Jie Liu's Homepage

Hello! I'm currently a first-year Ph.D. student at MMLab, The Chinese University of Hong Kong, supervised by Prof. Wanli Ouyang. Before embarking on my Ph.D. journey, I earned both my Master's degree in Software Engineering in 2023 and my Bachelor's degree in Computer Science and Technology in 2020 from Beihang University. Throughout my academic journey, I've had the privilege of collaborating closely with Prof. Dong Xu and Prof. Yaodong Yang.
I've also interned at SenseTime and Shanghai AI Lab.
My primary research interests are in the fields of Large Language Models and Reinforcement Learning.

News

🥳2023.12:	One Paper on Offline-to-Online RL (SO2) is accepted at AAAI 2024!
2023.10:	We release MODPO, a multi-objective direct preference optimization algorithm for language models!
2023.10:	We release MaskMA, a masked pretraining framework for multi-agent decision-making!
2023.08:	Become a Ph.D. student at MMLab in the Chinese University of Hong Kong.
2023.04:	One Paper on Autonomous Driving (ASAP-RL) is accepted at RSS 2023!
2022.11:	One Paper on Multi-agent RL (ACE) is accepted at AAAI 2023!
2021.03:	Inception Convolution is accepted at CVPR 2021 as an oral paper!

Selected Publications

AAAI

A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning

Yinmin Zhang*, Jie Liu*, Chuming Li* , Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024

PDF
Arxiv

Beyond One-Preference-for-All: Multi-Objective Direct Preference Optimization for Language Models

Zhanhui Zhou*, Jie Liu*, Chao Yang, Jing Shao, Yu Liu, Xiangyu Yue, Wanli Ouyang, Yu Qiao

Arxiv, 2023

PDF CODE
Arxiv

Masked Pretraining for Multi-Agent Decision Making

Jie Liu*, Yinmin Zhang*, Chuming Li, Chao Yang, Yaodong Yang, Yu Liu, Wanli Ouyang

Arxiv, 2023

PDF
RSS

Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors

Letian Wang, Jie Liu, Hao Shao, Wenshuo Wang, Ruobing Chen, Yu Liu, Steven L Waslander

Robotics: Science and Systems (RSS), 2023

PDF Code Video
AAAI

ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

Chuming Li*, Jie Liu*, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023

PDF Code
ECAI

Theoretically Guaranteed Policy Improvement Distilled from Model-Based Planning

Chuming Li, Ruonan Jia, Jie Liu, Yinmin Zhang, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Proceedings of the European Conference on Artificial Intelligence (ECAI), 2023

PDF
CVPR oral

Inception convolution with efficient dilation search

Jie Liu*, Chuming Li*, Feng Liang, Chen Lin, Ming Sun, Junjie Yan, Wanli Ouyang, Dong Xu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

PDF Code
Arxiv

Adaptive Gradient Method with Resilience and Momentum

Jie Liu, Chen Lin, Chuming Li, Lu Sheng, Ming Sun, Junjie Yan, Wanli Ouyang

Arxiv, 2020

PDF