Tian Xu
 |
Assistant Researcher, Email: xut@lamda.nju.edu.cn |
About me
Welcome to my homepage! Currently, I am an assistant researcher (Yuxiu Young Scholar) in the School of Artificial Intelligence at Nanjing University, and I am also a member of LAMDA Group, LAMDA-RL Group and National Key Laboratory for Novel Software Technology. My research interests lie in the theoretical foundation and algorithmic design in large-scale reinforcement learning. My work has been recognized with Oral Presentation (UAI 2023, ICLR 2024), Spotlight Presentation (NeurIPS 2023, ICLR 2024) and Best Paper Runner-up (NeurIPS 2024 FITML Workshop) distinctions.
Research interests
My research centers on reinforcement learning and imitation learning, with a focus on developing theoretical foundations and efficient algorithms for training large language models.
Education
| 09/2019 – 06/2025 | Ph.D., Nanjing University School of Artificial Intelligence Major: Computer Science Thesis: Adversarial Imitation Learning: Theory and Methods Advisor: Prof. Yang Yu |
| 06/2021 – 09/2021 | Visiting Student, The Chinese University of Hong Kong, Shenzhen Advisor: Prof. Zhi-Quan (Tom) Luo |
| 09/2015 – 06/2019 | B.Sc., Northwestern Polytechnical University School of Mathematics and Statistics Mathematics and Applied Mathematics |
Service
Reviewer
NeurIPS (2022-), ICML (2022-), ICLR (2024-), AISTATS (2024-), UAI (2021-), RLC (2024-), EWRL (2022-).
Award
[2020-10] National Scholarship for Graduates.
[2020-8] Second winner on KDD CUP 2020 Reinforcement Learning Competition Track.
[2016-9, 2017-9] National Scholarship for Undergraduates.