han Hsieh and Ruoshi Liu and Jitendra Malik and Guanya Shi and Akash Sharma},
  year = {2026},
  eprint = {2610.36539},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36539},
}

@misc{chen2026robolongr,
  title = {{RoboLongR: Causally Consistent Rewards Teach Robots to Progressively Master Long-Horizon Manipulation}},
  author = {Zixuan Chen and Lin Cao and Fenggang Zhang and Haotong Zhang and Yangtao Chen and Jieqi Shi and Jing Huo and Yang Gao},
  year = {2026},
  eprint = {2610.33863},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.33863},
}

@misc{wu2026robostd,
  title = {{RoboSTD: Zero-Shot Single-to-Dual Transfer via Sagittal Mirroring for Bimanual Learning}},
  author = {Hongyu Wu and Chong Liu and Shaoxuan Xie and Shaqi Luo and Hanyu Feng and Shihan Wu and Guocai Yao},
  year = {2026},
  eprint = {2610.36685},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36685},
}

@misc{huang2026cuarms,
  title = {{cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation}},
  author = {Philip Huang and Fabio Ramos and Jiaoyang Li and Caelan Garrett and Lars Johannsmeier},
  year = {2026},
  eprint = {2610.36250},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36250},
}

@misc{lambeta2020digit,
  title = {{DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation}},
  author = {Mike Lambeta and Po-Wei Chou and Stephen Tian and Brian Yang and Benjamin Maloon and Victoria Rose Most and Dave Stroud and Raymond Santos and Ahmad Byagowi and Gregg Kammerer and Dinesh Jayaraman and Roberto Calandra},
  year = {2020},
  eprint = {2005.14679},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2005.14679},
}

@misc{wang2020tacto,
  title = {{TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors}},
  author = {Shaoxiong Wang and Mike Lambeta and Po-Wei Chou and Roberto Calandra},
  year = {2020},
  eprint = {2012.08456},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2012.08456},
}

@misc{higuera2024sparsh,
  title = {{Sparsh: Self-supervised touch representations for vision-based tactile sensing}},
  author = {Carolina Higuera and Akash Sharma and Chaithanya Krishna Bodduluri and Taosha Fan and Patrick Lancaster and Mrinal Kalakrishnan and Michael Kaess and Byron Boots and Mike Lambeta and Tingfan Wu and Mustafa Mukadam},
  year = {2024},
  eprint = {2410.24090},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.24090},
}

@misc{yang2024binding,
  title = {{Binding Touch to Everything: Learning Unified Multimodal Tactile Representations}},
  author = {Fengyu Yang and Chao Feng and Ziyang Chen and Hyoungseob Park and Daniel Wang and Yiming Dou and Ziyao Zeng and Xien Chen and Rit Gangopadhyay and Andrew Owens and Alex Wong},
  year = {2024},
  eprint = {2401.18084},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2401.18084},
}

@misc{huang2024d,
  title = {{3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing}},
  author = {Binghao Huang and Yixuan Wang and Xinyi Yang and Yiyue Luo and Yunzhu Li},
  year = {2024},
  eprint = {2410.24091},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.24091},
}

@misc{bhirangi2024anyskin,
  title = {{AnySkin: Plug-and-play Skin Sensing for Robotic Touch}},
  author = {Raunaq Bhirangi and Venkatesh Pattabiraman and Enes Erciyes and Yifeng Cao and Tess Hellebrekers and Lerrel Pinto},
  year = {2024},
  eprint = {2409.08276},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2409.08276},
}

@misc{bhirangi2021reskin,
  title = {{ReSkin: versatile, replaceable, lasting tactile skins}},
  author = {Raunaq Bhirangi and Tess Hellebrekers and Carmel Majidi and Abhinav Gupta},
  year = {2021},
  eprint = {2111.00071},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2111.00071},
}

@misc{yang2022touch,
  title = {{Touch and Go: Learning from Human-Collected Vision and Touch}},
  author = {Fengyu Yang and Chenyang Ma and Jiacheng Zhang and Jing Zhu and Wenzhen Yuan and Andrew Owens},
  year = {2022},
  eprint = {2211.12498},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2211.12498},
}

@misc{lambeta2024digitizing,
  title = {{Digitizing Touch with an Artificial Multimodal Fingertip}},
  author = {Mike Lambeta and Tingfan Wu and Ali Sengul and Victoria Rose Most and Nolan Black and Kevin Sawyer and Romeo Mercado and Haozhi Qi and Alexander Sohn and Byron Taylor and Norb Tydingco and Gregg Kammerer and Dave Stroud and Jake Khatha and Kurt Jenkins and Kyle Most and Neal Stein and Ricardo Chavira and Thomas Craven-Bartle and Eric Sanchez and Yitian Ding and Jitendra Malik and Roberto Calandra},
  year = {2024},
  eprint = {2411.02479},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2411.02479},
}

@misc{si2021taxim,
  title = {{Taxim: An Example-based Simulation Model for GelSight Tactile Sensors}},
  author = {Zilin Si and Wenzhen Yuan},
  year = {2021},
  eprint = {2109.04027},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.04027},
}

@misc{lin2022tactile,
  title = {{Tactile Gym 2.0: Sim-to-real Deep Reinforcement Learning for Comparing Low-cost High-Resolution Robot Touch}},
  author = {Yijiong Lin and John Lloyd and Alex Church and Nathan F. Lepora},
  year = {2022},
  eprint = {2207.10763},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2207.10763},
}

@misc{taylor2021gelslim,
  title = {{GelSlim 3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Finger}},
  author = {Ian Taylor and Siyuan Dong and Alberto Rodriguez},
  year = {2021},
  eprint = {2103.12269},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2103.12269},
}

@misc{lin2022dtact,
  title = {{DTact: A Vision-Based Tactile Sensor that Measures High-Resolution 3D Geometry Directly from Darkness}},
  author = {Changyi Lin and Ziqi Lin and Shaoxiong Wang and Huazhe Xu},
  year = {2022},
  eprint = {2209.13916},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2209.13916},
}

@misc{lin2023dtact,
  title = {{9DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimation}},
  author = {Changyi Lin and Han Zhang and Jikai Xu and Lei Wu and Huazhe Xu},
  year = {2023},
  eprint = {2308.14277},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2308.14277},
}

@misc{lee2018making,
  title = {{Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks}},
  author = {Michelle A. Lee and Yuke Zhu and Krishnan Srinivasan and Parth Shah and Silvio Savarese and Li Fei-Fei and Animesh Garg and Jeannette Bohg},
  year = {2018},
  eprint = {1810.10191},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1810.10191},
}

@misc{li2022see,
  title = {{See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation}},
  author = {Hao Li and Yizhi Zhang and Junzhe Zhu and Shaoxiong Wang and Michelle A Lee and Huazhe Xu and Edward Adelson and Li Fei-Fei and Ruohan Gao and Jiajun Wu},
  year = {2022},
  eprint = {2212.03858},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2212.03858},
}

@misc{fu2024touch,
  title = {{A Touch, Vision, and Language Dataset for Multimodal Alignment}},
  author = {Letian Fu and Gaurav Datta and Huang Huang and William Chung-Ho Panitch and Jaimyn Drake and Joseph Ortiz and Mustafa Mukadam and Mike Lambeta and Roberto Calandra and Ken Goldberg},
  year = {2024},
  eprint = {2402.13232},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2402.13232},
}

@misc{qi2023general,
  title = {{General In-Hand Object Rotation with Vision and Touch}},
  author = {Haozhi Qi and Brent Yi and Sudharshan Suresh and Mike Lambeta and Yi Ma and Roberto Calandra and Jitendra Malik},
  year = {2023},
  eprint = {2309.09979},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.09979},
}

@misc{akinola2024tacsl,
  title = {{TacSL: A Library for Visuotactile Sensor Simulation and Learning}},
  author = {Iretiayo Akinola and Jie Xu and Jan Carius and Dieter Fox and Yashraj Narang},
  year = {2024},
  eprint = {2408.06506},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2408.06506},
}

@misc{yin2023rotating,
  title = {{Rotating without Seeing: Towards In-hand Dexterity through Touch}},
  author = {Zhao-Heng Yin and Binghao Huang and Yuzhe Qin and Qifeng Chen and Xiaolong Wang},
  year = {2023},
  eprint = {2303.10880},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2303.10880},
}

@misc{yuan2023robot,
  title = {{Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensing}},
  author = {Ying Yuan and Haichuan Che and Yuzhe Qin and Binghao Huang and Zhao-Heng Yin and Kang-Won Lee and Yi Wu and Soo-Chul Lim and Xiaolong Wang},
  year = {2023},
  eprint = {2312.01853},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2312.01853},
}

@misc{suresh2023neural,
  title = {{Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation}},
  author = {Sudharshan Suresh and Haozhi Qi and Tingfan Wu and Taosha Fan and Luis Pineda and Mike Lambeta and Jitendra Malik and Mrinal Kalakrishnan and Roberto Calandra and Michael Kaess and Joseph Ortiz and Mustafa Mukadam},
  year = {2023},
  eprint = {2312.13469},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2312.13469},
}

@misc{xue2025reactive,
  title = {{Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation}},
  author = {Han Xue and Jieji Ren and Wendi Chen and Gu Zhang and Yuan Fang and Guoying Gu and Huazhe Xu and Cewu Lu},
  year = {2025},
  eprint = {2503.02881},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.02881},
}

@misc{slepyan2026opentac,
  title = {{OpenTac: An Open Ecosystem for Customizable, Scalable, and Transferable 3D Tactile Sensing}},
  author = {Ariel Slepyan and Geeta Chandra Raju Bethala and Jiafeng Gu and Anagha Rajendra Dangle and Yinzhe Zhou and Hongyuan Fu and Jade Sim and Tuhin Basu and Xinyi Yin and Md Faizal Karim and Gregory Hager and Homanga Bharadhwaj and Anand Bhattad and Krishna Murthy Jatavallabhula and Nitish V. Thakor},
  year = {2026},
  eprint = {2610.31661},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31661},
}

@misc{wang2026gelslim,
  title = {{GelSlim 5.0: Unifying Vision and Touch with a Single Fingertip Camera}},
  author = {Xiangdong Wang and I-Hsuan Huang and Xiaohao Xu and Xili Yi and Nima Fazeli and Xiaonan Huang},
  year = {2026},
  eprint = {2610.31334},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31334},
}

@misc{xiang2026tactile,
  title = {{Tactile-Based Robotic Manipulation: From Mechanics-Driven to Data-Driven Perspectives}},
  author = {Jingyi Xiang and Yixuan Wang and Wenzhen Yuan},
  year = {2026},
  eprint = {2610.30438},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30438},
}

@misc{hou2026vectile,
  title = {{VecTile: A Low-Cost Flexible Tactile Array for 3-DoF Force Sensing}},
  author = {Jian Hou and Xin Zhou and Adam J. Spiers},
  year = {2026},
  eprint = {2610.31472},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31472},
}

@misc{ma2026acts,
  title = {{ACTS: Learning Visuo-Tactile World Models from Human Physical Interaction}},
  author = {Yuxiang Ma and Weihan Xu and Pengfei Ye and Anna Mei and Yuxin Ray Song and Tingle Li and Haonan Chen and Edward H. Adelson},
  year = {2026},
  eprint = {2610.24285},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.24285},
}

@misc{rudin2021learning,
  title = {{Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning}},
  author = {Nikita Rudin and David Hoeller and Philipp Reist and Marco Hutter},
  year = {2021},
  eprint = {2109.11978},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.11978},
}

@misc{lee2020learning,
  title = {{Learning Quadrupedal Locomotion over Challenging Terrain}},
  author = {Joonho Lee and Jemin Hwangbo and Lorenz Wellhausen and Vladlen Koltun and Marco Hutter},
  year = {2020},
  eprint = {2010.11251},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2010.11251},
}

@misc{hwangbo2019learning,
  title = {{Learning Agile and Dynamic Motor Skills for Legged Robots}},
  author = {Jemin Hwangbo and Joonho Lee and Alexey Dosovitskiy and Dario Bellicoso and Vassilios Tsounis and Vladlen Koltun and Marco Hutter},
  year = {2019},
  eprint = {1901.08652},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1901.08652},
}

@misc{kumar2021rma,
  title = {{RMA: Rapid Motor Adaptation for Legged Robots}},
  author = {Ashish Kumar and Zipeng Fu and Deepak Pathak and Jitendra Malik},
  year = {2021},
  eprint = {2107.04034},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2107.04034},
}

@misc{zhuang2023robot,
  title = {{Robot Parkour Learning}},
  author = {Ziwen Zhuang and Zipeng Fu and Jianren Wang and Christopher Atkeson and Soeren Schwertfeger and Chelsea Finn and Hang Zhao},
  year = {2023},
  eprint = {2309.05665},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.05665},
}

@misc{cheng2023extreme,
  title = {{Extreme Parkour with Legged Robots}},
  author = {Xuxin Cheng and Kexin Shi and Ananye Agarwal and Deepak Pathak},
  year = {2023},
  eprint = {2309.14341},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.14341},
}

@misc{radosavovic2023real,
  title = {{Real-World Humanoid Locomotion with Reinforcement Learning}},
  author = {Ilija Radosavovic and Tete Xiao and Bike Zhang and Trevor Darrell and Jitendra Malik and Koushil Sreenath},
  year = {2023},
  eprint = {2303.03381},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2303.03381},
}

@misc{cheng2024expressive,
  title = {{Expressive Whole-Body Control for Humanoid Robots}},
  author = {Xuxin Cheng and Yandong Ji and Junming Chen and Ruihan Yang and Ge Yang and Xiaolong Wang},
  year = {2024},
  eprint = {2402.16796},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2402.16796},
}

@misc{he2024learning,
  title = {{Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation}},
  author = {Tairan He and Zhengyi Luo and Wenli Xiao and Chong Zhang and Kris Kitani and Changliu Liu and Guanya Shi},
  year = {2024},
  eprint = {2403.04436},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.04436},
}

@misc{fu2024humanplus,
  title = {{HumanPlus: Humanoid Shadowing and Imitation from Humans}},
  author = {Zipeng Fu and Qingqing Zhao and Qi Wu and Gordon Wetzstein and Chelsea Finn},
  year = {2024},
  eprint = {2406.10454},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2406.10454},
}

@misc{he2025asap,
  title = {{ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills}},
  author = {Tairan He and Jiawei Gao and Wenli Xiao and Yuanhang Zhang and Zi Wang and Jiashun Wang and Zhengyi Luo and Guanqi He and Nikhil Sobanbab and Chaoyi Pan and Zeji Yi and Guannan Qu and Kris Kitani and Jessica Hodgins and Linxi "Jim" Fan and Yuke Zhu and Changliu Liu and Guanya Shi},
  year = {2025},
  eprint = {2502.01143},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.01143},
}

@misc{liao2026supermimic,
  title = {{SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model}},
  author = {Qiayuan Liao and Yiyang Shao and Junfeng Long and Kevin Zakka and Roberto Horowitz and Pieter Abbeel and Koushil Sreenath},
  year = {2026},
  eprint = {2610.28480},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28480},
}

