Huazhe Xu

[Google Scholar] [Twitter]
Home Publication Group Contact Misc

( * indicates equally leading, + indicates equally advising)

Suning Huang*, Zheyu Zhang*, Tianhai Liang, Yihan Xu, Zhehao Kou, Chenhao Lu, Guowei Xu, Zhengrong Xue, Huazhe Xu
MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
arXiv preprint, 2024.

[arXiv] [project page] [twitter]

Jikai Xu*, Lei Wu*, Changyi Lin, Ding Zhao, and Huazhe Xu
DTactive: A Vision-Based Tactile Sensor with Active Surface
arXiv preprint, 2024.

[arXiv] [project page] [hardware] [twitter]

Yuanhang Zhang*, Tianhai Liang*, Zhenyang Chen, Yanjie Ze, Huazhe Xu
Catch It! Learning to Catch in Flight with Mobile Dexterous Hands
arXiv preprint, 2024.

[arXiv] [project page] [twitter]

Chengkai Hou, Zhengrong Xue, Bingyang Zhou, Jinghan Ke, Shao Lin, Huazhe Xu
Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
Conference on Neural Information Processing Systems Datasets & Benchmarks Track (NeurIPS), 2024.

[arXiv] [project page]

Yongyuan Liang, Tingqiang Xu, Kaizhe Hu, Guangqi Jiang, Furong Huang, Huazhe Xu
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
Conference on Neural Information Processing Systems Datasets & Benchmarks Track (NeurIPS), 2024.

[arXiv] [project page]

Zhecheng Yuan*, Tianming Wei*, Shuiqi Cheng, Gu Zhang, Yuanpei Chen, Huazhe Xu
Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning
Conference on Robot Learning (CoRL), 2024.

[arXiv] [project page]

Chongkai Gao, Zhengrong Xue, Shuying Deng, Tianhai Liang, Siqi Yang, Lin Shao, Huazhe Xu
RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation without Point Cloud Segmentation
Conference on Robot Learning (CoRL), 2024.

[arXiv] [project page] [code]

Pu Hua*, Minghuan Liu*, Annabella Macaluso*, Yunfeng Lin, Weinan Zhang, Huazhe Xu, Lirui Wang
GenSim2: Scaling Robotic Data Generation with Multi-modal and Reasoning LLMs
Conference on Robot Learning (CoRL), 2024.

[arXiv] [project page] [code]

Yuanchen Ju*, Kaizhe Hu*, Guowei Zhang, Gu Zhang, Mingrun Jiang, Huazhe Xu
Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation
European Conference on Computer Vision (ECCV), 2024.

[arXiv] [project page] [code]

Tao Huang*, Guangqi Jiang*, Yanjie Ze, Huazhe Xu
Diffusion Reward: Learning Rewards via Conditional Video Diffusion
European Conference on Computer Vision (ECCV), 2024.

[arXiv] [project page] [code]

Zhengmao He, Kun Lei, Yanjie Ze, Koushil Sreenath, Zhongyu Li, Huazhe Xu
Learning Visual Quadrupedal Loco-Manipulation from Demonstrations
International Conference on Intelligent Robots and Systems (IROS), 2024.

[arXiv] [project page] [Twitter/X] [code coming soon]

Zeyuan Liu, Ziyu Huan, Xiyao Wang, Jiafei Lyu, Jian Tao, Xiu Li, Furong Huang, Huazhe Xu
World Models with Hints of Large Language Models for Goal Achieving
ArXiv Preprint, 2024.

[arXiv]

Yanjie Ze*, Gu Zhang*, Kangning Zhang, Chenyuan Hu, Muhan Wang, Huazhe Xu
3D Diffusion Policy
Robotics: Science and Systems (RSS), 2024.

[arXiv] [project page] [code]

Tianying Ji*, Yongyuan Liang*, Yan Zeng, Yu Luo, Guowei Xu, Jiawei Guo, Ruijie Zheng, Furong Huang, Fuchun Sun, Huazhe Xu
ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
International Conference on Machine Learning (ICML), 2024. (oral)

[arXiv] [project page] [code]

Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan
OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
International Conference on Machine Learning (ICML), 2024. (oral)

[arXiv] [code]

Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan
Offline-Boosted Actor-Critic:Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
International Conference on Machine Learning (ICML), 2024.

