Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Huazhe Xu

Huazhe Xu

Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

Jul 08, 2021
Ruihan Yang, Minghao Zhang, Nicklas Hansen, Huazhe Xu, Xiaolong Wang

Figure 1 for Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

Figure 2 for Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

Figure 3 for Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

Figure 4 for Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers

* Our project page with videos is at https://RchalYang.github.io/LocoTransformer

Access Paper or Ask Questions

Towards Learning to Play Piano with Dexterous Hands and Touch

Jun 08, 2021
Huazhe Xu, Yuping Luo, Shaoxiong Wang, Trevor Darrell, Roberto Calandra

Figure 1 for Towards Learning to Play Piano with Dexterous Hands and Touch

Figure 2 for Towards Learning to Play Piano with Dexterous Hands and Touch

Figure 3 for Towards Learning to Play Piano with Dexterous Hands and Touch

Figure 4 for Towards Learning to Play Piano with Dexterous Hands and Touch

Access Paper or Ask Questions

PyTouch: A Machine Learning Library for Touch Processing

May 26, 2021
Mike Lambeta, Huazhe Xu, Jingwei Xu, Po-Wei Chou, Shaoxiong Wang, Trevor Darrell, Roberto Calandra

Figure 1 for PyTouch: A Machine Learning Library for Touch Processing

Figure 2 for PyTouch: A Machine Learning Library for Touch Processing

Figure 3 for PyTouch: A Machine Learning Library for Touch Processing

Figure 4 for PyTouch: A Machine Learning Library for Touch Processing

* 7 pages. Accepted at ICRA 2021

Access Paper or Ask Questions

Solving Compositional Reinforcement Learning Problems via Task Reduction

Mar 19, 2021
Yunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang, Yi Wu

Figure 1 for Solving Compositional Reinforcement Learning Problems via Task Reduction

Figure 2 for Solving Compositional Reinforcement Learning Problems via Task Reduction

Figure 3 for Solving Compositional Reinforcement Learning Problems via Task Reduction

Figure 4 for Solving Compositional Reinforcement Learning Problems via Task Reduction

* Project website link updated

Access Paper or Ask Questions

Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

Mar 12, 2021
Zhenggang Tang, Chao Yu, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Du, Yu Wang, Yi Wu

Figure 1 for Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

Figure 2 for Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

Figure 3 for Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

Figure 4 for Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization

* Accepted paper on ICLR 2021. First two authors share equal contribution

Access Paper or Ask Questions

Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Dec 10, 2020
Jiashun Wang, Huazhe Xu, Jingwei Xu, Sifei Liu, Xiaolong Wang

Figure 1 for Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Figure 2 for Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Figure 3 for Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Figure 4 for Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Access Paper or Ask Questions

Hierarchical Style-based Networks for Motion Synthesis

Aug 24, 2020
Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Xiaolong Wang, Trevor Darrell

Figure 1 for Hierarchical Style-based Networks for Motion Synthesis

Figure 2 for Hierarchical Style-based Networks for Motion Synthesis

Figure 3 for Hierarchical Style-based Networks for Motion Synthesis

Figure 4 for Hierarchical Style-based Networks for Motion Synthesis

* ECCV 2020, Project Page:\

Access Paper or Ask Questions

Video Prediction via Example Guidance

Jul 03, 2020
Jingwei Xu, Huazhe Xu, Bingbing Ni, Xiaokang Yang, Trevor Darrell

Figure 1 for Video Prediction via Example Guidance

Figure 2 for Video Prediction via Example Guidance

Figure 3 for Video Prediction via Example Guidance

Figure 4 for Video Prediction via Example Guidance

* ICML 2020
* Project Page: https://sites.google.com/view/vpeg-supp/home

Access Paper or Ask Questions

Multi-Task Reinforcement Learning with Soft Modularization

Mar 30, 2020
Ruihan Yang, Huazhe Xu, Yi Wu, Xiaolong Wang

Figure 1 for Multi-Task Reinforcement Learning with Soft Modularization

Figure 2 for Multi-Task Reinforcement Learning with Soft Modularization

Figure 3 for Multi-Task Reinforcement Learning with Soft Modularization

Figure 4 for Multi-Task Reinforcement Learning with Soft Modularization

* Our project page: https://rchalyang.github.io/SoftModule

Access Paper or Ask Questions

Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

Oct 17, 2019
Huazhe Xu, Boyuan Chen, Yang Gao, Trevor Darrell

Figure 1 for Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

Figure 2 for Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

Figure 3 for Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

Figure 4 for Scoring-Aggregating-Planning: Learning task-agnostic priors from interactions and sparse rewards for zero-shot generalization

Access Paper or Ask Questions

Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

Aug 01, 2019
Yuping Luo, Huazhe Xu, Tengyu Ma

Figure 1 for Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

Figure 2 for Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

Figure 3 for Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling

Access Paper or Ask Questions

Modular Architecture for StarCraft II with Deep Reinforcement Learning

Nov 08, 2018
Dennis Lee, Haoran Tang, Jeffrey O Zhang, Huazhe Xu, Trevor Darrell, Pieter Abbeel

Figure 1 for Modular Architecture for StarCraft II with Deep Reinforcement Learning

Figure 2 for Modular Architecture for StarCraft II with Deep Reinforcement Learning

Figure 3 for Modular Architecture for StarCraft II with Deep Reinforcement Learning

Figure 4 for Modular Architecture for StarCraft II with Deep Reinforcement Learning

* Accepted to The 14th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'18)

Access Paper or Ask Questions

End-to-end Learning of Driving Models from Large-scale Video Datasets

Jul 23, 2017
Huazhe Xu, Yang Gao, Fisher Yu, Trevor Darrell

Figure 1 for End-to-end Learning of Driving Models from Large-scale Video Datasets

Figure 2 for End-to-end Learning of Driving Models from Large-scale Video Datasets

Figure 3 for End-to-end Learning of Driving Models from Large-scale Video Datasets

Figure 4 for End-to-end Learning of Driving Models from Large-scale Video Datasets

* camera ready for CVPR2017

Access Paper or Ask Questions

Natural Language Object Retrieval

Apr 11, 2016
Ronghang Hu, Huazhe Xu, Marcus Rohrbach, Jiashi Feng, Kate Saenko, Trevor Darrell

Figure 1 for Natural Language Object Retrieval

Figure 2 for Natural Language Object Retrieval

Figure 3 for Natural Language Object Retrieval

Figure 4 for Natural Language Object Retrieval

* Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016

Access Paper or Ask Questions