Huazhe Xu

papers

1,108

total citations

papers (29)

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

ICLR 2024arXiv

citations

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

ICLR 2025arXiv

citations

DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

ICLR 2025arXiv

citations

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

NEURIPS 2023arXiv

citations

CEIL: Generalized Contextual Imitation Learning

NEURIPS 2023arXiv

citations

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

ICML 2024arXiv

citations

MoVie: Visual Model-Based Policy Adaptation for View Generalization

NEURIPS 2023arXiv

citations

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

ICLR 2024arXiv

citations

Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation

CVPR 2025arXiv

citations

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

ICML 2024arXiv

citations

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

NEURIPS 2022arXiv

citations

Rethinking Transformers in Solving POMDPs

ICML 2024arXiv

citations

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

ICML 2024arXiv

citations

4D Visual Pre-training for Robot Learning

ICCV 2025arXiv

citations

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

ICML 2024arXiv

citations

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

ICML 2025arXiv

citations

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

NEURIPS 2023arXiv

citations

NovelD: A Simple yet Effective Exploration Criterion

NEURIPS 2021

citations

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

ICML 2024

citations

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

NEURIPS 2023

citations

Huazhe Xu

papers (29)

Multi-Task Reinforcement Learning with Soft Modularization

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

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning

Multi-Person 3D Motion Prediction with Multi-Range Transformers

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

Hierarchical Style-based Networks for Motion Synthesis

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

CEIL: Generalized Contextual Imitation Learning

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

MoVie: Visual Model-Based Policy Adaptation for View Generalization

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Rethinking Transformers in Solving POMDPs

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

4D Visual Pre-training for Robot Learning

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

NovelD: A Simple yet Effective Exploration Criterion

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

papers (29)

Multi-Task Reinforcement Learning with Soft Modularization

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

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning

Multi-Person 3D Motion Prediction with Multi-Range Transformers

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

Hierarchical Style-based Networks for Motion Synthesis

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

CEIL: Generalized Contextual Imitation Learning

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

MoVie: Visual Model-Based Policy Adaptation for View Generalization

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Rethinking Transformers in Solving POMDPs

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

4D Visual Pre-training for Robot Learning

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

NovelD: A Simple yet Effective Exploration Criterion

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning