Tongzhou Mu 木同舟

Tongzhou Mu 


Ph.D. in Computer Science,
University of California San Diego

Email: tongzhou.mu [@] gmail [DOT] com
X(Twitter) / Google Scholar / Github / LinkedIn


experience 

About me

I study video world models for robotics at Rhoda AI.

I earned my Ph.D. from the University of California San Diego, where I was fortunate to be advised by Prof. Hao Su. My academic background also includes a B.Eng. from Zhejiang University, and an M.Sc. from UC San Diego. I previously interned at 1X Technologies, NVIDIA Robotics Lab, and Microsoft Research Asia.

I am the primary developer of the first ManiSkill benchmark, and a key contributor to its succeeding generations, ManiSkill 2 and ManiSkill 3. ManiSkill has become one of the most widely adopted open-source simulation frameworks for robot learning.

Publications & Preprints

Papers sorted by years. Representative papers are highlighted.
* indicates equal contribution.

2026

 

Does Scaling Web-Video Pre-training Help Real Robots Do Real Work?
Tongzhou Mu and the Rhoda AI Team
Research Blog
[Blog Page] [Twitter Post]

dva 

Causal Video Models Are Data-Efficient Robot Policy Learners
Rhoda AI Team
Research Blog
[Blog Page] [Twitter Post]

dexwm 

Scaling Cross-Embodiment World Models for Dexterous Manipulation
Zihao He*, Bo Ai*, Tongzhou Mu, Yulin Liu, Weikang Wan, Jiawei Fu, Yilun Du, Henrik I. Christensen, Hao Su
International Conference on Intelligent Robots and Systems (IROS) 2026
[Project Page] [arXiv]

2025

esl 

Towards Embodiment Scaling Laws in Robot Locomotion
Bo Ai*, Liu Dai*, Nico Bohlinger* , Dichen Li*, Tongzhou Mu, Zhanxin Wu, K. Fay, Henrik I. Christensen, Jan Peters, Hao Su
Conference on Robot Learning (CoRL) 2025
[Project Page] [Twitter Post] [arXiv] [Video]

demo3 

DEMO³: Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning
Adrià López Escoriza, Nicklas Hansen, Stone Tao, Tongzhou Mu, Hao Su
International Conference on Machine Learning (ICML) 2025
[Project Page] [Twitter Post] [arXiv] [Code]

rnrdp 

Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
Zhuoqun Chen*^, Xiu Yuan*^, Tongzhou Mu, Hao Su
Transactions on Machine Learning Research (TMLR) 2025
[Project Page] [arXiv] [Code]
^Zhuoqun Chen and Xiu Yuan are students I advised

maniskill3 

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
Stone Tao, Fanbo Xiang, Arth Shukla, Yuzhe Qin, Xander Hinrichsen, Xiaodi Yuan, Chen Bao, Xinsong Lin, Yulin Liu, Tse-kai Chan, Yuan Gao, Xuanlin Li, Tongzhou Mu, Nan Xiao, Arnav Gurha, Viswesh Nagaswamy Rajesh, Yong Woo Choi, Yen-Ru Chen, Zhiao Huang, Roberto Calandra, Rui Chen, Shan Luo, Hao Su
Robotics: Science and Systems (RSS) 2025
[Project Page] [arXiv] [Code]

pi_dec 

Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
Xiu Yuan*^, Tongzhou Mu*, Stone Tao, Yunhao Fang, Mengke Zhang, Hao Su
International Conference on Learning Representations (ICLR) 2025
[Project Page] [Twitter Post] [arXiv] [Video] [Code] [Slides]
^ Xiu Yuan is an undergruduate student I advised

s2v_dagger 

When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
Tongzhou Mu*, Zhaoyang Li*^, Stanisław Wiktor Strzelecki*^, Xiu Yuan, Yunchao Yao, Litian Liang, Hao Su
AAAI Conference on Artificial Intelligence (AAAI) 2025
[arXiv] [Code]
^ Zhaoyang and Stanisław are master students I advised

2024

llm_explore 

Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving
Zhan Ling, Yunhao Fang, Xuanlin Li, Tongzhou Mu, Mingu Lee, Reza Pourreza, Roland Memisevic, Hao Su
Tech Report
[arXiv] [Code]

adademo 

AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent
Tongzhou Mu, Yijie Guo, Jie Xu, Ankit Goyal, Hao Su, Dieter Fox, Animesh Garg
International Symposium of Robotics Research (ISRR) 2024
Data-centric Machine Learning Research (DMLR) at ICLR 2024
[arXiv] [Slides]

drs 

DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks
Tongzhou Mu, Minghua Liu, Hao Su
International Conference on Learning Representations (ICLR) 2024
[Project Page] [Twitter Post] [arXiv] [Video] [Code] [Slides] [Poster]

2023

no_pretrain 

On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
Nicklas Hansen*, Zhecheng Yuan*, Yanjie Ze*, Tongzhou Mu* , Aravind Rajeswaran+, Hao Su+, Huazhe Xu+, Xiaolong Wang+
International Conference on Machine Learning (ICML) 2023
[arXiv] [Code]

skill_trans 

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
Stone Tao^, Xiaochen Li^, Tongzhou Mu, Zhiao Huang, Yuzhe Qin, Hao Su
International Conference on Machine Learning (ICML) 2023
[Project Page] [arXiv] [Video] [Code] [Slides]
^Stone Tao and Xiaochen Li are undergruduate students I advised

demo_rl 

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey
Tongzhou Mu, Hao Su
Tech Report
[arXiv] [Slides]

maniskill2 

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
Jiayuan Gu, Fanbo Xiang, Xuanlin Li*, Zhan Ling*, Xiqiang Liu*, Tongzhou Mu* , Yihe Tang*, Stone Tao*, Xinyue Wei*, Yunchao Yao*, Xiaodi Yuan, Pengwei Xie, Zhiao Huang, Rui Chen, Hao Su
* equally contributed authors are ordered by alphabets
International Conference on Learning Representations (ICLR) 2023
[Project Page] [arXiv] [Code] [Challenge Website]

active 

Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation
Xiaoshuai Zhang, Rui Chen, Fanbo Xiang, Yuzhe Qin, Jiayuan Gu, Zhan Ling, Minghua Liu, Peiyu Zeng, Songfang Han, Zhiao Huang, Tongzhou Mu, Jing Xu, Hao Su
IEEE Transactions on Robotics (T-RO) 2023
[arXiv]

2022

inter_rl 

Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning
Tongzhou Mu, Kaixiang Lin, Feiyang Niu, Govind Thattai
Transactions on Machine Learning Research (TMLR) 2022
[arXiv]

2021

ManiSkill 

ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations
Tongzhou Mu* , Zhan Ling*, Fanbo Xiang*, Derek Yang*, Xuanlin Li*, Stone Tao, Zhiao Huang, Zhiwei Jia, Hao Su
Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track 2021
[arXiv] [Video] [Slides] [Poster] [Code] [Baselines] [Challenge Website]

arena 

Arena: A Scalable and Configurable Benchmark for Policy Learning
Sirui Xu, Shuang Liu, Tongzhou Mu, Zhiwei Jia, Yiran Wu, Hao Su
Preprint
[Code]

2020

policy_refactorization 

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Tongzhou Mu* , Jiayuan Gu*, Zhiwei Jia, Hao Tang, Hao Su
Conference on Neural Information Processing Systems (NeurIPS) 2020
[Project Page] [arXiv] [Poster] [Slides] [Code]

sail 

State Alignment-based Imitation Learning
Fangchen Liu, Zhan Ling, Tongzhou Mu, Hao Su
International Conference on Learning Representations (ICLR) 2020
[arXiv] [Code]


Before 2019

value_transfer 

Transfer Value or Policy? A Value-centric Framework Towards Transferrable Continuous Reinforcement Learning
Xingchao Liu*, Tongzhou Mu* , Hao Su
Deep Reinforcement Learning Workshop at NeurIPS 2018

doubly_sgd 

Accelerated Doubly Stochastic Gradient Algorithm for Large-scale Empirical Risk Minimization
Zebang Shen, Hui Qian, Tongzhou Mu, Chao Zhang
International Joint Conference on Artificial Intelligence (IJCAI) 2017

adaptive_vr 

Adaptive Variance Reducing for Stochastic Gradient Descent
Zebang Shen, Hui Qian, Tengfei Zhou, Tongzhou Mu
International Joint Conference on Artificial Intelligence (IJCAI) 2016

Talks

Awards

Misc

  • I love powerlifting, tennis, golfing, and surfing in my free time.