@misc{miki2022learning,
  title = {{Learning robust perceptive locomotion for quadrupedal robots in the wild}},
  author = {Takahiro Miki and Joonho Lee and Jemin Hwangbo and Lorenz Wellhausen and Vladlen Koltun and Marco Hutter},
  year = {2022},
  eprint = {2201.08117},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2201.08117},
}

@misc{he2024omnih,
  title = {{OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning}},
  author = {Tairan He and Zhengyi Luo and Xialin He and Wenli Xiao and Chong Zhang and Weinan Zhang and Kris Kitani and Changliu Liu and Guanya Shi},
  year = {2024},
  eprint = {2406.08858},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2406.08858},
}

@misc{he2024hover,
  title = {{HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots}},
  author = {Tairan He and Wenli Xiao and Toru Lin and Zhengyi Luo and Zhenjia Xu and Zhenyu Jiang and Jan Kautz and Changliu Liu and Guanya Shi and Xiaolong Wang and Linxi Fan and Yuke Zhu},
  year = {2024},
  eprint = {2410.21229},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.21229},
}

@misc{margolis2022walk,
  title = {{Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior}},
  author = {Gabriel B Margolis and Pulkit Agrawal},
  year = {2022},
  eprint = {2212.03238},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2212.03238},
}

@misc{nahrendra2023dreamwaq,
  title = {{DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning}},
  author = {I Made Aswin Nahrendra and Byeongho Yu and Hyun Myung},
  year = {2023},
  eprint = {2301.10602},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2301.10602},
}

@misc{hoeller2023anymal,
  title = {{ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots}},
  author = {David Hoeller and Nikita Rudin and Dhionis Sako and Marco Hutter},
  year = {2023},
  eprint = {2306.14874},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2306.14874},
}

@misc{zhuang2024humanoid,
  title = {{Humanoid Parkour Learning}},
  author = {Ziwen Zhuang and Shenzhe Yao and Hang Zhao},
  year = {2024},
  eprint = {2406.10759},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2406.10759},
}

@misc{heyrman2026watch,
  title = {{Watch Your Step: Anticipated Perception for Humanoid Locomotion}},
  author = {Matthias Heyrman and Chenhao Li and Ioannis Dadiotis and Marco Hutter},
  year = {2026},
  eprint = {2610.29612},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29612},
}

@misc{peng2021amp,
  title = {{AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control}},
  author = {Xue Bin Peng and Ze Ma and Pieter Abbeel and Sergey Levine and Angjoo Kanazawa},
  year = {2021},
  eprint = {2104.02180},
  archivePrefix = {arXiv},
  primaryClass = {cs.GR},
  url = {https://arxiv.org/abs/2104.02180},
}

@misc{he2024agile,
  title = {{Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion}},
  author = {Tairan He and Chong Zhang and Wenli Xiao and Guanqi He and Changliu Liu and Guanya Shi},
  year = {2024},
  eprint = {2401.17583},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2401.17583},
}

@misc{team2026scaling,
  title = {{$λ_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation}},
  author = {Lambda-humanoid Team and : and Chongyang Xu and Jin Chen and Jinhui Ye and Yilun Chen and Yiming Jiang and Zhao Wu and Hu Wei and Lin Qu and Shifeng Zhang and Yisheng He and Yuming Jiang and Zenan Meng and Zheng Wu and Mu Xu and Steven Hoi},
  year = {2026},
  eprint = {2610.18950},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.18950},
}

@misc{liao2025beyondmimic,
  title = {{BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion}},
  author = {Qiayuan Liao and Takara E. Truong and Xiaoyu Huang and Yuman Gao and Guy Tevet and Koushil Sreenath and C. Karen Liu},
  year = {2025},
  eprint = {2508.08241},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2508.08241},
}

@misc{he2026vit,
  title = {{ViT-H: Generative Video-To-Humanoid Control with Motion Tracking Feedback}},
  author = {Zimo He and Tianyi Bian and Zizhong Yang and Hongjie Li and Nan Jiang and Jieming Cui and Baoxiong Jia and Yizhou Wang and Siyuan Huang and Yixin Zhu},
  year = {2026},
  eprint = {2610.32966},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32966},
}

@misc{amiet2026solving,
  title = {{Solving a Giant Rubik's Cube with a Quadruped Robot}},
  author = {Lukas Amiet and Gabriel Sánchez-Blanco Repgen and Mayank Mittal and Victor Klemm and Andrei Cramariuc and Marco Hutter and Cesar Cadena},
  year = {2026},
  eprint = {2610.24610},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.24610},
}

@misc{li2026learning,
  title = {{Learning Force-Reactive Humanoid Loco-Manipulation}},
  author = {Sihang Li and Xiaofeng Guo and Jinkun Cao and Charlie Cheng and Ruihan Yang and Chen Feng and Guanya Shi and Haozhi Qi},
  year = {2026},
  eprint = {2610.35862},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35862},
}

@misc{yang2026zero,
  title = {{Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data}},
  author = {Dianyi Yang and Mengya Liu and Zhumei Wang and Yu Liu and Xiaochen Zhang and Yixuan Li and Le Ma and Yuhang Yang and Weiqi Huang and Wei Liang and Baoxiong Jia and Siyuan Huang},
  year = {2026},
  eprint = {2610.35075},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35075},
}

@misc{chen2026humanoidndm,
  title = {{HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model}},
  author = {Chao Chen and Zhenrong Wang and Jilong Wang and Yusen Feng and Jiangran Lyu and Li Yi and He Wang},
  year = {2026},
  eprint = {2610.34126},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34126},
}

@misc{kim2026differentiable,
  title = {{Differentiable Contact Dynamics for Legged Locomotion: Policy Learning and Contact-Implicit Trajectory Optimization}},
  author = {Gijeong Kim and Seungbin Oh and Dongyun Kang and Hae-Won Park},
  year = {2026},
  eprint = {2610.35852},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35852},
}

@misc{cao2026humit,
  title = {{HuMiT: Low-Latency Whole-Body Humanoid Teleoperation via Compact Reference Tracking}},
  author = {Liu Cao and Botian Xu and Ruoqu Chen and Jiajun Liu and Mingzhi Pei and Zihao Wang and Zhongyu Li and Mengdi Xu},
  year = {2026},
  eprint = {2610.29903},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29903},
}

@misc{yi2026swap,
  title = {{SWAP: Test-Time Steerable Humanoid Whole-Body Collision Avoidance}},
  author = {Zeji Yi and Guanqi He and Xiaofeng Guo and Guannan Qu and Pieter Abbeel and Yan Duan and Karen Liu and Guanya Shi},
  year = {2026},
  eprint = {2610.25711},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25711},
}

@misc{lin2026action,
  title = {{Action-Aligned Latent Planning for Versatile Humanoid Loco-Manipulation}},
  author = {Yutang Lin and Guanya Shi and C. Karen Liu},
  year = {2026},
  eprint = {2610.24675},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.24675},
}

@misc{xu2026reach,
  title = {{REACH: An RL-based Hierarchical Humanoid Crawling Framework for Adaptable Confined Space Traversal}},
  author = {Shengzhang Xu and Yuning Guo and Weiyi Hu and Yifeng Xu and Zhongyu Li and He Kong},
  year = {2026},
  eprint = {2610.36546},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36546},
}

@misc{li2026graft,
  title = {{GRAFT: Geometry-Aware Residual Adaptation for Foundation Trackers}},
  author = {Liang Li and Guoyao Zhang and Xingyu Chen and Sikai Wu and Qianyang Wu and Yuhang Lin and Renjing Xu and Mingliang Zhou and Diyun Xiang},
  year = {2026},
  eprint = {2610.36507},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36507},
}

@misc{drolet2026whole,
  title = {{Whole-Body Humanoid Control via Stochastic Motion Tokenization}},
  author = {Michael Drolet and Oleg Arenz and Jan Peters},
  year = {2026},
  eprint = {2610.36452},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36452},
}

@misc{azulay2026test,
  title = {{Test-Time Motion Steering for Perceptive Humanoid Fall Recovery}},
  author = {Osher Azulay and Cheng-Lin Hsieh and Stella X. Yu},
  year = {2026},
  eprint = {2610.30061},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30061},
}

@misc{ha2018world,
  title = {{World Models}},
  author = {David Ha and Jürgen Schmidhuber},
  year = {2018},
  eprint = {1803.10122},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1803.10122},
}

@misc{hafner2023mastering,
  title = {{Mastering Diverse Domains through World Models}},
  author = {Danijar Hafner and Jurgis Pasukonis and Jimmy Ba and Timothy Lillicrap},
  year = {2023},
  eprint = {2301.04104},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2301.04104},
}

@misc{wu2022daydreamer,
  title = {{DayDreamer: World Models for Physical Robot Learning}},
  author = {Philipp Wu and Alejandro Escontrela and Danijar Hafner and Ken Goldberg and Pieter Abbeel},
  year = {2022},
  eprint = {2206.14176},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2206.14176},
}

@misc{yang2023learning,
  title = {{Learning Interactive Real-World Simulators}},
  author = {Sherry Yang and Yilun Du and Kamyar Ghasemipour and Jonathan Tompson and Leslie Kaelbling and Dale Schuurmans and Pieter Abbeel},
  year = {2023},
  eprint = {2310.06114},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2310.06114},
}

@misc{bruce2024genie,
  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},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2402.15391},
}

@misc{nvidia2025cosmos,
  title = {{Cosmos World Foundation Model Platform for Physical AI}},
  author = {NVIDIA and : and Niket Agarwal and Arslan Ali and Maciej Bala and Yogesh Balaji and Erik Barker and Tiffany Cai and Prithvijit Chattopadhyay and Yongxin Chen and Yin Cui and Yifan Ding and Daniel Dworakowski and Jiaojiao Fan and Michele Fenzi and Francesco Ferroni and Sanja Fidler and Dieter Fox and Songwei Ge and Yunhao Ge and Jinwei Gu and Siddharth Gururani and Ethan He and Jiahui Huang and Jacob Huffman and Pooya Jannaty and Jingyi Jin and Seung Wook Kim and Gergely Klár and Grace Lam and Shiyi Lan and Laura Leal-Taixe and Anqi Li and Zhaoshuo Li and Chen-Hsuan Lin and Tsung-Yi Lin and Huan Ling and Ming-Yu Liu and Xian Liu and Alice Luo and Qianli Ma and Hanzi Mao and Kaichun Mo and Arsalan Mousavian and Seungjun Nah and Sriharsha Niverty and David Page and Despoina Paschalidou and Zeeshan Patel and Lindsey Pavao and others},
  year = {2025},
  eprint = {2501.03575},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2501.03575},
}

@misc{assran2025v,
  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},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2506.09985},
}

@misc{hafner2019dream,
  title = {{Dream to Control: Learning Behaviors by Latent Imagination}},
  author = {Danijar Hafner and Timothy Lillicrap and Jimmy Ba and Mohammad Norouzi},
  year = {2019},
  eprint = {1912.01603},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1912.01603},
}

@misc{hansen2023td,
  title = {{TD-MPC2: Scalable, Robust World Models for Continuous Control}},
  author = {Nicklas Hansen and Hao Su and Xiaolong Wang},
  year = {2023},
  eprint = {2310.16828},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2310.16828},
}

@misc{zhou2024dino,
  title = {{DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning}},
  author = {Gaoyue Zhou and Hengkai Pan and Yann LeCun and Lerrel Pinto},
  year = {2024},
  eprint = {2411.04983},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2411.04983},
}

@misc{liu2026ropedia,
  title = {{Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience}},
  author = {Tianqi Liu and Hanfei Zhao and Qifeng Liang and Hui En Pang and Jiarui Xu and Sayang Mu and Penghao Qiu and YingSheng Zhang and Jun Wang and Ziang Cao and Mingze Sun and Yukang Cao and Fangzhou Hong and Zhaoxi Chen and Ziwei Liu},
  year = {2026},
  eprint = {2610.26855},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.26855},
}

@misc{mei2026robotic,
  title = {{Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions}},
  author = {Zhiting Mei and Tenny Yin and Ola Shorinwa and Apurva Badithela and Zhonghe Zheng and Joseph Bruno and Madison Bland and Lihan Zha and Asher Hancock and Jaime Fernández Fisac and Philip Dames and Anirudha Majumdar},
  year = {2026},
  eprint = {2601.07823},
  archivePrefix = {arXiv},
  primaryClass = {eess.SY},
  url = {https://arxiv.org/abs/2601.07823},
}

@misc{hafner2018learning,
  title = {{Learning Latent Dynamics for Planning from Pixels}},
  author = {Danijar Hafner and Timothy Lillicrap and Ian Fischer and Ruben Villegas and David Ha and Honglak Lee and James Davidson},
  year = {2018},
  eprint = {1811.04551},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1811.04551},
}

@misc{hafner2020mastering,
  title = {{Mastering Atari with Discrete World Models}},
  author = {Danijar Hafner and Timothy Lillicrap and Mohammad Norouzi and Jimmy Ba},
  year = {2020},
  eprint = {2010.02193},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2010.02193},
}

@misc{micheli2022transformers,
  title = {{Transformers are Sample-Efficient World Models}},
  author = {Vincent Micheli and Eloi Alonso and François Fleuret},
  year = {2022},
  eprint = {2209.00588},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2209.00588},
}

@misc{du2023learning,
  title = {{Learning Universal Policies via Text-Guided Video Generation}},
  author = {Yilun Du and Mengjiao Yang and Bo Dai and Hanjun Dai and Ofir Nachum and Joshua B. Tenenbaum and Dale Schuurmans and Pieter Abbeel},
  year = {2023},
  eprint = {2302.00111},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2302.00111},
}

@misc{hansen2022temporal,
  title = {{Temporal Difference Learning for Model Predictive Control}},
  author = {Nicklas Hansen and Xiaolong Wang and Hao Su},
  year = {2022},
  eprint = {2203.04955},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2203.04955},
}

@misc{ding2026cw,
  title = {{CW-WAM: A Structured Contact-Wrench World Action Model for Force-Sensitive Manipulation}},
  author = {Houzhu Ding and Xinda Qi and Luqi Wang and Ming Yang},
  year = {2026},
  eprint = {2610.30117},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30117},
}

@misc{wu2023unleashing,
  title = {{Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation}},
  author = {Hongtao Wu and Ya Jing and Chilam Cheang and Guangzeng Chen and Jiafeng Xu and Xinghang Li and Minghuan Liu and Hang Li and Tao Kong},
  year = {2023},
  eprint = {2312.13139},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2312.13139},
}

@misc{hu2024video,
  title = {{Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations}},
  author = {Yucheng Hu and Yanjiang Guo and Pengchao Wang and Xiaoyu Chen and Yen-Jen Wang and Jianke Zhang and Koushil Sreenath and Chaochao Lu and Jianyu Chen},
  year = {2024},
  eprint = {2412.14803},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2412.14803},
}

@misc{li2025unified,
  title = {{Unified Video Action Model}},
  author = {Shuang Li and Yihuai Gao and Dorsa Sadigh and Shuran Song},
  year = {2025},
  eprint = {2503.00200},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.00200},
}

@misc{cen2025worldvla,
  title = {{WorldVLA: Towards Autoregressive Action World Model}},
  author = {Jun Cen and Chaohui Yu and Hangjie Yuan and Yuming Jiang and Siteng Huang and Jiayan Guo and Xin Li and Yibing Song and Hao Luo and Fan Wang and Deli Zhao and Hao Chen},
  year = {2025},
  eprint = {2506.21539},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.21539},
}

