Projects
Publications
2025
-
Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator
Haichao Zhang, Haonan Yu, Le Zhao, Andrew Choi, Qinxun Bai, Yiqing Yang, Wei Xu
IEEE Robotics and Automation Letters (RA-L), 2025
[PDF] [Project Page] -
Generalized Tangent Kernel: A Unified Geometric Foundation for Natural Gradient and Standard Gradient
Qinxun Bai*, Steven Rosenberg*, Wei Xu
Transactions on Machine Learning Research (TMLR), 2025
[PDF] -
Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration
Yan Chen, Qinxun Bai, Yiteng Zhang, Shi Dong, Maria Dimakopoulou, Qi Sun, Zhengyuan Zhou
International Conference on Machine Learning (ICML), 2025
[PDF]
2024
-
VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE
Haonan Yu and Wei Xu
International Conference on Learning Representations (ICLR), 2024
[PDF] [Code] -
FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning
Yuwei Fu, Haichao Zhang, Di Wu, Wei Xu and Benoit Boulet
International Conference on Machine Learning (ICML), 2024
[PDF] [Project Page] [Code] -
Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
David Smerkous, Qinxun Bai, Fuxin Li
Advances in Neural Information Processing Systems (NeurIPS), 2024
[PDF] -
Robot Policy Learning with Temporal Optimal Transport Reward
Yuwei Fu, Haichao Zhang, Di Wu, Wei Xu, Benoit Boulet
Advances in Neural Information Processing Systems (NeurIPS), 2024
[PDF] [Code]
2023
-
Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
Haichao Zhang, Wei Xu and Haonan Yu
International Conference on Learning Representations (ICLR), 2023
[PDF] [Project Page] [Code] -
Efficient Multi-Task and Transfer Reinforcement Learning with Parameter-Compositional Framework
Lingfeng Sun*, Haichao Zhang*, Wei Xu and Masayoshi Tomizuka
IEEE Robotics and Automation Letters (RA-L), 2023
[PDF]
2022
-
Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning
Haichao Zhang, Wei Xu and Haonan Yu
International Conference on Learning Representations (ICLR), 2022 Spotlight
[PDF] [Project Page] [Slides] [Code] -
Distributionally Robust Q-Learning
Zijian Liu, Qinxun Bai, Jose Blanchet, Perry Dong, Wei Xu, Zhengqing Zhou and Zhengyuan Zhou
International Conference on Machine Learning (ICML), 2022
[PDF] [Project Page] [Slides] [Code] -
PaCo: Parameter-Compositional Multi-Task Reinforcement Learning
Lingfeng Sun*, Haichao Zhang*, Wei Xu and Masayoshi Tomizuka
Advances in Neural Information Processing Systems (NeurIPS), 2022
[PDF] [Project Page] [Code] -
Towards Safe Reinforcement Learning with a Safety Editor Policy
Haonan Yu, Wei Xu and Haichao Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2022
[PDF] [Code]
2021
-
Mutual Information State Intrinsic Control
Rui Zhao, Yang Gao, Pieter Abbeel, Volker Tresp and Wei Xu
International Conference on Learning Representations (ICLR), 2021
[PDF] [Code] -
Hierarchical Reinforcement Learning By Discovering Intrinsic Options
Jesse Zhang, Haonan Yu and Wei Xu
International Conference on Learning Representations (ICLR), 2021
[PDF] [Code] -
Generative Particle Variational Inference via Estimation of Functional Gradients
Neale Ratzlaff, Qinxun Bai, Li Fuxin and Wei Xu
International Conference on Machine Learning (ICML), 2021
[PDF] -
An Empowerment-based Solution to Robotic Manipulation Tasks with Sparse Rewards
Siyu Dai, Wei Xu, Andreas Hofmann and Brian Williams
Robotics: Science and Systems (RSS), 2021
[PDF] -
TAAC: Temporally Abstract Actor-Critic for Continuous Control
Haonan Yu, Wei Xu and Haichao Zhang
Advances in Neural Information Processing Systems (NeurIPS), 2021
[PDF] [Code]
Relevant Publications Before 2021 (including prior work)
-
Implicit Generative Modeling for Efficient Exploration
Neale Ratzlaff, Qinxun Bai, Li Fuxin and Wei Xu
International Conference on Machine Learning (ICML), 2020
[PDF] -
Moment Matching for Multi-Source Domain Adaptation
Xingchao Peng, Qinxun Bai, Xide Xia, Zijun Huang, Kate Saenko, Bo Wang
International Conference on Computer Vision (ICCV), 2019
[PDF] -
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
Haichao Zhang and Jianyu Wang
Advances in Neural Information Processing Systems (NeurIPS), 2019
[PDF] -
Interactive Grounded Language Acquisition and Generalization in a 2D World
Haonan Yu, Haichao Zhang and Wei Xu
International Conference on Learning Representations (ICLR), 2018
[PDF] -
Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents
Haonan Yu, Xiaochen Lian, Haichao Zhang and Wei Xu
Annual Conference on Robot Learning (CoRL), 2018
[PDF] -
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
Haichao Zhang, Haonan Yu and Wei Xu
The 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018
[PDF] -
Listen, Interact and Talk: Learning to Speak via Interaction
Haichao Zhang, Haonan Yu and Wei Xu
NIPS Workshop on Visually-Grounded Interaction and Language (NIPS-ViGIL), 2017
[PDF]