[arXiv] [project page] [code]

Chenhao Lu, Ruizhe Shi, Yuyao Liu, Kaizhe Hu, Simon S. Du, Huazhe Xu
Rethinking Transformers in Solving POMDPs
International Conference on Machine Learning (ICML), 2024.

[arXiv] [code]

Tianying Ji, Yu Luo, Fuchun Sun, Xianyuan Zhan, Jianwei Zhang, Huazhe Xu.
Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
International Conference on Machine Learning (ICML), 2024.

[arXiv] [project page] [code coming soon]

Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daumé III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang.
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
International Conference on Machine Learning (ICML), 2024.

[arXiv] [project page] [code]

Guoping Pan*, Qingwei Ben*, Zhecheng Yuan, Guangqi Jiang, Yandong Ji, Jiangmiao Pang, Houde Liu, Huazhe Xu
RoboDuet: A Framework Affording Mobile-Manipulation and Cross-Embodiment
arXiv preprint, 2024.

[arXiv] [project page] [code coming soon]

Zhengrong Xue*, Han Zhang*, Jingwen Cheng, Zhengmao He, Yuanchen Ju, Changyi Lin, Gu Zhang, Huazhe Xu
ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch
International Conference on Robot Automation (ICRA), 2024.

[arXiv] [project page] [code]

Dehao Wei, Huazhe Xu
A Wearable Robotic Hand for Hand-over-Hand Imitation Learning
International Conference on Robot Automation (ICRA), 2024.

[arXiv] [project page]

Chenchang Li*, Zihao Ai*, Tong Wu, Xiaosa Li, Wenbo Ding+, Huazhe Xu+
DeformNet: Latent Space Modeling and Dynamics Prediction for Deformable Object Manipulation
International Conference on Robot Automation (ICRA), 2024.

[arXiv]

Guowei Xu*, Ruijie Zheng*, Yongyuan Liang*, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé III, Furong Huang, Huazhe Xu
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
International Conference on Learning Representation (ICLR), 2024. (spotlight, top 5%)

[arXiv] [project page] [code]

Lirui Wang, Yiyang Ling*, Zhecheng Yuan*, Mohit Shridhar, Chen Bao, Yuzhe Qin, Bailin Wang, Huazhe Xu, Xiaolong Wang
GenSim: Generating Robotic Simulation Tasks via Large Language Models
International Conference on Learning Representation (ICLR), 2024. (spotlight, top 5%)
Abridged version in LangRob Workshop@CoRL'23 (outstanding paper award).

[arXiv] [project page] [code]

Kun Lei, Zhengmao He*, Chenhao Lu*, Kaizhe Hu, Yang Gao, Huazhe Xu
Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step Policy Optimization
International Conference on Learning Representation (ICLR), 2024.

[arXiv] [project page] [code]

Ruizhe Shi*, Yuyao Liu*, Yanjie Ze, Simon S. Du, Huazhe Xu
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
International Conference on Learning Representation (ICLR), 2024.

[arXiv] [project page] [code]

Xiyao Wang, Ruijie Zheng, Yanchao Sun, Ruonan Jia, Wichayaporn Wongkamjan, Huazhe Xu, Furong Huang
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
International Conference on Learning Representation (ICLR), 2024.

[arXiv] [code coming soon]

Suning Huang, Boyuan Chen, Huazhe Xu, Vincent Sitzmann
Morphological Maze: Control Reconfigurable Soft Robots with Fine-grained Morphology Change
International Conference on Learning Representation (ICLR), 2024.

[paper] [code]

Ziyu Wang*, Yanjie Ze*, Yifei Sun, Zhecheng Yuan, Huazhe Xu
Generalizable Visual Reinforcement Learning with Segment Anything Model
arXiv preprint.

[arXiv] [project page] [code]

Changyi Lin, Han Zhang, Jikai Xu, Lei Wu, Huazhe Xu
9DTact: A Compact Vision-Based Tactile Sensor for Accurate 3D Shape Reconstruction and Generalizable 6D Force Estimation
IEEE Robotics and Automation Letters (RA-L) with a presentation at ICRA'24.