@misc{liao2025genie,
  title = {{Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation}},
  author = {Yue Liao and Pengfei Zhou and Siyuan Huang and Donglin Yang and Shengcong Chen and Yuxin Jiang and Yue Hu and Jingbin Cai and Si Liu and Jianlan Luo and Liliang Chen and Shuicheng Yan and Maoqing Yao and Guanghui Ren},
  year = {2025},
  eprint = {2508.05635},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2508.05635},
}

@misc{tian2026uniflowwam,
  title = {{UniFlowWAM: A Unified World-Action Model with Visual Semantics and 4D Geometry}},
  author = {Jialin Tian and Zhuofan Li and Xinkai Wang and Bokai Lin and Chenyi Wang and Xinyu Zhan and Cewu Lu and Lixin Yang},
  year = {2026},
  eprint = {2610.30991},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30991},
}

@misc{sidorov2026greenwam,
  title = {{GreenWAM: A World Foundation Model for Robotics}},
  author = {Gennady Sidorov and Valerii Kornilov and Denis Grankin and Polina Fedotova and Aleksey Postnikov},
  year = {2026},
  eprint = {2610.18774},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.18774},
}

@misc{jang2026self,
  title = {{Self-Distilling Future Video Representations for World Action Models}},
  author = {Huiwon Jang and Suhyeok Jang and Hyeonmo Kang and Seungku Kim and Jinwoo Shin and Sihyun Yu},
  year = {2026},
  eprint = {2610.30320},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30320},
}

@misc{liu2026agentic,
  title = {{Agentic World Action Models}},
  author = {Zhuoyang Liu and Dantong Niu and Botong Zhang and Boning Shao and Jing Wang and Ruijie Zheng and Yuvan Sharma and Runyu Lu and Jiaming Liu and Renrui Zhang and Roei Herzig and Yutong Bai and Ken Goldberg and Danfei Xu and Yuke Zhu and Guanzhi Wang and Linxi "Jim" Fan and Trevor Darrell},
  year = {2026},
  eprint = {2610.30136},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30136},
}

@misc{lv2026skeleton,
  title = {{Skeleton-Grounded Latent Action Model for Robot World Models}},
  author = {Qi Lv and Jiayi Lin and Yuxin Jiang and Jianzong Wang and Xiang Deng and Mike Shou Zheng},
  year = {2026},
  eprint = {2610.31474},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31474},
}

@misc{zhu2026rynnunify,
  title = {{RynnUnify: Towards Unified Embodied Brain}},
  author = {Minghao Zhu and Bohan Hou and Kun Xiang and Zixuan Wang and Yinzhou Tang and Yifei Yang and Zhikai Wang and Tianyi Zhang and Kehan Li and Haoyu Zhao and Siteng Huang and Leigang Qu and Sicong Leng and Dongchi Huang and Mingxiu Chen and Shijian Lu and Yue Wang and Xiaodan Liang and Zhenyu Zeng and Deli Zhao and Chengju Liu and Jianfei Yang and Xin Li},
  year = {2026},
  eprint = {2610.32965},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32965},
}

@misc{jang2025dreamgen,
  title = {{DreamGen: Unlocking Generalization in Robot Learning through Video World Models}},
  author = {Joel Jang and Seonghyeon Ye and Zongyu Lin and Jiannan Xiang and Johan Bjorck and Yu Fang and Fengyuan Hu and Spencer Huang and Kaushil Kundalia and Yen-Chen Lin and Loic Magne and Ajay Mandlekar and Avnish Narayan and You Liang Tan and Guanzhi Wang and Jing Wang and Qi Wang and Yinzhen Xu and Xiaohui Zeng and Kaiyuan Zheng and Ruijie Zheng and Ming-Yu Liu and Luke Zettlemoyer and Dieter Fox and Jan Kautz and Scott Reed and Yuke Zhu and Linxi Fan},
  year = {2025},
  eprint = {2505.12705},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.12705},
}

@misc{xing2026physical,
  title = {{Physical Canvas: A Vision Tactile World Model For Robot Policy Evaluation And Learning}},
  author = {Zebin Xing and Yuhang Zheng and Yupeng Zheng and Yichen Zhang and Zichen Li and Shangqing Zhou and Yujie Zang and Yuchen Liu and Zhongpu Xia and Haoran Li and Qichao Zhang},
  year = {2026},
  eprint = {2610.28613},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28613},
}

@misc{zou2026pica,
  title = {{PICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models}},
  author = {Yude Zou and Yifei Yao and Guanbo Jiao and Jianming Ma and Guanjie Zheng and Xing Gao},
  year = {2026},
  eprint = {2610.26813},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.26813},
}

@misc{zhang2026oswam,
  title = {{OSWAM: An Effective World Action Model with One-Step Action Generation}},
  author = {Guowen Zhang and Liyi Chen and Xu Hu and Pengfei Wang and Jingfan Chen and Chenhang He and Lei Zhang},
  year = {2026},
  eprint = {2610.35850},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.35850},
}

@misc{scardecchia2026video,
  title = {{Video World Models Need Predictable Latents}},
  author = {Mattia Scardecchia and Sherry Yang},
  year = {2026},
  eprint = {2610.34663},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2610.34663},
}

@misc{lee2026dexplicit,
  title = {{DeXplicit: Making Physical State Explicit in Dexterous Manipulation World Models}},
  author = {Adam Lee and Mutian Xu and Yukang Cao and Shulin Tian and Ziwei Liu},
  year = {2026},
  eprint = {2610.30781},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.30781},
}

@misc{bateman2026training,
  title = {{Training Controllable World Models via Action Influence Maximization}},
  author = {Samuel M. Bateman and Tenny Yin and Chongyi Zheng and Lei Huang and Brian Wang and Benjamin Eysenbach and Jaime Fernández Fisac and Dhruv Shah},
  year = {2026},
  eprint = {2610.27387},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27387},
}

@misc{geng2026trajwam,
  title = {{TrajWAM: An Efficient Trajectory-Guided World Action Model for Dynamic Robotic Manipulation}},
  author = {Haohan Geng and Sha Zhang and Weishuo Sun and Guanting Ye and Wenhao Yu and Yuang Xie and Qicheng Zeng and Peng Ye and Jiajun Deng and Jianmin Ji},
  year = {2026},
  eprint = {2610.25763},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25763},
}

@misc{liu2026gawm,
  title = {{GAWM: A Compact Latent World-Action Model for Multi-Task Robot Manipulation}},
  author = {Yang Liu and Xiaoli Liu and Liuzhao Li and Yuduo Song and Muyuan Liu and Xiang Gao},
  year = {2026},
  eprint = {2610.37091},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37091},
}

@misc{collins2026tapestry,
  title = {{TAPESTRY: A Single Backbone for Video Generation and Robot Control}},
  author = {Jeremy A. Collins and Seungjae Lee and Rachanon Wachakorn and Krishnan Srinivasan and Animesh Garg and Vitor Campagnolo Guizilini and Paarth Shah},
  year = {2026},
  eprint = {2610.36823},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36823},
}

@misc{zhao2026rynnworld,
  title = {{RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions}},
  author = {Haoyu Zhao and Yinzhou Tang and Zixuan Wang and Minghao Zhu and Dongchi Huang and Xingyue Zhao and Qin Zhao and Kehan Li and Siteng Huang and Xin Li and Zhenyu Zeng and Mingxiu Chen and Deli Zhao and Zhongyu Li},
  year = {2026},
  eprint = {2610.36791},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36791},
}

@misc{luo2026rollback,
  title = {{Rollback: Experience Backtracking in World Models for Policy Improvement}},
  author = {Jiayi Luo and Yang Zhang and Liliang Chen and Nan Wang and Chen Gao and Boxiang Qiu and Zhuoxuan Li and Baorui Peng and Chuankang Li and Yuxiang Yan and Si Liu and Qingyun Sun and Shuicheng Yan and Maoqing Yao and Jianxin Li and Guanghui Ren},
  year = {2026},
  eprint = {2610.36068},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36068},
}

@misc{hu2026trace,
  title = {{Trace-WAM: Learning to Act via 3D Motion Prediction for World Action Models}},
  author = {Xu Hu and Changjie Wu and Linzhe Shi and Hang Zhang and Chen Yang and Lingjun Zhang and Guowen Zhang and Mu Xu and Junran Peng and Qing Li and Zhaoxiang Zhang},
  year = {2026},
  eprint = {2610.36840},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36840},
}

@misc{kim2026adapting,
  title = {{Adapting Video Models for Robot Control via Motion-guided Asymmetric Prediction}},
  author = {Taeyoung Kim and Junyoung Sung and Heeseung Kwon and Minseop Kim and Jinwoo Shin},
  year = {2026},
  eprint = {2610.36624},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.36624},
}

@misc{mittal2026calibrated,
  title = {{Calibrated for Which Policy? Conformal Uncertainty for Fixed World Models Under Intervention}},
  author = {Ayush Mittal and Dhruv Gupta},
  year = {2026},
  eprint = {2610.35877},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2610.35877},
}

@misc{ahn2022do,
  title = {{Do As I Can, Not As I Say: Grounding Language in Robotic Affordances}},
  author = {Michael Ahn and Anthony Brohan and Noah Brown and Yevgen Chebotar and Omar Cortes and Byron David and Chelsea Finn and Chuyuan Fu and Keerthana Gopalakrishnan and Karol Hausman and Alex Herzog and Daniel Ho and Jasmine Hsu and Julian Ibarz and Brian Ichter and Alex Irpan and Eric Jang and Rosario Jauregui Ruano and Kyle Jeffrey and Sally Jesmonth and Nikhil J Joshi and Ryan Julian and Dmitry Kalashnikov and Yuheng Kuang and Kuang-Huei Lee and Sergey Levine and Yao Lu and Linda Luu and Carolina Parada and Peter Pastor and Jornell Quiambao and Kanishka Rao and Jarek Rettinghouse and Diego Reyes and Pierre Sermanet and Nicolas Sievers and Clayton Tan and Alexander Toshev and Vincent Vanhoucke and Fei Xia and Ted Xiao and Peng Xu and Sichun Xu and Mengyuan Yan and Andy Zeng},
  year = {2022},
  eprint = {2204.01691},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2204.01691},
}

@misc{liang2022code,
  title = {{Code as Policies: Language Model Programs for Embodied Control}},
  author = {Jacky Liang and Wenlong Huang and Fei Xia and Peng Xu and Karol Hausman and Brian Ichter and Pete Florence and Andy Zeng},
  year = {2022},
  eprint = {2209.07753},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2209.07753},
}

@misc{huang2022inner,
  title = {{Inner Monologue: Embodied Reasoning through Planning with Language Models}},
  author = {Wenlong Huang and Fei Xia and Ted Xiao and Harris Chan and Jacky Liang and Pete Florence and Andy Zeng and Jonathan Tompson and Igor Mordatch and Yevgen Chebotar and Pierre Sermanet and Noah Brown and Tomas Jackson and Linda Luu and Sergey Levine and Karol Hausman and Brian Ichter},
  year = {2022},
  eprint = {2207.05608},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2207.05608},
}

@misc{anderson2017vision,
  title = {{Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments}},
  author = {Peter Anderson and Qi Wu and Damien Teney and Jake Bruce and Mark Johnson and Niko Sünderhauf and Ian Reid and Stephen Gould and Anton van den Hengel},
  year = {2017},
  eprint = {1711.07280},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/1711.07280},
}

@misc{huang2022visual,
  title = {{Visual Language Maps for Robot Navigation}},
  author = {Chenguang Huang and Oier Mees and Andy Zeng and Wolfram Burgard},
  year = {2022},
  eprint = {2210.05714},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2210.05714},
}

@misc{sridhar2023nomad,
  title = {{NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration}},
  author = {Ajay Sridhar and Dhruv Shah and Catherine Glossop and Sergey Levine},
  year = {2023},
  eprint = {2310.07896},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2310.07896},
}

@misc{liu2024ok,
  title = {{OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics}},
  author = {Peiqi Liu and Yaswanth Orru and Jay Vakil and Chris Paxton and Nur Muhammad Mahi Shafiullah and Lerrel Pinto},
  year = {2024},
  eprint = {2401.12202},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2401.12202},
}

@misc{wang2026cracking,
  title = {{Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System}},
  author = {Zixuan Wang and Jia-Ning Li and Yinzhou Tang and Yanzhao Yu and Biao Wu and Meng Fang and Xin Li and Yiwu Zhong},
  year = {2026},
  eprint = {2610.19600},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.19600},
}

@misc{gong2026hierarchical,
  title = {{Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance}},
  author = {Zhefei Gong and Hefeifei Jiang and Zehao Wang and Jiachen Li},
  year = {2026},
  eprint = {2610.20607},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.20607},
}

@misc{shah2023vint,
  title = {{ViNT: A Foundation Model for Visual Navigation}},
  author = {Dhruv Shah and Ajay Sridhar and Nitish Dashora and Kyle Stachowicz and Kevin Black and Noriaki Hirose and Sergey Levine},
  year = {2023},
  eprint = {2306.14846},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2306.14846},
}

@misc{shah2022gnm,
  title = {{GNM: A General Navigation Model to Drive Any Robot}},
  author = {Dhruv Shah and Ajay Sridhar and Arjun Bhorkar and Noriaki Hirose and Sergey Levine},
  year = {2022},
  eprint = {2210.03370},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2210.03370},
}

@misc{yokoyama2023vlfm,
  title = {{VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation}},
  author = {Naoki Yokoyama and Sehoon Ha and Dhruv Batra and Jiuguang Wang and Bernadette Bucher},
  year = {2023},
  eprint = {2312.03275},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2312.03275},
}

@misc{zhang2024navid,
  title = {{NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation}},
  author = {Jiazhao Zhang and Kunyu Wang and Rongtao Xu and Gengze Zhou and Yicong Hong and Xiaomeng Fang and Qi Wu and Zhizheng Zhang and He Wang},
  year = {2024},
  eprint = {2402.15852},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2402.15852},
}

@misc{zhang2024uni,
  title = {{Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks}},
  author = {Jiazhao Zhang and Kunyu Wang and Shaoan Wang and Minghan Li and Haoran Liu and Songlin Wei and Zhongyuan Wang and Zhizheng Zhang and He Wang},
  year = {2024},
  eprint = {2412.06224},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.06224},
}

@misc{macenski2020marathon,
  title = {{The Marathon 2: A Navigation System}},
  author = {Steve Macenski and Francisco Martín and Ruffin White and Jonatan Ginés Clavero},
  year = {2020},
  eprint = {2003.00368},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2003.00368},
}

@misc{cheng2024navila,
  title = {{NaVILA: Legged Robot Vision-Language-Action Model for Navigation}},
  author = {An-Chieh Cheng and Yandong Ji and Zhaojing Yang and Zaitian Gongye and Xueyan Zou and Jan Kautz and Erdem Bıyık and Hongxu Yin and Sifei Liu and Xiaolong Wang},
  year = {2024},
  eprint = {2412.04453},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.04453},
}

@misc{krantz2020beyond,
  title = {{Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments}},
  author = {Jacob Krantz and Erik Wijmans and Arjun Majumdar and Dhruv Batra and Stefan Lee},
  year = {2020},
  eprint = {2004.02857},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2004.02857},
}

