Tian Xu

Joined

May 2021

Names

Tian Xu (Preferred)

Emails

****@lamda.nju.edu.cn (Confirmed)

Personal Links

Career & Education History

PhD student

School of Artificial Intelligence, Nanjing University (nju.edu.cn)

2019 – 2025

Advisors, Relations & Conflicts

Coworker

2024 – Present

Coauthor

2019 – Present

Coauthor

Jing-cheng Pang

2019 – Present

Expertise

Reinforcement Learning

2019 – 2023

Imitation Learning

2019 – 2023

Publications

Provably Efficient Policy-Reward Co-Pretraining for Adversarial Imitation Learning
Tian Xu, Zexuan Chen, Zhilong Zhang, Yi-Chen Li, Yang Yu
- Submitted to ICLR 2026
- Readers: Everyone
Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
Zhilong Zhang, Tian Xu, Xinghao Du, Xingchen Cao, Yihao Sun, Yang Yu
- ICML 2025 poster
- Readers: Everyone
Entropic Distribution Matching for Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity
Ziniu Li, Congliang Chen, Tian Xu, Zeyu Qin, Jiancong Xiao, Ruoyu Sun, Zhi-Quan Luo
- FITML 2024 Oral
- Readers: Everyone
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
Ziniu Li, Congliang Chen, Tian Xu, Zeyu Qin, Jiancong Xiao, Zhi-Quan Luo, Ruoyu Sun
- ICLR 2025 Poster
- Readers: Everyone
Model gradient: unified model and policy learning in model-based reinforcement learning
Chengxing Jia, Fuxiang Zhang, Tian Xu, Jing-Cheng Pang, Zongzhang Zhang, Yang Yu
- Published: 01 Jan 2024, Last Modified: 21 Feb 2024
- Frontiers Comput. Sci. 2024
- Readers: Everyone
Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
Tian Xu, Zhilong Zhang, Ruishuo Chen, Yihao Sun, Yang Yu
- NeurIPS 2024 poster
- Readers: Everyone
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo
- ICML 2024 Poster
- Readers: Everyone
Limited Preference Aided Imitation Learning from Imperfect Demonstrations
Xingchen Cao, Fan-Ming Luo, Junyin Ye, Tian Xu, Zhilong Zhang, Yang Yu
- ICML 2024 Poster
- Readers: Everyone
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo
- ICML 2024
- Readers: Everyone
Limited Preference Aided Imitation Learning from Imperfect Demonstrations
Xingchen Cao, Fan-Ming Luo, Junyin Ye, Tian Xu, Zhilong Zhang, Yang Yu
- ICML 2024
- Readers: Everyone

View all 38 publications

Co-Authors

View all 35 co-authors