Faculty

Yao Mu
Assistant Professor

Email:muyao@sjtu.edu.cn

Institute:Institute of Artificial Intelligence

MainPage:yaomarkmu.github.io

Brief Introduction

Yao Mu is a tenure-track Assistant Professor at Shanghai Jiao Tong University. He is a recipient of a national-level young talent program and a Shanghai overseas high-level talent award. He received his Ph.D. from the Department of Computer Science at The University of Hong Kong and has been a visiting researcher at ETH Zurich, the National University of Singapore, and other institutions.

Dr. Mu has long been engaged in research on multimodal embodied intelligence and robot learning. He has served as an Area Chair for top international machine learning conferences such as ICLR, and is an Executive Committee Member of the Technical Committee on Intelligent Robots of the China Computer Federation. He has also organized multiple workshops and challenges at leading international conferences, including CVPR 2025, IROS 2025, and SIGGRAPH Asia 2025.

He has published more than 50 papers in top international journals and conferences in computer science, including IJRR, RSS, NeurIPS, ICML, and CVPR, with over 3,200 citations on Google Scholar. His honors include a nomination for the Best Paper Award at IROS 2025, the Best Paper Award at the ECCV 2024 Workshop on Collaborative Embodied Intelligence, the 2024 Scholarship Award at the Chinese Association of Automation Symposium on Autonomous Robots (awarded to only five researchers nationwide), the Best Student Paper Award at IEEE ICCAS 2020, and a nomination for the Best Student Paper Award at IEEE IV 2021.


Education

2021-09 至 2025-04, 香港大学, 博士

2018-09 至 2021-06, 清华大学, 硕士
2014-09 至 2018-06, 哈尔滨工业大学, 学士





Professional Experience

2025年加入上海交通大学参加工作

Publications


I. Representative Publications in the Past Five Years

  1. Yao Mu; Qinglong Zhang; Mengkang Hu; Wenhai Wang; Mingyu Ding; Jun Jin; Bin Wang; Jifeng Dai; Yu Qiao; Ping Luo; EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought, The Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, USA, 2023-12-12 to 2023-12-14, Conference Paper, Sole First Author.

  2. Yao Mu; Shoufa Chen; Mingyu Ding; Jianyu Chen; Runjian Chen; Ping Luo; CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer, The Thirty-Ninth International Conference on Machine Learning (ICML 2022), Baltimore, Maryland, USA, 2022-7-17 to 2022-7-23, Conference Paper, Sole First Author.

  3. Yao Mu; Yuzheng Zhuang; Fei Ni; Bin Wang; Jianyu Chen; Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning, The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, USA, 2022-11-28 to 2022-12-9, Conference Paper, Sole First Author.

  4. Yao Mu; Junting Chen; Qinglong Zhang; Shoufa Chen; Qiaojun Yu; Chongjian Ge; Runjian Chen; Zhixuan Liang; Mengkang Hu; Chaofan Tao; Peize Sun; Haibao Yu; Chao Yang; Wenqi Shao; Wenhai Wang; Jifeng Dai; Yu Qiao; Mingyu Ding; Ping Luo; RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis, The Forty-First International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-7-21 to 2024-7-27, Conference Paper, Sole First Author.

  5. Yao Mu; Tianxing Chen; Zanxin Chen; Shijia Peng; Zhiqian Lan; Zeyu Gao; Zhixuan Liang; Qiaojun Yu; Yude Zou; Mingkun Xu; Lunkai Lin; Zhiqiang Xie; Mingyu Ding; Ping Luo; RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins, The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025), Nashville, TN, USA, 2025-6-11 to 2025-6-15, Conference Paper, Co-First Author, Co-Corresponding Author.


II. Other Published Works

  1. Yao Mu; Yuzheng Zhuang; Bin Wang; Guangxiang Zhu; Wulong Liu; Jianyu Chen; Ping Luo; Shengbo Eben Li; Chongjie Zhang; Jianye Hao; Model-Based Reinforcement Learning via Imagination with Derived Memory, The Thirty-Fifth Annual Conference on Neural Information Processing Systems (NeurIPS 2021), Virtual-only, 2021-12-7 to 2021-12-10, Conference Paper, Sole First Author.

  2. Yao Mu; Shunyu Yao; Mingyu Ding; Ping Luo; Chuang Gan; EC2: Emergent Communication for Embodied Control, The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023 (CVPR 2023), Vancouver, Canada, 2023-8-18 to 2023-8-22, Conference Paper, Sole First Author.

  3. Yao Mu; Baiyu Peng; Ziqing Gu; Shengbo Eben Li; Chang Liu; Bingbing Nie; Jianfeng Zheng; Bo Zhang; Mixed Reinforcement Learning for Efficient Policy Optimization in Stochastic Environments, The 20th International Conference on Control, Automation and Systems (ICCAS 2020), Busan, Korea, 2020-10-13 to 2020-10-16, Conference Paper, Sole First Author.

  4. Tianxing Chen; Yao Mu; Zhixuan Liang; Zanxin Chen; Shijia Peng; Qiangyu Chen; Mingkun Xu; Ruizhen Hu; Hongyuan Zhang; Xuelong Li; Ping Luo; G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation, The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR 2025), Nashville, TN, USA, 2025-6-11 to 2025-6-15, Conference Paper, Co-First Author, Co-Corresponding Author.

  5. Pengying Wu; Yao Mu; Bingxian Wu; Yi Hou; Ji Ma; Shanghang Zhang; Chang Liu; Voronoi-based Zero-shot Object Navigation with Large Language Model, The Forty-First International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-7-21 to 2024-7-27, Conference Paper, Co-First Author.

  6. Zeyu Gao; Yao Mu; Chen Chen; Jingliang Duan; Ping Luo; Yanfeng Lu; Shengbo Eben Li; Enhance Sample Efficiency and Robustness of End-to-End Urban Autonomous Driving via Semantic Masked World Model, IEEE Transactions on Intelligent Transportation Systems, 2024, 25(10): 13067-13079, Journal Article, Co-First Author.

  7. Shentao Qin; Yujie Yang; Yao Mu; Jie Li; Wenjun Zou; Jingliang Duan; Shengbo Eben Li; Feasible Reachable Policy Iteration, The Forty-First International Conference on Machine Learning (ICML 2024), Vienna, Austria, 2024-7-21 to 2024-7-27, Conference Paper, Co-First Author.

  8. Kehan Wen; Yutong Hu; Yao Mu; Lei Ke; M3PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model, The Thirteenth International Conference on Learning Representations (ICLR 2025), Singapore, 2025-4, Conference Paper, Co-Corresponding Author.

  9. Zhihao Zhu; Yifan Zheng; Siyu Pan; Yaohui Jin; Yao Mu; PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation, International Conference on Computer Vision 2025 (ICCV 2025), Hawaii, USA, 2025, Conference Paper, Co-Corresponding Author.

  10. Zhixuan Liang; Yao Mu; Mingyu Ding; Fei Ni; Masayoshi Tomizuka; Ping Luo; AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners, The Fortieth International Conference on Machine Learning (ICML 2023), Hawaii, USA, 2023-7-23 to 2023-7-29.


Awards

Awarded the Best Paper Finalist at IROS 2025, the Best Paper Award at the ECCV 2024 Workshop on Collaborative Embodied Intelligence, the Scholarship Award at the 2024 Chinese Association of Automation Symposium on Autonomous Robots (one of only five recipients nationwide), the Best Student Paper Award at IEEE ICCAS 2020, the Best Student Paper Finalist at IEEE IV 2021, as well as the Hong Kong PhD Fellowship, the Presidential Scholarship of The University of Hong Kong, and honors including Outstanding Graduate of Tsinghua University.


Academic Service

He has served as an Area Chair for ICLR, one of the premier international conferences in machine learning, and as an Executive Committee Member of the Technical Committee on Intelligent Robots of the China Computer Federation (CCF). He has also organized multiple workshops at leading international conferences, including CVPR 2025, IROS 2025, and SIGGRAPH Asia 2025. In addition, he was invited as a distinguished speaker at the 2025 ChinaMM, an invited speaker at the 2024 and 2025 China Embodied Intelligence Conference, an invited speaker at the 2024 and 2025 Vision and Learning Youth Scholar Symposium, and an invited speaker at the Young Scholars Forum of the 9th International Conference on Cognitive Systems and Information Processing, among others.

He initiated and led the RoboTwin Bimanual Collaborative Robot Challenge at CVPR, which attracted more than 60 teams worldwide, and co-organized the bimanual manipulation competition of the 19th “Challenge Cup” Artificial Intelligence+ Special Competition together with Horizon Robotics. In collaboration with partners including Horizon Rich Robot, he also co-founded the embodied intelligence community Deeptimber, which has grown to more than 1,500 active members and has hosted over 20 academic forums.