@misc{shah2022lm,
  title = {{LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action}},
  author = {Dhruv Shah and Blazej Osinski and Brian Ichter and Sergey Levine},
  year = {2022},
  eprint = {2207.04429},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2207.04429},
}

@misc{chaplot2020object,
  title = {{Object Goal Navigation using Goal-Oriented Semantic Exploration}},
  author = {Devendra Singh Chaplot and Dhiraj Gandhi and Abhinav Gupta and Ruslan Salakhutdinov},
  year = {2020},
  eprint = {2007.00643},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2007.00643},
}

@misc{chaplot2020learning,
  title = {{Learning to Explore using Active Neural SLAM}},
  author = {Devendra Singh Chaplot and Dhiraj Gandhi and Saurabh Gupta and Abhinav Gupta and Ruslan Salakhutdinov},
  year = {2020},
  eprint = {2004.05155},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2004.05155},
}

@misc{gadre2022cows,
  title = {{CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation}},
  author = {Samir Yitzhak Gadre and Mitchell Wortsman and Gabriel Ilharco and Ludwig Schmidt and Shuran Song},
  year = {2022},
  eprint = {2203.10421},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2203.10421},
}

@misc{ramrakhya2023pirlnav,
  title = {{PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav}},
  author = {Ram Ramrakhya and Dhruv Batra and Erik Wijmans and Abhishek Das},
  year = {2023},
  eprint = {2301.07302},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2301.07302},
}

@misc{yang2026scalenav,
  title = {{ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation}},
  author = {Yihui Yang and Yuanhong Yu and Jiawei Wang and Zhongrui Yu and Jia Shi and Kun Zhan and Ruizhen Hu and Xiaowei Zhou and Yu Liu and Sida Peng},
  year = {2026},
  eprint = {2610.25690},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25690},
}

@misc{zhou2023navgpt,
  title = {{NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models}},
  author = {Gengze Zhou and Yicong Hong and Qi Wu},
  year = {2023},
  eprint = {2305.16986},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2305.16986},
}

@misc{an2023etpnav,
  title = {{ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments}},
  author = {Dong An and Hanqing Wang and Wenguan Wang and Zun Wang and Yan Huang and Keji He and Liang Wang},
  year = {2023},
  eprint = {2304.03047},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2304.03047},
}

@misc{xu2026tarsphere,
  title = {{TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments}},
  author = {Yicheng Xu and Zhikai Xu and Ziyuan Chen and Yuhang Dong and Tao Zhang and Zhucun Xue and Yong Liu and Jiangning Zhang},
  year = {2026},
  eprint = {2610.30043},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30043},
}

@misc{feng2026embodiedworld,
  title = {{EmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models}},
  author = {X. Feng and J. Tang and Z. Lin and L. Chen and S. Shao and Q. Lu and K. Huang},
  year = {2026},
  eprint = {2610.25959},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2610.25959},
}

@misc{zhou2026injepa,
  title = {{InJePA: Intention-First Latent Planning with Coupled JEPA World Models for Visual Navigation}},
  author = {Siming Zhou and Bowen Ma and Ruiran Du and Pengcheng Zheng and Sheng Zheng and Dongshen Han and Zhijie Li and Wei Dong and Fan Mo and Chaoning Zhang},
  year = {2026},
  eprint = {2610.23896},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23896},
}

@misc{wang2026havana,
  title = {{HAVANA: A Hierarchical Video-Action Model for Vision-Language Navigation}},
  author = {Dongzhihan Wang and Yi Du and Chen Wang and Xiuxian Li and Liang Xu},
  year = {2026},
  eprint = {2610.24122},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.24122},
}

@misc{zhou2026moon,
  title = {{MOON: Learning When to Forget and How to Move On in Vision-and-Language Navigation}},
  author = {Jingmeng Zhou and Seson Sun and Binyao Xu and Lingming Zhang and Hanshi Wang and Fudong Ge and Weiming Hu and Jin Gao and Zhipeng Zhang},
  year = {2026},
  eprint = {2610.33546},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.33546},
}

@misc{yu2026one,
  title = {{One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation}},
  author = {Zhuoyuan Yu and Yuxing Long and Du Wang and Junyang Wang and Hongwei Fan and Hao Dong},
  year = {2026},
  eprint = {2610.33794},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.33794},
}

@misc{chen2026see,
  title = {{See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space}},
  author = {Jiawei Chen and Yinxi Wang and Zihan Yang and Meijun Gao and Yaowei Liu and Shuming Zhang and Zecheng Li and Xiangju Mi and Yuxuan Liu and Runzhong Huang and Tianlin Li and Xun Zhang and Zhengyang Wang and Xu Miao and Tong Yang},
  year = {2026},
  eprint = {2610.31762},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31762},
}

@misc{campos2020orb,
  title = {{ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM}},
  author = {Carlos Campos and Richard Elvira and Juan J. Gómez Rodríguez and José M. M. Montiel and Juan D. Tardós},
  year = {2020},
  eprint = {2007.11898},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2007.11898},
}

@misc{shan2020lio,
  title = {{LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping}},
  author = {Tixiao Shan and Brendan Englot and Drew Meyers and Wei Wang and Carlo Ratti and Daniela Rus},
  year = {2020},
  eprint = {2007.00258},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2007.00258},
}

@misc{xu2021fast,
  title = {{FAST-LIO2: Fast Direct LiDAR-inertial Odometry}},
  author = {Wei Xu and Yixi Cai and Dongjiao He and Jiarong Lin and Fu Zhang},
  year = {2021},
  eprint = {2107.06829},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2107.06829},
}

@misc{teed2021droid,
  title = {{DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras}},
  author = {Zachary Teed and Jia Deng},
  year = {2021},
  eprint = {2108.10869},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2108.10869},
}

@misc{matsuki2023gaussian,
  title = {{Gaussian Splatting SLAM}},
  author = {Hidenobu Matsuki and Riku Murai and Paul H. J. Kelly and Andrew J. Davison},
  year = {2023},
  eprint = {2312.06741},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2312.06741},
}

@misc{wang2023dust,
  title = {{DUSt3R: Geometric 3D Vision Made Easy}},
  author = {Shuzhe Wang and Vincent Leroy and Yohann Cabon and Boris Chidlovskii and Jerome Revaud},
  year = {2023},
  eprint = {2312.14132},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2312.14132},
}

@misc{wang2025vggt,
  title = {{VGGT: Visual Geometry Grounded Transformer}},
  author = {Jianyuan Wang and Minghao Chen and Nikita Karaev and Andrea Vedaldi and Christian Rupprecht and David Novotny},
  year = {2025},
  eprint = {2503.11651},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2503.11651},
}

@misc{wen2023foundationpose,
  title = {{FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects}},
  author = {Bowen Wen and Wei Yang and Jan Kautz and Stan Birchfield},
  year = {2023},
  eprint = {2312.08344},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2312.08344},
}

@misc{yang2024depth,
  title = {{Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}},
  author = {Lihe Yang and Bingyi Kang and Zilong Huang and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao},
  year = {2024},
  eprint = {2401.10891},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2401.10891},
}

@misc{gu2023conceptgraphs,
  title = {{ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning}},
  author = {Qiao Gu and Alihusein Kuwajerwala and Sacha Morin and Krishna Murthy Jatavallabhula and Bipasha Sen and Aditya Agarwal and Corban Rivera and William Paul and Kirsty Ellis and Rama Chellappa and Chuang Gan and Celso Miguel de Melo and Joshua B. Tenenbaum and Antonio Torralba and Florian Shkurti and Liam Paull},
  year = {2023},
  eprint = {2309.16650},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.16650},
}

@misc{kirillov2023segment,
  title = {{Segment Anything}},
  author = {Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick},
  year = {2023},
  eprint = {2304.02643},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2304.02643},
}

@misc{ravi2024sam,
  title = {{SAM 2: Segment Anything in Images and Videos}},
  author = {Nikhila Ravi and Valentin Gabeur and Yuan-Ting Hu and Ronghang Hu and Chaitanya Ryali and Tengyu Ma and Haitham Khedr and Roman Rädle and Chloe Rolland and Laura Gustafson and Eric Mintun and Junting Pan and Kalyan Vasudev Alwala and Nicolas Carion and Chao-Yuan Wu and Ross Girshick and Piotr Dollár and Christoph Feichtenhofer},
  year = {2024},
  eprint = {2408.00714},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2408.00714},
}

@misc{liu2023grounding,
  title = {{Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection}},
  author = {Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Qing Jiang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang},
  year = {2023},
  eprint = {2303.05499},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2303.05499},
}

@misc{wen2025foundationstereo,
  title = {{FoundationStereo: Zero-Shot Stereo Matching}},
  author = {Bowen Wen and Matthew Trepte and Joseph Aribido and Jan Kautz and Orazio Gallo and Stan Birchfield},
  year = {2025},
  eprint = {2501.09898},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2501.09898},
}

@misc{liu2026sparv,
  title = {{SpaRV: Sparse Radiance Voxels for Scalable Geometrically Consistent LiDAR-Visual Mapping and Rendering}},
  author = {Jianheng Liu and Yunfei Wan and Fangming Cheng and Xiangyu Hong and Zuhao Zou and Haotian Li and Longji Yin and Chunran Zheng and Jiarong Lin and Fu Zhang},
  year = {2026},
  eprint = {2610.25665},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25665},
}

@misc{jiang2026vision,
  title = {{Vision as Proprioception: Estimating Humanoid Robot Pose from Video}},
  author = {Jiaxi Jiang and Matthias Heyrman and René Zurbrügg and Marco Hutter and Christian Holz},
  year = {2026},
  eprint = {2610.25288},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25288},
}

@misc{jiang2026which,
  title = {{Which Depth Estimator for Jetson AGX Orin? A 2026 Benchmark of Monocular and Stereo Methods}},
  author = {Leaf Jiang},
  year = {2026},
  eprint = {2610.27199},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27199},
}

@misc{oquab2023dinov,
  title = {{DINOv2: Learning Robust Visual Features without Supervision}},
  author = {Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
  year = {2023},
  eprint = {2304.07193},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2304.07193},
}

@misc{karaev2023cotracker,
  title = {{CoTracker: It is Better to Track Together}},
  author = {Nikita Karaev and Ignacio Rocco and Benjamin Graham and Natalia Neverova and Andrea Vedaldi and Christian Rupprecht},
  year = {2023},
  eprint = {2307.07635},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2307.07635},
}

@misc{leroy2024grounding,
  title = {{Grounding Image Matching in 3D with MASt3R}},
  author = {Vincent Leroy and Yohann Cabon and Jérôme Revaud},
  year = {2024},
  eprint = {2406.09756},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2406.09756},
}

@misc{zheng2024fast,
  title = {{FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry}},
  author = {Chunran Zheng and Wei Xu and Zuhao Zou and Tong Hua and Chongjian Yuan and Dongjiao He and Bingyang Zhou and Zheng Liu and Jiarong Lin and Fangcheng Zhu and Yunfan Ren and Rong Wang and Fanle Meng and Fu Zhang},
  year = {2024},
  eprint = {2408.14035},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2408.14035},
}

@misc{yang2024depth,
  title = {{Depth Anything V2}},
  author = {Lihe Yang and Bingyi Kang and Zilong Huang and Zhen Zhao and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao},
  year = {2024},
  eprint = {2406.09414},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2406.09414},
}

@misc{wen2023bundlesdf,
  title = {{BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects}},
  author = {Bowen Wen and Jonathan Tremblay and Valts Blukis and Stephen Tyree and Thomas Muller and Alex Evans and Dieter Fox and Jan Kautz and Stan Birchfield},
  year = {2023},
  eprint = {2303.14158},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2303.14158},
}

@misc{wang2026ace,
  title = {{ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models}},
  author = {Yinhe Wang and Tao Tao and Zexin He and Shuang Luo and Wei Mao and Yao Mu and Feng Pan and Hanming Deng and Lewei Lu and Zhi Hou and Xingang Pan and Dahua Lin and Dacheng Tao and Xiaogang Wang},
  year = {2026},
  eprint = {2610.27040},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27040},
}

@misc{carion2025sam,
  title = {{SAM 3: Segment Anything with Concepts}},
  author = {Nicolas Carion and Laura Gustafson and Yuan-Ting Hu and Shoubhik Debnath and Ronghang Hu and Didac Suris and Chaitanya Ryali and Kalyan Vasudev Alwala and Haitham Khedr and Andrew Huang and Jie Lei and Tengyu Ma and Baishan Guo and Arpit Kalla and Markus Marks and Joseph Greer and Meng Wang and Peize Sun and Roman Rädle and Triantafyllos Afouras and Effrosyni Mavroudi and Katherine Xu and Tsung-Han Wu and Yu Zhou and Liliane Momeni and Rishi Hazra and Shuangrui Ding and Sagar Vaze and Francois Porcher and Feng Li and Siyuan Li and Aishwarya Kamath and Ho Kei Cheng and Piotr Dollár and Nikhila Ravi and Kate Saenko and Pengchuan Zhang and Christoph Feichtenhofer},
  year = {2025},
  eprint = {2511.16719},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2511.16719},
}

@misc{sundaralingam2023curobo,
  title = {{cuRobo: Parallelized Collision-Free Minimum-Jerk Robot Motion Generation}},
  author = {Balakumar Sundaralingam and Siva Kumar Sastry Hari and Adam Fishman and Caelan Garrett and Karl Van Wyk and Valts Blukis and Alexander Millane and Helen Oleynikova and Ankur Handa and Fabio Ramos and Nathan Ratliff and Dieter Fox},
  year = {2023},
  eprint = {2310.17274},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2310.17274},
}

@misc{fishman2022motion,
  title = {{Motion Policy Networks}},
  author = {Adam Fishman and Adithyavairan Murali and Clemens Eppner and Bryan Peele and Byron Boots and Dieter Fox},
  year = {2022},
  eprint = {2210.12209},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2210.12209},
}

@misc{janner2022planning,
  title = {{Planning with Diffusion for Flexible Behavior Synthesis}},
  author = {Michael Janner and Yilun Du and Joshua B. Tenenbaum and Sergey Levine},
  year = {2022},
  eprint = {2205.09991},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2205.09991},
}

@misc{ames2019control,
  title = {{Control Barrier Functions: Theory and Applications}},
  author = {Aaron D. Ames and Samuel Coogan and Magnus Egerstedt and Gennaro Notomista and Koushil Sreenath and Paulo Tabuada},
  year = {2019},
  eprint = {1903.11199},
  archivePrefix = {arXiv},
  primaryClass = {eess.SY},
  url = {https://arxiv.org/abs/1903.11199},
}

@misc{brunke2021safe,
  title = {{Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning}},
  author = {Lukas Brunke and Melissa Greeff and Adam W. Hall and Zhaocong Yuan and Siqi Zhou and Jacopo Panerati and Angela P. Schoellig},
  year = {2021},
  eprint = {2108.06266},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2108.06266},
}

@misc{yuan2021safe,
  title = {{safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Robotics}},
  author = {Zhaocong Yuan and Adam W. Hall and Siqi Zhou and Lukas Brunke and Melissa Greeff and Jacopo Panerati and Angela P. Schoellig},
  year = {2021},
  eprint = {2109.06325},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.06325},
}

@misc{mastalli2019crocoddyl,
  title = {{Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control}},
  author = {Carlos Mastalli and Rohan Budhiraja and Wolfgang Merkt and Guilhem Saurel and Bilal Hammoud and Maximilien Naveau and Justin Carpentier and Ludovic Righetti and Sethu Vijayakumar and Nicolas Mansard},
  year = {2019},
  eprint = {1909.04947},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1909.04947},
}

@misc{verschueren2019acados,
  title = {{acados: a modular open-source framework for fast embedded optimal control}},
  author = {Robin Verschueren and Gianluca Frison and Dimitris Kouzoupis and Jonathan Frey and Niels van Duijkeren and Andrea Zanelli and Branimir Novoselnik and Thivaharan Albin and Rien Quirynen and Moritz Diehl},
  year = {2019},
  eprint = {1910.13753},
  archivePrefix = {arXiv},
  primaryClass = {math.OC},
  url = {https://arxiv.org/abs/1910.13753},
}

@misc{skerlj2026sub,
  title = {{Sub-Millisecond Reflexes for Continuous Physical Human-Robot Interaction}},
  author = {Jon Škerlj and Sami Haddadin},
  year = {2026},
  eprint = {2610.21913},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.21913},
}

@misc{wu2026prismplan,
  title = {{PrismPlan: A Shared GPU Substrate for Motion Planning Across Paradigms}},
  author = {Hong Wu and ChaoXuan Liu and ShuJie Wang},
  year = {2026},
  eprint = {2610.23884},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23884},
}

@misc{howell2022predictive,
  title = {{Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo}},
  author = {Taylor Howell and Nimrod Gileadi and Saran Tunyasuvunakool and Kevin Zakka and Tom Erez and Yuval Tassa},
  year = {2022},
  eprint = {2212.00541},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2212.00541},
}

@misc{viljoen2026cusadi,
  title = {{CusADi2: Latency-Optimized Batch Computation of Robot Kinematics, Jacobians, and Hessians on the GPU}},
  author = {John Viljoen and Lasse Peters and Masayoshi Tomizuka and Negar Mehr},
  year = {2026},
  eprint = {2610.25476},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25476},
}

@misc{stellato2017osqp,
  title = {{OSQP: An Operator Splitting Solver for Quadratic Programs}},
  author = {Bartolomeo Stellato and Goran Banjac and Paul Goulart and Alberto Bemporad and Stephen Boyd},
  year = {2017},
  eprint = {1711.08013},
  archivePrefix = {arXiv},
  primaryClass = {math.OC},
  url = {https://arxiv.org/abs/1711.08013},
}

@misc{thomason2023motions,
  title = {{Motions in Microseconds via Vectorized Sampling-Based Planning}},
  author = {Wil Thomason and Zachary Kingston and Lydia E. Kavraki},
  year = {2023},
  eprint = {2309.14545},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.14545},
}

@misc{ratliff2018riemannian,
  title = {{Riemannian Motion Policies}},
  author = {Nathan D. Ratliff and Jan Issac and Daniel Kappler and Stan Birchfield and Dieter Fox},
  year = {2018},
  eprint = {1801.02854},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1801.02854},
}

@misc{bansal2017hamilton,
  title = {{Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances}},
  author = {Somil Bansal and Mo Chen and Sylvia Herbert and Claire J. Tomlin},
  year = {2017},
  eprint = {1709.07523},
  archivePrefix = {arXiv},
  primaryClass = {eess.SY},
  url = {https://arxiv.org/abs/1709.07523},
}

@misc{berscheid2021jerk,
  title = {{Jerk-limited Real-time Trajectory Generation with Arbitrary Target States}},
  author = {Lars Berscheid and Torsten Kröger},
  year = {2021},
  eprint = {2105.04830},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2105.04830},
}

@misc{lee2026keeping,
  title = {{Keeping Contact: Task-Adaptive Friction Margins for Bimanual Non-Prehensile Manipulation}},
  author = {Qian Ying Lee and Lin Yang and Domenico Campolo},
  year = {2026},
  eprint = {2610.36961},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36961},
}

@misc{wang2026generalist,
  title = {{A generalist policy for muscle-driven control across individual musculoskeletal models}},
  author = {Bozhao Wang and Yinglei Zhu and Zhengqing Li and Zhiyuan Zhang and Weiming Kang and Yiheng He and XinJun Liu and Senhao Hou and Huichan Zhao and Xiaoqiang Tang},
  year = {2026},
  eprint = {2610.36535},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36535},
}

@misc{schulman2017proximal,
  title = {{Proximal Policy Optimization Algorithms}},
  author = {John Schulman and Filip Wolski and Prafulla Dhariwal and Alec Radford and Oleg Klimov},
  year = {2017},
  eprint = {1707.06347},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1707.06347},
}

@misc{haarnoja2018soft,
  title = {{Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor}},
  author = {Tuomas Haarnoja and Aurick Zhou and Pieter Abbeel and Sergey Levine},
  year = {2018},
  eprint = {1801.01290},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1801.01290},
}

@misc{ross2010reduction,
  title = {{A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning}},
  author = {Stephane Ross and Geoffrey J. Gordon and J. Andrew Bagnell},
  year = {2010},
  eprint = {1011.0686},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1011.0686},
}

@misc{ball2023efficient,
  title = {{Efficient Online Reinforcement Learning with Offline Data}},
  author = {Philip J. Ball and Laura Smith and Ilya Kostrikov and Sergey Levine},
  year = {2023},
  eprint = {2302.02948},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2302.02948},
}

@misc{luo2024serl,
  title = {{SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning}},
  author = {Jianlan Luo and Zheyuan Hu and Charles Xu and You Liang Tan and Jacob Berg and Archit Sharma and Stefan Schaal and Chelsea Finn and Abhishek Gupta and Sergey Levine},
  year = {2024},
  eprint = {2401.16013},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2401.16013},
}

@misc{luo2024precise,
  title = {{Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning}},
  author = {Jianlan Luo and Charles Xu and Jeffrey Wu and Sergey Levine},
  year = {2024},
  eprint = {2410.21845},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.21845},
}

@misc{mandlekar2021what,
  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},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2108.03298},
}

@misc{kostrikov2021offline,
  title = {{Offline Reinforcement Learning with Implicit Q-Learning}},
  author = {Ilya Kostrikov and Ashvin Nair and Sergey Levine},
  year = {2021},
  eprint = {2110.06169},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2110.06169},
}

@misc{shafiullah2022behavior,
  title = {{Behavior Transformers: Cloning $k$ modes with one stone}},
  author = {Nur Muhammad Mahi Shafiullah and Zichen Jeff Cui and Ariuntuya Altanzaya and Lerrel Pinto},
  year = {2022},
  eprint = {2206.11251},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2206.11251},
}

@misc{ren2024diffusion,
  title = {{Diffusion Policy Policy Optimization}},
  author = {Allen Z. Ren and Justin Lidard and Lars L. Ankile and Anthony Simeonov and Pulkit Agrawal and Anirudha Majumdar and Benjamin Burchfiel and Hongkai Dai and Max Simchowitz},
  year = {2024},
  eprint = {2409.00588},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2409.00588},
}

@misc{kumar2020conservative,
  title = {{Conservative Q-Learning for Offline Reinforcement Learning}},
  author = {Aviral Kumar and Aurick Zhou and George Tucker and Sergey Levine},
  year = {2020},
  eprint = {2006.04779},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2006.04779},
}

@misc{chen2021decision,
  title = {{Decision Transformer: Reinforcement Learning via Sequence Modeling}},
  author = {Lili Chen and Kevin Lu and Aravind Rajeswaran and Kimin Lee and Aditya Grover and Michael Laskin and Pieter Abbeel and Aravind Srinivas and Igor Mordatch},
  year = {2021},
  eprint = {2106.01345},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2106.01345},
}

@misc{fujimoto2018addressing,
  title = {{Addressing Function Approximation Error in Actor-Critic Methods}},
  author = {Scott Fujimoto and Herke van Hoof and David Meger},
  year = {2018},
  eprint = {1802.09477},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/1802.09477},
}

@misc{ho2016generative,
  title = {{Generative Adversarial Imitation Learning}},
  author = {Jonathan Ho and Stefano Ermon},
  year = {2016},
  eprint = {1606.03476},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1606.03476},
}

@misc{florence2021implicit,
  title = {{Implicit Behavioral Cloning}},
  author = {Pete Florence and Corey Lynch and Andy Zeng and Oscar Ramirez and Ayzaan Wahid and Laura Downs and Adrian Wong and Johnny Lee and Igor Mordatch and Jonathan Tompson},
  year = {2021},
  eprint = {2109.00137},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.00137},
}

@misc{nair2020awac,
  title = {{AWAC: Accelerating Online Reinforcement Learning with Offline Datasets}},
  author = {Ashvin Nair and Abhishek Gupta and Murtaza Dalal and Sergey Levine},
  year = {2020},
  eprint = {2006.09359},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2006.09359},
}

@misc{kalashnikov2018qt,
  title = {{QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation}},
  author = {Dmitry Kalashnikov and Alex Irpan and Peter Pastor and Julian Ibarz and Alexander Herzog and Eric Jang and Deirdre Quillen and Ethan Holly and Mrinal Kalakrishnan and Vincent Vanhoucke and Sergey Levine},
  year = {2018},
  eprint = {1806.10293},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1806.10293},
}

@misc{yarats2021mastering,
  title = {{Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning}},
  author = {Denis Yarats and Rob Fergus and Alessandro Lazaric and Lerrel Pinto},
  year = {2021},
  eprint = {2107.09645},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2107.09645},
}

@misc{wagenmaker2025steering,
  title = {{Steering Your Diffusion Policy with Latent Space Reinforcement Learning}},
  author = {Andrew Wagenmaker and Mitsuhiko Nakamoto and Yunchu Zhang and Seohong Park and Waleed Yagoub and Anusha Nagabandi and Abhishek Gupta and Sergey Levine},
  year = {2025},
  eprint = {2506.15799},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.15799},
}

@misc{park2025flow,
  title = {{Flow Q-Learning}},
  author = {Seohong Park and Qiyang Li and Sergey Levine},
  year = {2025},
  eprint = {2502.02538},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2502.02538},
}

@misc{li2025simplevla,
  title = {{SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning}},
  author = {Haozhan Li and Yuxin Zuo and Jiale Yu and Yuhao Zhang and Zhaohui Yang and Kaiyan Zhang and Xuekai Zhu and Yuchen Zhang and Tianxing Chen and Ganqu Cui and Dehui Wang and Dingxiang Luo and Yuchen Fan and Youbang Sun and Jia Zeng and Jiangmiao Pang and Shanghang Zhang and Yu Wang and Yao Mu and Bowen Zhou and Ning Ding},
  year = {2025},
  eprint = {2509.09674},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2509.09674},
}

@misc{nakamoto2023cal,
  title = {{Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning}},
  author = {Mitsuhiko Nakamoto and Yuexiang Zhai and Anikait Singh and Max Sobol Mark and Yi Ma and Chelsea Finn and Aviral Kumar and Sergey Levine},
  year = {2023},
  eprint = {2303.05479},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2303.05479},
}

@misc{chebotar2023q,
  title = {{Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions}},
  author = {Yevgen Chebotar and Quan Vuong and Alex Irpan and Karol Hausman and Fei Xia and Yao Lu and Aviral Kumar and Tianhe Yu and Alexander Herzog and Karl Pertsch and Keerthana Gopalakrishnan and Julian Ibarz and Ofir Nachum and Sumedh Sontakke and Grecia Salazar and Huong T Tran and Jodilyn Peralta and Clayton Tan and Deeksha Manjunath and Jaspiar Singht and Brianna Zitkovich and Tomas Jackson and Kanishka Rao and Chelsea Finn and Sergey Levine},
  year = {2023},
  eprint = {2309.10150},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.10150},
}

@misc{zang2025rlinf,
  title = {{RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models}},
  author = {Hongzhi Zang and Mingjie Wei and Si Xu and Yongji Wu and Zhen Guo and Yuanqing Wang and Hao Lin and Peihong Wang and Liangzhi Shi and Yuqing Xie and Zhexuan Xu and Zhihao Liu and Kang Chen and Wenhao Tang and Quanlu Zhang and Weinan Zhang and Chao Yu and Yu Wang},
  year = {2025},
  eprint = {2510.06710},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2510.06710},
}

@misc{yu2026learning,
  title = {{Learning from Fleet Experience: Collective Experience Learning Across 96 Robots}},
  author = {Chao Yu and Shu'ang Yu and Hao Lin and Hongzhi Zang and Yuxiang Yan and Chenxi Jiang and Zhen Guo and Chuankang Li and Yihao Chen and Xin Xu and Xu Fu and Jiakai Zhou and Liangzhi Shi and Hongyi Ren and Yiwei Liu and Jing Wu and Yuanqing Wang and Chen Wu and Bo Dai and Chunyu Yang and Hongliang Huang and Shuoyu Yue and Weiqi Yin and Yinuo Chen and Ruihua Chen and Chunyang Zhu and Han Xiao and Yanghao Li and Ruipu Wu and Zhikai Cai and Xiu Chen and Xu Tan and Si Liu and Yuchen Yan and Jialin Zhang and Wen Zeng and Yiming Zhou and Zixiao Huang and Xinlei Chen and Guanghui Ren and Quanlu Zhang and Boxun Li and Maoqing Yao and Yu Wang},
  year = {2026},
  eprint = {2610.25736},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25736},
}

@misc{kim2026accrue,
  title = {{ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models}},
  author = {Changyeon Kim and Kimin Lee and Yashraj Narang and Yijie Guo},
  year = {2026},
  eprint = {2610.18596},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.18596},
}

@misc{liu2026agenticroborl,
  title = {{AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics}},
  author = {Xinxin Liu and Bingxin Xu and Wenrui Bao and Ming Li and Wentao Bao and Chen Chen and Yuzhang Shang},
  year = {2026},
  eprint = {2610.28589},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28589},
}

@misc{zhang2026scaling,
  title = {{Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds}},
  author = {Kuan Zhang and Yukun Chen and Zhihao Yang and Yue Su and Xiangnan Wu and Zirong Chen and Run Luo and Jinkun Hou and Tao Tan and Yinhe Zheng and Yiming Li},
  year = {2026},
  eprint = {2610.28698},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2610.28698},
}

@misc{luo2026toward,
  title = {{Toward Recursive Self-Improvement in Physical AI}},
  author = {Meng Luo and Zechen Bai and Shanqing Xu and Yanlin Li and Kaixin Li and Mengchen Qian and Weifeng Lu and Ran Zhang and Yingtian Zou and Ziyang Luo and Wei Chen and Hongzhan Lin},
  year = {2026},
  eprint = {2610.29677},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29677},
}

@misc{li2026where,
  title = {{Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy}},
  author = {Zekai Li and Jiayi Yu and Jinlu Zhang and Luyang Niu and Zekun Qi and Jun Zheng and Xuchuan Chen and Dairu Liu and Yintianrun Zhang and He Wang and Li Yi},
  year = {2026},
  eprint = {2610.26848},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.26848},
}

