Xu, Huazhe
72 publications
ICLRW
2025
DemoGen: Synthetic Demonstration Generation for Data-Efficient Visuomotor Policy Learning
CoRL
2025
DemoSpeedup: Accelerating Visuomotor Policies via Entropy-Guided Demonstration Acceleration
ICLR
2025
DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo
ICML
2025
MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
ICLR
2025
Robots Pre-Train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
CVPR
2025
Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation
ICLR
2024
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
CoRL
2024
Learning to Manipulate Anywhere: A Visual Generalizable Framework for Reinforcement Learning
NeurIPS
2024
Make-an-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
ICML
2024
Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
CoRL
2024
RiEMann: Near Real-Time SE(3)-Equivariant Robot Manipulation Without Point Cloud Segmentation
ICMLW
2024
RoboGolf: Mastering Real-World Minigolf with a Reflective Multi-Modality Vision-Language Model
NeurIPS
2023
$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
NeurIPSW
2023
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
NeurIPS
2023
H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
NeurIPSW
2023
Unleashing the Power of Pre-Trained Language Models for Offline Reinforcement Learning
IJCAI
2022
Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning
NeurIPSW
2022
Is Model Ensemble Necessary? Model-Based RL via a Single Model with Lipschitz Regularized Value Function
ICML
2022
Plan Better amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
NeurIPSW
2021
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
NeurIPSW
2021
Plan Better amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
ICLR
2020
Learning Self-Correctable Policies and Value Functions from Demonstrations with Negative Sampling