[arXiv] [project page] [hardware & code] [tutorial[CN]] [tutorial[EN]]

Haochen Shi*, Huazhe Xu*, Zhiao Huang, Yunzhu Li, Jiajun Wu.
RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects in 3D with Graph Networks
International Journal of Robotics Research (IJRR).(acceptance rate: 5.3%; IF: 6.887)

[paper]

Zhecheng Yuan*, Sizhe Yang*, Pu Hua, Can Chang, Kaizhe Hu, Huazhe Xu
RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
Conference on Neural Information Processing Systems Datasets & Benchmarks Track (NeurIPS), 2023.

[arXiv] [project page] [code]

Ruijie Zheng, Xiyao Wang, Yanchao Sun, Shuang Ma, Jieyu Zhao, Huazhe Xu+, Hal Daumé III+, Furong Huang+
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Conference on Neural Information Processing Systems (NeurIPS), 2023.

[arXiv] [project page] [code]

Jialu Gao*, Kaizhe Hu*, Guowei Xu, Huazhe Xu
Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?
Conference on Neural Information Processing Systems (NeurIPS), 2023.

[arXiv] [project page] [code coming soon]

Sizhe Yang*, Yanjie Ze*, Huazhe Xu
MoVie: Visual Model-Based Policy Adaptation for View Generalization
Conference on Neural Information Processing Systems (NeurIPS), 2023.

[arXiv] [project page] [code]

Yanjie Ze, Yuyao Liu*, Ruizhe Shi*, Jiaxin Qin, Zhecheng Yuan, Jiashun Wang, Huazhe Xu
H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
Conference on Neural Information Processing Systems (NeurIPS), 2023.

[arXiv] [project page] [code]

Jinxin Liu*, Li He*, Yachen Kang, Zifeng Zhuang, Donglin Wang, Huazhe Xu
CEIL: Generalized Contextual Imitation Learning
Conference on Neural Information Processing Systems (NeurIPS), 2023.

[arXiv] [code]

Haochen Shi*, Huazhe Xu*, Samuel Clarke, Yunzhu Li, Jiajun Wu
RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools
Conference on Robot Learning (CoRL), 2023. (best system paper award, oral)

[arXiv] [project page] [code]

Yuerong Li, Zhengrong Xue, Huazhe Xu
OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024.

[arXiv] [code]

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

[arXiv] [code]

Zhengrong Xue, Zhecheng Yuan, Jiashun Wang, Xueqian Wang, Yang Gao, Huazhe Xu.
USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation
International Conference on Robot Automation (ICRA), 2023.

[arXiv] [project page] [code]

Changyi Lin, Ziqi Lin, Shaoxiong Wang, Huazhe Xu.
DTact: A Vision-Based Tactile Sensor that Measures High-Resolution 3D Geometry Directly from Darkness
International Conference on Robot Automation (ICRA), 2023.

[arXiv] [project page] [media] [code]

Ray Chen Zheng*, Kaizhe Hu*, Zhecheng Yuan, Boyuan Chen, Huazhe Xu.
Extraneousness-Aware Imitation Learning
International Conference on Robot Automation (ICRA), 2023.

[arXiv] [project page] [code coming soon]

Yunfei Li*, Chaoyi Pan*, Huazhe Xu, Xiaolong Wang, Yi Wu.
Efficient Bimanual Handover and Rearrangement via Symmetry-Aware Actor-Critic Learning
International Conference on Robot Automation (ICRA), 2023.

[paper] [project page] [code]

Kaizhe Hu*, Ray Zheng*, Yang Gao, Huazhe Xu.
Decision Transformer under Random Frame Dropping
International Conference on Learning Representation (ICLR), 2023.

[arXiv] [code]

Pu Hua, Yubei Chen+, Huazhe Xu+.
Simple Emergent Action Representations from Multi-Task Policy Training
International Conference on Learning Representation (ICLR), 2023.