@misc{lu2026tilde,
  title = {{TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models}},
  author = {Yuxiang Lu and Yantong Liu and Jinghua Hou and Xueli Sun and Ruihua Han and Zhe Liu and Hengshuang Zhao},
  year = {2026},
  eprint = {2610.25376},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25376},
}

@misc{zhang2026egoforesight,
  title = {{EgoForesight: Effectively Scaling Policy Learning with Noisy Egocentric Actions}},
  author = {Chubin Zhang and Changyuan Wang and Yirui Wang and Ao Li and Shilin Ma and Yue Su and Cai Zhou and Xiuwei Xu and Tianle Zhang and Yansong Tang},
  year = {2026},
  eprint = {2610.31845},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31845},
}

@misc{gu2026training,
  title = {{Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation}},
  author = {Chun Gu and Xiaofei Wei and Yiming Chen and Bozhou Zhang and Juntong Zhang and Xiatian Zhu and Li Zhang},
  year = {2026},
  eprint = {2610.29264},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29264},
}

@misc{park2026discodemo,
  title = {{DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning}},
  author = {Minho Park and Kinam Kim and Donghu Kim and Byungkun Lee and Dongyoon Hwang and Yongjae Shin and Junha Hyung and Hojoon Lee and Jaegul Choo},
  year = {2026},
  eprint = {2610.32093},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32093},
}

@misc{yu2026hidra,
  title = {{HIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning}},
  author = {Fanqi Yu and Matteo Tiezzi and Cigdem Beyan and Tommaso Apicella and Vittorio Murino},
  year = {2026},
  eprint = {2610.36374},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36374},
}

@misc{luu2026progress,
  title = {{Progress-Guided Preference Generation for Aligning Generative Control Policies}},
  author = {Tung M. Luu and Tri Ton and Duc M. Nguyen and Xuan Thanh Nguyen and Nguyen Gia Binh and Quang Tan Nguyen and Vu Duong and Daniel Sonntag and Duy M. H. Nguyen and Vien Anh Ngo and Chang D. Yoo},
  year = {2026},
  eprint = {2610.25692},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2610.25692},
}

@misc{zakka2025mujoco,
  title = {{MuJoCo Playground}},
  author = {Kevin Zakka and Baruch Tabanpour and Qiayuan Liao and Mustafa Haiderbhai and Samuel Holt and Jing Yuan Luo and Arthur Allshire and Erik Frey and Koushil Sreenath and Lueder A. Kahrs and Carmelo Sferrazza and Yuval Tassa and Pieter Abbeel},
  year = {2025},
  eprint = {2502.08844},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.08844},
}

@misc{makoviychuk2021isaac,
  title = {{Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning}},
  author = {Viktor Makoviychuk and Lukasz Wawrzyniak and Yunrong Guo and Michelle Lu and Kier Storey and Miles Macklin and David Hoeller and Nikita Rudin and Arthur Allshire and Ankur Handa and Gavriel State},
  year = {2021},
  eprint = {2108.10470},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2108.10470},
}

@misc{mittal2023orbit,
  title = {{Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments}},
  author = {Mayank Mittal and Calvin Yu and Qinxi Yu and Jingzhou Liu and Nikita Rudin and David Hoeller and Jia Lin Yuan and Ritvik Singh and Yunrong Guo and Hammad Mazhar and Ajay Mandlekar and Buck Babich and Gavriel State and Marco Hutter and Animesh Garg},
  year = {2023},
  eprint = {2301.04195},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2301.04195},
}

@misc{tao2024maniskill,
  title = {{ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI}},
  author = {Stone Tao and Fanbo Xiang and Arth Shukla and Yuzhe Qin and Xander Hinrichsen and Xiaodi Yuan and Chen Bao and Xinsong Lin and Yulin Liu and Tse-kai Chan and Yuan Gao and Xuanlin Li and Tongzhou Mu and Nan Xiao and Arnav Gurha and Viswesh Nagaswamy Rajesh and Yong Woo Choi and Yen-Ru Chen and Zhiao Huang and Roberto Calandra and Rui Chen and Shan Luo and Hao Su},
  year = {2024},
  eprint = {2410.00425},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.00425},
}

@misc{zhu2020robosuite,
  title = {{robosuite: A Modular Simulation Framework and Benchmark for Robot Learning}},
  author = {Yuke Zhu and Josiah Wong and Ajay Mandlekar and Roberto Martín-Martín and Abhishek Joshi and Kevin Lin and Abhiram Maddukuri and Soroush Nasiriany and Yifeng Zhu},
  year = {2020},
  eprint = {2009.12293},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2009.12293},
}

@misc{nasiriany2024robocasa,
  title = {{RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots}},
  author = {Soroush Nasiriany and Abhiram Maddukuri and Lance Zhang and Adeet Parikh and Aaron Lo and Abhishek Joshi and Ajay Mandlekar and Yuke Zhu},
  year = {2024},
  eprint = {2406.02523},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2406.02523},
}

@misc{xiang2020sapien,
  title = {{SAPIEN: A SimulAted Part-based Interactive ENvironment}},
  author = {Fanbo Xiang and Yuzhe Qin and Kaichun Mo and Yikuan Xia and Hao Zhu and Fangchen Liu and Minghua Liu and Hanxiao Jiang and Yifu Yuan and He Wang and Li Yi and Angel X. Chang and Leonidas J. Guibas and Hao Su},
  year = {2020},
  eprint = {2003.08515},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2003.08515},
}

@misc{tobin2017domain,
  title = {{Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World}},
  author = {Josh Tobin and Rachel Fong and Alex Ray and Jonas Schneider and Wojciech Zaremba and Pieter Abbeel},
  year = {2017},
  eprint = {1703.06907},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1703.06907},
}

@misc{peng2017sim,
  title = {{Sim-to-Real Transfer of Robotic Control with Dynamics Randomization}},
  author = {Xue Bin Peng and Marcin Andrychowicz and Wojciech Zaremba and Pieter Abbeel},
  year = {2017},
  eprint = {1710.06537},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1710.06537},
}

@misc{ma2026active,
  title = {{Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training}},
  author = {Liqian Ma and Vaibhav Saxena and Utkarsh Aashu Mishra and Shuo Cheng and Yongxin Chen and Danfei Xu},
  year = {2026},
  eprint = {2610.19479},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.19479},
}

@misc{chen2025robotwin,
  title = {{RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation}},
  author = {Tianxing Chen and Zanxin Chen and Baijun Chen and Zijian Cai and Yibin Liu and Zixuan Li and Qiwei Liang and Xianliang Lin and Yiheng Ge and Zhenyu Gu and Weiliang Deng and Yubin Guo and Tian Nian and Xuanbing Xie and Qiangyu Chen and Kailun Su and Tianling Xu and Guodong Liu and Mengkang Hu and Huan-ang Gao and Kaixuan Wang and Zhixuan Liang and Yusen Qin and Xiaokang Yang and Ping Luo and Yao Mu},
  year = {2025},
  eprint = {2506.18088},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.18088},
}

@misc{mandlekar2023mimicgen,
  title = {{MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations}},
  author = {Ajay Mandlekar and Soroush Nasiriany and Bowen Wen and Iretiayo Akinola and Yashraj Narang and Linxi Fan and Yuke Zhu and Dieter Fox},
  year = {2023},
  eprint = {2310.17596},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2310.17596},
}

@misc{li2024behavior,
  title = {{BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation}},
  author = {Chengshu Li and Ruohan Zhang and Josiah Wong and Cem Gokmen and Sanjana Srivastava and Roberto Martín-Martín and Chen Wang and Gabrael Levine and Wensi Ai and Benjamin Martinez and Hang Yin and Michael Lingelbach and Minjune Hwang and Ayano Hiranaka and Sujay Garlanka and Arman Aydin and Sharon Lee and Jiankai Sun and Mona Anvari and Manasi Sharma and Dhruva Bansal and Samuel Hunter and Kyu-Young Kim and Alan Lou and Caleb R Matthews and Ivan Villa-Renteria and Jerry Huayang Tang and Claire Tang and Fei Xia and Yunzhu Li and Silvio Savarese and Hyowon Gweon and C. Karen Liu and Jiajun Wu and Li Fei-Fei},
  year = {2024},
  eprint = {2403.09227},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.09227},
}

@misc{nvidia2025isaac,
  title = {{Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning}},
  author = {NVIDIA and : and Mayank Mittal and Pascal Roth and James Tigue and Antoine Richard and Octi Zhang and Peter Du and Antonio Serrano-Muñoz and Xinjie Yao and René Zurbrügg and Nikita Rudin and Lukasz Wawrzyniak and Milad Rakhsha and Alain Denzler and Eric Heiden and Ales Borovicka and Ossama Ahmed and Iretiayo Akinola and Abrar Anwar and Mark T. Carlson and Ji Yuan Feng and Animesh Garg and Renato Gasoto and Lionel Gulich and Yijie Guo and M. Gussert and Alex Hansen and Mihir Kulkarni and Chenran Li and Wei Liu and Viktor Makoviychuk and Grzegorz Malczyk and Hammad Mazhar and Masoud Moghani and Adithyavairavan Murali and Michael Noseworthy and Alexander Poddubny and Nathan Ratliff and Welf Rehberg and Clemens Schwarke and Ritvik Singh and James Latham Smith and Bingjie Tang and Ruchik Thaker and Matthew Trepte and Karl Van Wyk and Fangzhou Yu and Alex Millane and Vikram Ramasamy and others},
  year = {2025},
  eprint = {2511.04831},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2511.04831},
}

@misc{kolve2017ai,
  title = {{AI2-THOR: An Interactive 3D Environment for Visual AI}},
  author = {Eric Kolve and Roozbeh Mottaghi and Winson Han and Eli VanderBilt and Luca Weihs and Alvaro Herrasti and Matt Deitke and Kiana Ehsani and Daniel Gordon and Yuke Zhu and Aniruddha Kembhavi and Abhinav Gupta and Ali Farhadi},
  year = {2017},
  eprint = {1712.05474},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/1712.05474},
}

@misc{puig2023habitat,
  title = {{Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots}},
  author = {Xavier Puig and Eric Undersander and Andrew Szot and Mikael Dallaire Cote and Tsung-Yen Yang and Ruslan Partsey and Ruta Desai and Alexander William Clegg and Michal Hlavac and So Yeon Min and Vladimír Vondruš and Theophile Gervet and Vincent-Pierre Berges and John M. Turner and Oleksandr Maksymets and Zsolt Kira and Mrinal Kalakrishnan and Jitendra Malik and Devendra Singh Chaplot and Unnat Jain and Dhruv Batra and Akshara Rai and Roozbeh Mottaghi},
  year = {2023},
  eprint = {2310.13724},
  archivePrefix = {arXiv},
  primaryClass = {cs.HC},
  url = {https://arxiv.org/abs/2310.13724},
}

@misc{eschmann2026hyperdrone,
  title = {{HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second}},
  author = {Jonas Eschmann and Giuseppe Loianno},
  year = {2026},
  eprint = {2610.28950},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28950},
}

@misc{freeman2021brax,
  title = {{Brax: A Differentiable Physics Engine for Large Scale Rigid Body Simulation}},
  author = {C. Daniel Freeman and Erik Frey and Anton Raichuk and Sertan Girgin and Igor Mordatch and Olivier Bachem},
  year = {2021},
  eprint = {2106.13281},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2106.13281},
}

@misc{szot2021habitat,
  title = {{Habitat 2.0: Training Home Assistants to Rearrange their Habitat}},
  author = {Andrew Szot and Alex Clegg and Eric Undersander and Erik Wijmans and Yili Zhao and John Turner and Noah Maestre and Mustafa Mukadam and Devendra Chaplot and Oleksandr Maksymets and Aaron Gokaslan and Vladimir Vondrus and Sameer Dharur and Franziska Meier and Wojciech Galuba and Angel Chang and Zsolt Kira and Vladlen Koltun and Jitendra Malik and Manolis Savva and Dhruv Batra},
  year = {2021},
  eprint = {2106.14405},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2106.14405},
}

@misc{gu2024humanoid,
  title = {{Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer}},
  author = {Xinyang Gu and Yen-Jen Wang and Jianyu Chen},
  year = {2024},
  eprint = {2404.05695},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2404.05695},
}

@misc{tassa2020dm,
  title = {{dm_control: Software and Tasks for Continuous Control}},
  author = {Yuval Tassa and Saran Tunyasuvunakool and Alistair Muldal and Yotam Doron and Piotr Trochim and Siqi Liu and Steven Bohez and Josh Merel and Tom Erez and Timothy Lillicrap and Nicolas Heess},
  year = {2020},
  eprint = {2006.12983},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2006.12983},
}

@misc{lin2020softgym,
  title = {{SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation}},
  author = {Xingyu Lin and Yufei Wang and Jake Olkin and David Held},
  year = {2020},
  eprint = {2011.07215},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2011.07215},
}

@misc{jiang2024dexmimicgen,
  title = {{DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning}},
  author = {Zhenyu Jiang and Yuqi Xie and Kevin Lin and Zhenjia Xu and Weikang Wan and Ajay Mandlekar and Linxi Fan and Yuke Zhu},
  year = {2024},
  eprint = {2410.24185},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.24185},
}

@misc{liu2026scenebloom,
  title = {{SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning}},
  author = {Yuhan Liu and Lianhui Qin and Shenji Wan},
  year = {2026},
  eprint = {2610.32978},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.32978},
}

@misc{gao2025genmanip,
  title = {{GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation}},
  author = {Ning Gao and Yilun Chen and Shuai Yang and Xinyi Chen and Yang Tian and Hao Li and Haifeng Huang and Hanqing Wang and Tai Wang and Jiangmiao Pang},
  year = {2025},
  eprint = {2506.10966},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.10966},
}

@misc{castillaarquillo2026mare,
  title = {{MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy}},
  author = {Raúl Castilla-Arquillo and Miguel Olivares-Mendez},
  year = {2026},
  eprint = {2610.28465},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28465},
}

@misc{collaboration2023open,
  title = {{Open X-Embodiment: Robotic Learning Datasets and RT-X Models}},
  author = {Open X-Embodiment Collaboration and Abby O'Neill and Abdul Rehman and Abhinav Gupta and Abhiram Maddukuri and Abhishek Gupta and Abhishek Padalkar and Abraham Lee and Acorn Pooley and Agrim Gupta and Ajay Mandlekar and Ajinkya Jain and Albert Tung and Alex Bewley and Alex Herzog and Alex Irpan and Alexander Khazatsky and Anant Rai and Anchit Gupta and Andrew Wang and Andrey Kolobov and Anikait Singh and Animesh Garg and Aniruddha Kembhavi and Annie Xie and Anthony Brohan and Antonin Raffin and Archit Sharma and Arefeh Yavary and Arhan Jain and Ashwin Balakrishna and Ayzaan Wahid and Ben Burgess-Limerick and Beomjoon Kim and Bernhard Schölkopf and Blake Wulfe and Brian Ichter and Cewu Lu and Charles Xu and Charlotte Le and Chelsea Finn and Chen Wang and Chenfeng Xu and Cheng Chi and Chenguang Huang and Christine Chan and Christopher Agia and Chuer Pan and Chuyuan Fu and Coline Devin and others},
  year = {2023},
  eprint = {2310.08864},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2310.08864},
}

