Profiles2020-2025
Tian Xu
Nanjing University
7Papers
0Last author
18Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- Preserving Diversity in Supervised Fine-Tuning of Large Language ModelsAuthor 3 of 7ICLR 2025
- ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language ModelsAuthor 2 of 8ICML 2024 · 165 citations
- Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement LearningAuthor 2 of 4ICLR 2024 · 16 citations
- Provably and Practically Efficient Adversarial Imitation Learning with General Function ApproximationAuthor 1 of 5NeurIPS 2024 · 8 citations
- Policy Rehearsing: Training Generalizable Policies for Reinforcement LearningAuthor 6 of 11ICLR 2024 · 6 citations
- Imitation Learning from Imperfection: Theoretical Justifications and AlgorithmsAuthor 2 of 6NeurIPS 2023 · 26 citations
- Error Bounds of Imitating Policies and EnvironmentsAuthor 1 of 3NeurIPS 2020 · 141 citations