[arXiv] [project page] [code]

Linfeng Zhao, Huazhe Xu, Lawson L.S. Wong.
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
International Conference on Learning Representation (ICLR), 2023.

[arXiv] [code]

Ruijie Zheng*, Xiyao Wang*, Huazhe Xu, Furong Huang.
Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function
International Conference on Learning Representation (ICLR), 2023.

Abridged in NeurIPS 2022 DRL workshop (spotlight).

[arXiv] [project page] [code coming soon]

Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu.
Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning
Conference on Neural Information Processing Systems (NeurIPS), 2022. (spotlight)

[arxiv] [project page] [code]

Can Chang, Ni Mu, Jiajun Wu, Ling Pan, Huazhe Xu.
E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance
Conference on Neural Information Processing Systems (NeurIPS), 2022. (spotlight)

[arXiv] [project page] [code]

Haoyu Xiong, Haoyuan Fu, Jieyi Zhang, Chen Bao, Qiang Zhang, Yongxi Huang, Wenqiang Xu, Animesh Garg, Huazhe Xu, Cewu Lu
RoboTube: Learning Household Manipulation from Human Videos with Simulated Twin Environments
RSS Workshop, 2022.

[openreview] [video] [code coming soon]

Hao Li, Yizhi Zhang, Junzhe Zhu, Shaoxiong Wang, Michelle A Lee, Huazhe Xu, Edward Adelson, Li Fei-Fei, Ruohan Gao, Jiajun Wu.
See, Hear, and Feel: Smart Sensory Fusion for Robotic Manipulation
International Conference on Robots Learning (CORL), 2022.

[arXiv] [project page] [code]

Yixing Wang*, Sifan Ye*, Jiaman Li, Dennis Lee, Karen Liu, Huazhe Xu+, Jiajun Wu+.
Scene Synthesis from Human Motion
Siggraph Asia, 2022.

[arXiv] [project page] [code]

Huazhe Xu, Yuping Luo, Shaoxiong Wang, Trevor Darrell, Roberto Calandra.
Towards Learning to Play Piano with Dexterous Hands and Touch
International Conference on Intelligent Robots and Systems (IROS), 2022.

[arXiv] [code coming soon]

Ling Pan, Longbo Huang, Tengyu Ma, Huazhe Xu.
Plan Better amid Conservatism: Offline Multi-agent Reinforcement Learning with Actor Rectification
International Conference on Machine Learning (ICML), 2022.

[arXiv] [project page] [code]

Yunfei Li, Tian Gao, Jiaqi Yang, Huazhe Xu, Yi Wu.
Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning
International Conference on Machine Learning (ICML), 2022.

[arXiv] [project page] [code]

Haochen Shi*, Huazhe Xu*, Zhiao Huang, Yunzhu Li, Jiajun Wu.
RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks
Robotics: Science and Systems (RSS), 2022.

[arXiv] [project page] [code] [media MIT Tech Review] [media HAI]

Zhecheng Yuan, Guozheng Ma, Yao Mu, Bo Xia, Bo Yuan, Xueqian Wang, Ping Luo, Huazhe Xu.
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
International Joint Conference on Artificial Intelligence (IJCAI), 2022.

[arXiv] [project page]

Ruihan Yang*, Minghao Zhang*, Nicklas Hansen, Huazhe Xu, Xiaolong Wang.
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
International Conference on Learning Representation (ICLR), 2022. (spotlight)

[arXiv] [project page] [video] [code]

Jiashun Wang, Huazhe Xu, Medhini Narasimhan, Xiaolong Wang.
Multi-Person 3D Motion Prediction with Multi-Range Transformers.
Conference on Neural Information Processing Systems (NeurIPS), 2021.

[arXiv] [project page] [code]

Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian.
NovelD: A Simple yet Effective Exploration Criterion
Conference on Neural Information Processing Systems (NeurIPS), 2021.

[arXiv] [code] [talk]

Minghao Zhang*, Pingcheng Jian*, Yi Wu, Huazhe Xu, Xiaolong Wang.
Disentangled Attention as Intrinsic Regularization for Bimanual Multi-Object Manipulation
Arxiv Preprints.