@misc{khazatsky2024droid,
  title = {{DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset}},
  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 others},
  year = {2024},
  eprint = {2403.12945},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.12945},
}

@misc{walke2023bridgedata,
  title = {{BridgeData V2: A Dataset for Robot Learning at Scale}},
  author = {Homer Walke and Kevin Black and Abraham Lee and Moo Jin Kim and Max Du and Chongyi Zheng and Tony Zhao and Philippe Hansen-Estruch and Quan Vuong and Andre He and Vivek Myers and Kuan Fang and Chelsea Finn and Sergey Levine},
  year = {2023},
  eprint = {2308.12952},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2308.12952},
}

@misc{fang2023rh,
  title = {{RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot}},
  author = {Hao-Shu Fang and Hongjie Fang and Zhenyu Tang and Jirong Liu and Chenxi Wang and Junbo Wang and Haoyi Zhu and Cewu Lu},
  year = {2023},
  eprint = {2307.00595},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2307.00595},
}

@misc{agibotworldcontributors2025agibot,
  title = {{AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems}},
  author = {AgiBot-World-Contributors and Qingwen Bu and Jisong Cai and Li Chen and Xiuqi Cui and Yan Ding and Siyuan Feng and Shenyuan Gao and Xindong He and Xuan Hu and Xu Huang and Shu Jiang and Yuxin Jiang and Cheng Jing and Hongyang Li and Jialu Li and Chiming Liu and Yi Liu and Yuxiang Lu and Jianlan Luo and Ping Luo and Yao Mu and Yuehan Niu and Yixuan Pan and Jiangmiao Pang and Yu Qiao and Guanghui Ren and Cheng Ruan and Jiaqi Shan and Yongjian Shen and Chengshi Shi and Mingkang Shi and Modi Shi and Chonghao Sima and Jianheng Song and Huijie Wang and Wenhao Wang and Dafeng Wei and Chengen Xie and Guo Xu and Junchi Yan and Cunbiao Yang and Lei Yang and Shukai Yang and Maoqing Yao and Jia Zeng and Chi Zhang and Qinglin Zhang and Bin Zhao and Chengyue Zhao and others},
  year = {2025},
  eprint = {2503.06669},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.06669},
}

@misc{grauman2021ego,
  title = {{Ego4D: Around the World in 3,000 Hours of Egocentric Video}},
  author = {Kristen Grauman and Andrew Westbury and Eugene Byrne and Zachary Chavis and Antonino Furnari and Rohit Girdhar and Jackson Hamburger and Hao Jiang and Miao Liu and Xingyu Liu and Miguel Martin and Tushar Nagarajan and Ilija Radosavovic and Santhosh Kumar Ramakrishnan and Fiona Ryan and Jayant Sharma and Michael Wray and Mengmeng Xu and Eric Zhongcong Xu and Chen Zhao and Siddhant Bansal and Dhruv Batra and Vincent Cartillier and Sean Crane and Tien Do and Morrie Doulaty and Akshay Erapalli and Christoph Feichtenhofer and Adriano Fragomeni and Qichen Fu and Abrham Gebreselasie and Cristina Gonzalez and James Hillis and Xuhua Huang and Yifei Huang and Wenqi Jia and Weslie Khoo and Jachym Kolar and Satwik Kottur and Anurag Kumar and Federico Landini and Chao Li and Yanghao Li and Zhenqiang Li and Karttikeya Mangalam and Raghava Modhugu and Jonathan Munro and Tullie Murrell and Takumi Nishiyasu and Will Price and others},
  year = {2021},
  eprint = {2110.07058},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2110.07058},
}

@misc{liu2023libero,
  title = {{LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning}},
  author = {Bo Liu and Yifeng Zhu and Chongkai Gao and Yihao Feng and Qiang Liu and Yuke Zhu and Peter Stone},
  year = {2023},
  eprint = {2306.03310},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2306.03310},
}

@misc{mees2021calvin,
  title = {{CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks}},
  author = {Oier Mees and Lukas Hermann and Erick Rosete-Beas and Wolfram Burgard},
  year = {2021},
  eprint = {2112.03227},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2112.03227},
}

@misc{james2019rlbench,
  title = {{RLBench: The Robot Learning Benchmark \& Learning Environment}},
  author = {Stephen James and Zicong Ma and David Rovick Arrojo and Andrew J. Davison},
  year = {2019},
  eprint = {1909.12271},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1909.12271},
}

@misc{yu2019meta,
  title = {{Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning}},
  author = {Tianhe Yu and Deirdre Quillen and Zhanpeng He and Ryan Julian and Avnish Narayan and Hayden Shively and Adithya Bellathur and Karol Hausman and Chelsea Finn and Sergey Levine},
  year = {2019},
  eprint = {1910.10897},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/1910.10897},
}

@misc{li2024evaluating,
  title = {{Evaluating Real-World Robot Manipulation Policies in Simulation}},
  author = {Xuanlin Li and Kyle Hsu and Jiayuan Gu and Karl Pertsch and Oier Mees and Homer Rich Walke and Chuyuan Fu and Ishikaa Lunawat and Isabel Sieh and Sean Kirmani and Sergey Levine and Jiajun Wu and Chelsea Finn and Hao Su and Quan Vuong and Ted Xiao},
  year = {2024},
  eprint = {2405.05941},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2405.05941},
}

@misc{savva2019habitat,
  title = {{Habitat: A Platform for Embodied AI Research}},
  author = {Manolis Savva and Abhishek Kadian and Oleksandr Maksymets and Yili Zhao and Erik Wijmans and Bhavana Jain and Julian Straub and Jia Liu and Vladlen Koltun and Jitendra Malik and Devi Parikh and Dhruv Batra},
  year = {2019},
  eprint = {1904.01201},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/1904.01201},
}

@misc{han2026embodied,
  title = {{Embodied Skill Bench: Benchmarking How Well Agents with Embodied Skills Perform on Physical Tasks}},
  author = {Zhi Han and Zihan Guo and Chenxi Zeng and Zicai Cui and Yue Xin and Ming Zhou and Dongzhan Zhou and Weinan Zhang and Yang Li},
  year = {2026},
  eprint = {2610.16238},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.16238},
}

@misc{wu2024robomind,
  title = {{RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation}},
  author = {Kun Wu and Chengkai Hou and Jiaming Liu and Zhengping Che and Xiaozhu Ju and Zhuqin Yang and Meng Li and Yinuo Zhao and Zhiyuan Xu and Guang Yang and Shichao Fan and Xinhua Wang and Fei Liao and Zhen Zhao and Guangyu Li and Zhao Jin and Lecheng Wang and Jilei Mao and Ning Liu and Pei Ren and Qiang Zhang and Yaoxu Lyu and Mengzhen Liu and Jingyang He and Yulin Luo and Zeyu Gao and Chenxuan Li and Chenyang Gu and Yankai Fu and Di Wu and Xingyu Wang and Sixiang Chen and Zhenyu Wang and Pengju An and Siyuan Qian and Shanghang Zhang and Jian Tang},
  year = {2024},
  eprint = {2412.13877},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.13877},
}

@misc{wang2026robocasa,
  title = {{RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation}},
  author = {Haocheng Wang and Youquan Liu and Weiyu Guo and Aokai Zhang and Donghang Wu and Hongyu Liu and Sha Zhang and Weidong Yang and Ben Fei},
  year = {2026},
  eprint = {2610.27861},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27861},
}

@misc{ramakrishnan2021habitat,
  title = {{Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI}},
  author = {Santhosh K. Ramakrishnan and Aaron Gokaslan and Erik Wijmans and Oleksandr Maksymets and Alex Clegg and John Turner and Eric Undersander and Wojciech Galuba and Andrew Westbury and Angel X. Chang and Manolis Savva and Yili Zhao and Dhruv Batra},
  year = {2021},
  eprint = {2109.08238},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2109.08238},
}

@misc{dasari2019robonet,
  title = {{RoboNet: Large-Scale Multi-Robot Learning}},
  author = {Sudeep Dasari and Frederik Ebert and Stephen Tian and Suraj Nair and Bernadette Bucher and Karl Schmeckpeper and Siddharth Singh and Sergey Levine and Chelsea Finn},
  year = {2019},
  eprint = {1910.11215},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1910.11215},
}

@misc{grauman2023ego,
  title = {{Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives}},
  author = {Kristen Grauman and Andrew Westbury and Lorenzo Torresani and Kris Kitani and Jitendra Malik and Triantafyllos Afouras and Kumar Ashutosh and Vijay Baiyya and Siddhant Bansal and Bikram Boote and Eugene Byrne and Zach Chavis and Joya Chen and Feng Cheng and Fu-Jen Chu and Sean Crane and Avijit Dasgupta and Jing Dong and Maria Escobar and Cristhian Forigua and Abrham Gebreselasie and Sanjay Haresh and Jing Huang and Md Mohaiminul Islam and Suyog Jain and Rawal Khirodkar and Devansh Kukreja and Kevin J Liang and Jia-Wei Liu and Sagnik Majumder and Yongsen Mao and Miguel Martin and Effrosyni Mavroudi and Tushar Nagarajan and Francesco Ragusa and Santhosh Kumar Ramakrishnan and Luigi Seminara and Arjun Somayazulu and Yale Song and Shan Su and Zihui Xue and Edward Zhang and Jinxu Zhang and Angela Castillo and Changan Chen and Xinzhu Fu and Ryosuke Furuta and Cristina Gonzalez and Prince Gupta and Jiabo Hu and others},
  year = {2023},
  eprint = {2311.18259},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2311.18259},
}

@misc{deitke2022objaverse,
  title = {{Objaverse: A Universe of Annotated 3D Objects}},
  author = {Matt Deitke and Dustin Schwenk and Jordi Salvador and Luca Weihs and Oscar Michel and Eli VanderBilt and Ludwig Schmidt and Kiana Ehsani and Aniruddha Kembhavi and Ali Farhadi},
  year = {2022},
  eprint = {2212.08051},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2212.08051},
}

@misc{dai2017scannet,
  title = {{ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes}},
  author = {Angela Dai and Angel X. Chang and Manolis Savva and Maciej Halber and Thomas Funkhouser and Matthias Nießner},
  year = {2017},
  eprint = {1702.04405},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/1702.04405},
}

@misc{sferrazza2024humanoidbench,
  title = {{HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation}},
  author = {Carmelo Sferrazza and Dun-Ming Huang and Xingyu Lin and Youngwoon Lee and Pieter Abbeel},
  year = {2024},
  eprint = {2403.10506},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.10506},
}

@misc{pumacay2024colosseum,
  title = {{THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation}},
  author = {Wilbert Pumacay and Ishika Singh and Jiafei Duan and Ranjay Krishna and Jesse Thomason and Dieter Fox},
  year = {2024},
  eprint = {2402.08191},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2402.08191},
}

@misc{chao2021dexycb,
  title = {{DexYCB: A Benchmark for Capturing Hand Grasping of Objects}},
  author = {Yu-Wei Chao and Wei Yang and Yu Xiang and Pavlo Molchanov and Ankur Handa and Jonathan Tremblay and Yashraj S. Narang and Karl Van Wyk and Umar Iqbal and Stan Birchfield and Jan Kautz and Dieter Fox},
  year = {2021},
  eprint = {2104.04631},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2104.04631},
}

@misc{calli2015benchmarking,
  title = {{Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols}},
  author = {Berk Calli and Aaron Walsman and Arjun Singh and Siddhartha Srinivasa and Pieter Abbeel and Aaron M. Dollar},
  year = {2015},
  eprint = {1502.03143},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1502.03143},
}

@misc{damen2020rescaling,
  title = {{Rescaling Egocentric Vision}},
  author = {Dima Damen and Hazel Doughty and Giovanni Maria Farinella and Antonino Furnari and Evangelos Kazakos and Jian Ma and Davide Moltisanti and Jonathan Munro and Toby Perrett and Will Price and Michael Wray},
  year = {2020},
  eprint = {2006.13256},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2006.13256},
}

@misc{liu2022hoi,
  title = {{HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction}},
  author = {Yunze Liu and Yun Liu and Che Jiang and Kangbo Lyu and Weikang Wan and Hao Shen and Boqiang Liang and Zhoujie Fu and He Wang and Li Yi},
  year = {2022},
  eprint = {2203.01577},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2203.01577},
}

@misc{yang2022oakink,
  title = {{OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction}},
  author = {Lixin Yang and Kailin Li and Xinyu Zhan and Fei Wu and Anran Xu and Liu Liu and Cewu Lu},
  year = {2022},
  eprint = {2203.15709},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2203.15709},
}

@misc{fan2022arctic,
  title = {{ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}},
  author = {Zicong Fan and Omid Taheri and Dimitrios Tzionas and Muhammed Kocabas and Manuel Kaufmann and Michael J. Black and Otmar Hilliges},
  year = {2022},
  eprint = {2204.13662},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2204.13662},
}

@misc{zhang2024vlabench,
  title = {{VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks}},
  author = {Shiduo Zhang and Zhe Xu and Peiju Liu and Xiaopeng Yu and Yuan Li and Qinghui Gao and Zhaoye Fei and Zhangyue Yin and Zuxuan Wu and Yu-Gang Jiang and Xipeng Qiu},
  year = {2024},
  eprint = {2412.18194},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.18194},
}

@misc{geng2025roboverse,
  title = {{RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning}},
  author = {Haoran Geng and Feishi Wang and Songlin Wei and Yuyang Li and Bangjun Wang and Boshi An and Charlie Tianyue Cheng and Haozhe Lou and Peihao Li and Yen-Jen Wang and Yutong Liang and Dylan Goetting and Chaoyi Xu and Haozhe Chen and Yuxi Qian and Yiran Geng and Jiageng Mao and Weikang Wan and Mingtong Zhang and Jiangran Lyu and Siheng Zhao and Jiazhao Zhang and Jialiang Zhang and Chengyang Zhao and Haoran Lu and Yufei Ding and Ran Gong and Yuran Wang and Yuxuan Kuang and Ruihai Wu and Baoxiong Jia and Carlo Sferrazza and Hao Dong and Siyuan Huang and Yue Wang and Jitendra Malik and Pieter Abbeel},
  year = {2025},
  eprint = {2504.18904},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.18904},
}

@misc{zhou2026egoexplorer,
  title = {{EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In Situ}},
  author = {Yunsong Zhou and Xuekun Jiang and Haiqi Shen and Hangxu Liu and Chaojian Shi and Yujie Liu and Jingyuan Li and Haoran Yang and Jiafei Cao and Dongzhan Zhou and Dong Wang and Yao Mu and Chunhua Shen and Weinan Zhang},
  year = {2026},
  eprint = {2610.18872},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.18872},
}

@misc{luo2026handson,
  title = {{HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation}},
  author = {Tianwei Luo and Yiming He and Hongjin Wu and Ting Pan and Debin Ren and Haorui Guo and Junlin Yang and Yuxin Zuo and Zhehao Kou and Kaisen Yang and Zhuoqun Lai and Yi Ding and Jiale Yu and Yuchen Zhang and Zijie Qiu and Haozhan Li and Ning Ding},
  year = {2026},
  eprint = {2610.26765},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.26765},
}

@misc{liu2026robovalue,
  title = {{RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models}},
  author = {Shengbang Liu and Zhengye Du and Zhilong Wan and Honghao Su and Chenxiang Xia and Chang Ge and Jinyang Xiao and Nan Wang and Zhipeng Hu and Huining Yuan and Shu'ang Yu and Yue Chen and Tianxing Chen and Chuankang Li and Maoqing Yao and Wenbo Ding and Yu Wang and Guanghui Ren and Chao Yu},
  year = {2026},
  eprint = {2610.26663},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.26663},
}

@misc{sung2026libero,
  title = {{LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints}},
  author = {Ming Shin Cindy Sung and Duan Leijiahao and Haoxiang Wang and Boning Tan and Liangna Fu and Chao Tan and Yafu Li and Yulong Chen and Chaoqun Wan and Zhen Huang and Shuxian Liang and Xian-Sheng Hua},
  year = {2026},
  eprint = {2610.16782},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2610.16782},
}

@misc{hoque2025egodex,
  title = {{EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video}},
  author = {Ryan Hoque and Peide Huang and David J. Yoon and Mouli Sivapurapu and Jian Zhang},
  year = {2025},
  eprint = {2505.11709},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2505.11709},
}

@misc{leng2026flora,
  title = {{FLORA: An Open Model Suite for Scaling Robotics Data Engines}},
  author = {Sicong Leng and Yunze Man and Zhiqi Li and Jing Wang and Yuhe Zhang and Ryan Punamiya and Siddharth Patki and Kaiyuan Zheng and Zi-ang Cao and Zhiding Yu and Sifei Liu and Danfei Xu and Ben Levin and Jan Kautz and Yuke Zhu and Johan Bjorck and Linxi "Jim" Fan},
  year = {2026},
  eprint = {2610.31779},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31779},
}

@misc{wang2026bidex,
  title = {{BiDex-100: A Comprehensive Benchmark for Bimanual Dexterous Manipulation Across 100+ Simulation Tasks}},
  author = {Yong Wang and Kecheng Zheng and Xing Zhu and Chao Xu and Yujun Shen and Shengze Cai},
  year = {2026},
  eprint = {2610.25459},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.25459},
}

@misc{wang2026astrobench,
  title = {{AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation}},
  author = {Zizhe Wang and Jia Deng and Xin Lu and Zehao Jia and Yi Huang and Yao Zhu},
  year = {2026},
  eprint = {2610.31064},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31064},
}

@misc{chen2026embodied,
  title = {{Embodied Playground: A Long-Horizon Agentic Robotics Benchmark for Physical, Strategic, and Spatial Reasoning}},
  author = {Feng Chen and Pei Zhou and Lixuan He and Yunchao Yao and Li Sun and Shenghua Gao and Mingyu Ding and Kaifeng Zhang and Kaichen Zhou and Yi Ma},
  year = {2026},
  eprint = {2610.27039},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27039},
}

@misc{chen2026behavior,
  title = {{Behavior Spatial Benchmark: Evaluating Spatial Understanding for Robotics}},
  author = {Sirui Chen and Huang Huang and Qineng Wang and Wenlong Huang and Manling Li and Ruohan Zhang and Li Fei-Fei and Jiajun Wu},
  year = {2026},
  eprint = {2610.34051},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34051},
}

@misc{gao2026embodiedlab,
  title = {{EmbodiedLab: Benchmarking Embodied Agents That Act to Know}},
  author = {Hongcheng Gao and Zelin Zheng and Alex Zhou and Jay Zhu and Shijia Ge and Yazhe Wang and Xiping Li and Jianshu Zeng and Di Wu and Xuan Shangguan and Yexing Wan and Lingyu He and Yongli Wang and Xiaohan Yu and Zhiqi Jia and Yue Liu and Bryan Hooi and Yinpeng Dong and Wentao Zhang and Sihang Wu and Xiao He},
  year = {2026},
  eprint = {2610.35385},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35385},
}

@misc{mao2026robotagentbench,
  title = {{RobotAgentBench: Towards Open-world Robot Autonomy}},
  author = {Lingjun Mao and Jinglin Cao and Lukun He and Wenpeng Xu and Yuchen Yan and Hengyu Jin and Zijun Zhang and Jinzhou Tang and Songyao Jin and Ziche Liu and Yifei Shao and Junbo Huang and Fang Nan and Ruobing Han and Ziqiao Xi and Ziming Xu and Shuang Liang and Sibo Zhu and Wenyi Wu and Xinyue Wang and Yiming Huang and Xinkai Zou and Gao Zhu and Kun Zhou and Biwei Huang},
  year = {2026},
  eprint = {2610.34649},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34649},
}

@misc{hickok2026so,
  title = {{SO-101 Bench: Accessible Spatial Manipulation}},
  author = {Truman Hickok},
  year = {2026},
  eprint = {2610.36420},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.36420},
}

@misc{ma2026robojudge,
  title = {{RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation}},
  author = {Siyuan Ma and Yu Qi and Cheng Ye and Ruotian Peng and Xinyi Xu and Zitiantao Lin and Zedong Cai and Yijian Huang and Weiyang Liu and Siyuan Wang and Yandong Wen},
  year = {2026},
  eprint = {2610.27782},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.27782},
}

@misc{shaw2023leap,
  title = {{LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning}},
  author = {Kenneth Shaw and Ananye Agarwal and Deepak Pathak},
  year = {2023},
  eprint = {2309.06440},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.06440},
}

@misc{wu2023gello,
  title = {{GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators}},
  author = {Philipp Wu and Yide Shentu and Zhongke Yi and Xingyu Lin and Pieter Abbeel},
  year = {2023},
  eprint = {2309.13037},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.13037},
}

@misc{cheng2024open,
  title = {{Open-TeleVision: Teleoperation with Immersive Active Visual Feedback}},
  author = {Xuxin Cheng and Jialong Li and Shiqi Yang and Ge Yang and Xiaolong Wang},
  year = {2024},
  eprint = {2407.01512},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2407.01512},
}

@misc{liao2024berkeley,
  title = {{Berkeley Humanoid: A Research Platform for Learning-based Control}},
  author = {Qiayuan Liao and Bike Zhang and Xuanyu Huang and Xiaoyu Huang and Zhongyu Li and Koushil Sreenath},
  year = {2024},
  eprint = {2407.21781},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2407.21781},
}

@misc{chi2025demonstrating,
  title = {{Demonstrating Berkeley Humanoid Lite: An Open-source, Accessible, and Customizable 3D-printed Humanoid Robot}},
  author = {Yufeng Chi and Qiayuan Liao and Junfeng Long and Xiaoyu Huang and Sophia Shao and Borivoje Nikolic and Zhongyu Li and Koushil Sreenath},
  year = {2025},
  eprint = {2504.17249},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.17249},
}

@misc{shi2025toddlerbot,
  title = {{ToddlerBot: Open-Source ML-Compatible Humanoid Platform for Loco-Manipulation}},
  author = {Haochen Shi and Weizhuo Wang and Shuran Song and C. Karen Liu},
  year = {2025},
  eprint = {2502.00893},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.00893},
}

@misc{jiang2025behavior,
  title = {{BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities}},
  author = {Yunfan Jiang and Ruohan Zhang and Josiah Wong and Chen Wang and Yanjie Ze and Hang Yin and Cem Gokmen and Shuran Song and Jiajun Wu and Li Fei-Fei},
  year = {2025},
  eprint = {2503.05652},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.05652},
}

@misc{team2024aloha,
  title = {{ALOHA 2: An Enhanced Low-Cost Hardware for Bimanual Teleoperation}},
  author = {ALOHA 2 Team and Jorge Aldaco and Travis Armstrong and Robert Baruch and Jeff Bingham and Sanky Chan and Kenneth Draper and Debidatta Dwibedi and Chelsea Finn and Pete Florence and Spencer Goodrich and Wayne Gramlich and Torr Hage and Alexander Herzog and Jonathan Hoech and Thinh Nguyen and Ian Storz and Baruch Tabanpour and Leila Takayama and Jonathan Tompson and Ayzaan Wahid and Ted Wahrburg and Sichun Xu and Sergey Yaroshenko and Kevin Zakka and Tony Z. Zhao},
  year = {2024},
  eprint = {2405.02292},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2405.02292},
}

@misc{kemp2021design,
  title = {{The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environments}},
  author = {Charles C. Kemp and Aaron Edsinger and Henry M. Clever and Blaine Matulevich},
  year = {2021},
  eprint = {2109.10892},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.10892},
}

@misc{christoph2025orca,
  title = {{ORCA: An Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning}},
  author = {Clemens C. Christoph and Maximilian Eberlein and Filippos Katsimalis and Arturo Roberti and Aristotelis Sympetheros and Michel R. Vogt and Davide Liconti and Chenyu Yang and Barnabas Gavin Cangan and Ronan J. Hinchet and Robert K. Katzschmann},
  year = {2025},
  eprint = {2504.04259},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.04259},
}

@misc{ben2025homie,
  title = {{HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit}},
  author = {Qingwei Ben and Feiyu Jia and Jia Zeng and Junting Dong and Dahua Lin and Jiangmiao Pang},
  year = {2025},
  eprint = {2502.13013},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.13013},
}

@misc{qin2023anyteleop,
  title = {{AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System}},
  author = {Yuzhe Qin and Wei Yang and Binghao Huang and Karl Van Wyk and Hao Su and Xiaolong Wang and Yu-Wei Chao and Dieter Fox},
  year = {2023},
  eprint = {2307.04577},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2307.04577},
}

@misc{fang2023airexo,
  title = {{AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wild}},
  author = {Hongjie Fang and Hao-Shu Fang and Yiming Wang and Jieji Ren and Jingjing Chen and Ruo Zhang and Weiming Wang and Cewu Lu},
  year = {2023},
  eprint = {2309.14975},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2309.14975},
}

@misc{fang2025airexo,
  title = {{AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons}},
  author = {Hongjie Fang and Chenxi Wang and Yiming Wang and Jingjing Chen and Shangning Xia and Jun Lv and Zihao He and Xiyan Yi and Yunhan Guo and Xinyu Zhan and Lixin Yang and Weiming Wang and Cewu Lu and Hao-Shu Fang},
  year = {2025},
  eprint = {2503.03081},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2503.03081},
}

@misc{ding2024bunny,
  title = {{Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning}},
  author = {Runyu Ding and Yuzhe Qin and Jiyue Zhu and Chengzhe Jia and Shiqi Yang and Ruihan Yang and Xiaojuan Qi and Xiaolong Wang},
  year = {2024},
  eprint = {2407.03162},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2407.03162},
}

@misc{dass2024telemoma,
  title = {{TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation}},
  author = {Shivin Dass and Wensi Ai and Yuqian Jiang and Samik Singh and Jiaheng Hu and Ruohan Zhang and Peter Stone and Ben Abbatematteo and Roberto Martín-Martín},
  year = {2024},
  eprint = {2403.07869},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.07869},
}

@misc{grimminger2019open,
  title = {{An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research}},
  author = {Felix Grimminger and Avadesh Meduri and Majid Khadiv and Julian Viereck and Manuel Wüthrich and Maximilien Naveau and Vincent Berenz and Steve Heim and Felix Widmaier and Thomas Flayols and Jonathan Fiene and Alexander Badri-Spröwitz and Ludovic Righetti},
  year = {2019},
  eprint = {1910.00093},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1910.00093},
}

@misc{xu2025dexumi,
  title = {{DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation}},
  author = {Mengda Xu and Han Zhang and Yifan Hou and Zhenjia Xu and Linxi Fan and Manuela Veloso and Shuran Song},
  year = {2025},
  eprint = {2505.21864},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.21864},
}

@misc{yang2024ace,
  title = {{ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation}},
  author = {Shiqi Yang and Minghuan Liu and Yuzhe Qin and Runyu Ding and Jialong Li and Xuxin Cheng and Ruihan Yang and Sha Yi and Xiaolong Wang},
  year = {2024},
  eprint = {2408.11805},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2408.11805},
}

@misc{lin2024learning,
  title = {{Learning Visuotactile Skills with Two Multifingered Hands}},
  author = {Toru Lin and Yu Zhang and Qiyang Li and Haozhi Qi and Brent Yi and Sergey Levine and Jitendra Malik},
  year = {2024},
  eprint = {2404.16823},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2404.16823},
}

@misc{wu2024tidybot,
  title = {{TidyBot++: An Open-Source Holonomic Mobile Manipulator for Robot Learning}},
  author = {Jimmy Wu and William Chong and Robert Holmberg and Aaditya Prasad and Yihuai Gao and Oussama Khatib and Shuran Song and Szymon Rusinkiewicz and Jeannette Bohg},
  year = {2024},
  eprint = {2412.10447},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.10447},
}

@misc{ha2024umi,
  title = {{UMI-on-Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers}},
  author = {Huy Ha and Yihuai Gao and Zipeng Fu and Jie Tan and Shuran Song},
  year = {2024},
  eprint = {2407.10353},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2407.10353},
}

@misc{zhang2025doglove,
  title = {{DOGlove: Dexterous Manipulation with a Low-Cost Open-Source Haptic Force Feedback Glove}},
  author = {Han Zhang and Songbo Hu and Zhecheng Yuan and Huazhe Xu},
  year = {2025},
  eprint = {2502.07730},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.07730},
}

@misc{zorin2025ruka,
  title = {{RUKA: Rethinking the Design of Humanoid Hands with Learning}},
  author = {Anya Zorin and Irmak Guzey and Billy Yan and Aadhithya Iyer and Lisa Kondrich and Nikhil X. Bhattasali and Lerrel Pinto},
  year = {2025},
  eprint = {2504.13165},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.13165},
}

@misc{shaw2024bimanual,
  title = {{Bimanual Dexterity for Complex Tasks}},
  author = {Kenneth Shaw and Yulong Li and Jiahui Yang and Mohan Kumar Srirama and Ray Liu and Haoyu Xiong and Russell Mendonca and Deepak Pathak},
  year = {2024},
  eprint = {2411.13677},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2411.13677},
}

@misc{xie2026dexport,
  title = {{DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection}},
  author = {Amber Xie and Jiawei Fu and Xiaofeng Guo and Carmelo Sferrazza and Guanya Shi and Haozhi Qi},
  year = {2026},
  eprint = {2610.32969},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32969},
}

@misc{adwani2026phd,
  title = {{PHD-Hand: A Printable Humanoid Dexterous Hand with Linkage-Driven 3-DOA Digits}},
  author = {Neel Adwani and Muhaiminul Islam Akash and Saffia Ouali and Ethan Liu and Cong Wang},
  year = {2026},
  eprint = {2610.29030},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.29030},
}

@misc{langella2026locopilot,
  title = {{LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning}},
  author = {Antonio Langella and Giovanni Minelli and Giovanni B. Dessy and Lorenzo Amatucci and Giulio Turrisi and Victor Barasuol and Claudio Semini},
  year = {2026},
  eprint = {2610.27998},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27998},
}

@misc{murali2026openjaws,
  title = {{OpenJaws: An Open Hardware UMI Framework with Stereo Localization for Generalist Manipulation}},
  author = {Adithyavairavan Murali and Yash Oza and Karanbir Chahal and Neel Jawale and Silas De Vries and Hesam Rabeti and Erwin Coumans and Balakumar Sundaralingam and Stan Birchfield},
  year = {2026},
  eprint = {2610.36598},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36598},
}