[arXiv] [project page] [code coming soon]

Huazhe Xu*, Boyuan Chen*, Yang Gao, Trevor Darrell.
Zero-shot Policy Learning with Spatial Temporal Reward Decomposition on Contingency-aware Observation
International Conference on Robot Automation (ICRA), 2021.

[arXiv] [code] [project page]

Mike Lambeta, Huazhe Xu, Jingwei Xu, Po-Wei Chou, Shaoxiong Wang,Trevor Darrell, and Roberto Calandra
PyTouch: A Machine Learning Library for Touch Processing
International Conference on Robot Automation (ICRA), 2021.

[arXiv] [code]

Jiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu, Xiaolong Wang.
Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes.
Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

[arXiv] [project page] [code]

Yunfei Li, Huazhe Xu, Yilin Wu, Xiaolong Wang, Yi Wu.
Solving Compositional Reinforcement Learning Problems via Task Reduction.
International Conference on Learning Representations (ICLR), 2021.

[openreview] [arxiv] [code] [project page]

Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu.
Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization.
International Conference on Learning Representations (ICLR), 2021.

[openreview] [project page] [code]

Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian.
Multi-Agent Collaboration via Reward Attribution Decomposition
Arxiv preprints, 2020.

[arXiv] [code]

Ruihan Yang, Huazhe Xu, Yi Wu, Xiaolong Wang.
Multi-Task Reinforcement Learning with Soft Modularization.
Conference on Neural Information Processing Systems (NeurIPS), 2020.

[pdf] [code] [project page] [Talk]

Jingwei Xu*, Huazhe Xu*, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, Trevor Darrell.
Hierarchical Style-based Networks for Motion Synthesis.
European Conference on Computer Vision (ECCV), 2020.

[arXiv] [project page] [BibTeX]

Jingwei Xu*, Huazhe Xu*, Bingbing Ni, Xiaokang Yang, Trevor Darrell.
Video Prediction via Demonstration Guidance
International Conference on Machine Learning (ICML), 2020. (oral)

[arXiv] [project page] [code]

Yuping Luo, Huazhe Xu, Tengyu Ma.
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling,
International Conference on Learning Representation (ICLR), 2020.

[arXiv]

Jierui Lin*, Yifei Xing*, Huazhe Xu, Yang Gao.
Learning a Perception-Logic Network for Unsupervised Scene Conditioned Driving Behavior,
Robotics: Science and Systems IDA workshop (RSS workshop), 2020.

[manuscript] [code coming soon] [talk] [demo]

Yuping Luo*, Huazhe Xu*, Yuanzhi Li, Yuandong Tian, Tengyu Ma.
Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees,
International Conference on Learning Representation (ICLR), 2019.

[arXiv] [code]

Hang Gao*, Huazhe Xu*, Qi-zhi Cai, Ruth Wang, Fisher Yu, Trevor Darrell.
Disentangling Propagationand Generation for Video Prediction,
International Conference on Computer Vision (ICCV), 2019.

[arXiv] [code coming soon]

Yang Gao*,Huazhe Xu*, Fisher Yu, Sergey Levine, Trevor Darrell.
Reinforcement Learning from Imperfect Demonstrations,
Neurips 2018 Deep RL Symposium (Neurips Symposium), 2018.

[arXiv]

Haoran Tang*, Dennis Lee*, Jeffrey O Zhang, Huazhe Xu, Trevor Darrell, Pieter Abbeel.
Modular Architecture for StarCraft II with Deep Reinforcement Learning,
he 14th AAAI Conference on Artificial Intelligenceand Interactive Digital Entertainmen (AIIDE), 2018.

[arXiv]

Huazhe Xu*, Yang Gao*, Fisher Yu, Trevor Darrell.
End-to-end Learning of Driving Models from Large-scale Video Datasets,
Conference on Computer Vision and Pattern Recognition (CVPR), 2017. (oral)

[arXiv] [code]

Ronghang Hu, Huazhe Xu, Marcus Rohrbach, Jiashi Feng, Kate Saeko, Trevor Darrell.
atural Language Object Retrieval,
Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (oral)

[arXiv] [code]