Long-Fei Li @ LAMDA, NJU-AI
Biography
I obtained my Ph.D. degree from the School of Artificial
Intelligence at Nanjing University in 2025,
where I was very fortunate to be advised by Prof. Zhi-Hua
Zhou. Before that, I received my B.Sc.
degree in Computer Science and Technology in June
2020 from Shanghai Jiao Tong University, where I was
also selected for the ZhiYuan Honors
Program. Additionally, I visited the National
University of Singapore from July to December 2019.
Research Interests
My research interests include Machine Learning and Sequential Decision Making. Most recently, I
am interested in
- Online Learning, Bandits, MDPs, Reinforcement Learning
- LLM alignment, Reinforcement Learning from Human Feedback (RLHF)
Preprints
- Provably Efficient RLHF Pipeline: A Unified View from Contextual Bandits. [PDF, arXiv]
Long-Fei Li*, Yu-Yang Qian*, Peng Zhao, and Zhi-Hua Zhou. (* Equal contribution)
Publications
- Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation. [PDF, arXiv]
Long-Fei Li, Yu-Jie Zhang, Peng Zhao, and Zhi-Hua Zhou.
In: Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, Canada, 2024.
Page: 58539--58573.
- Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs. [PDF, arXiv]
Long-Fei Li, Peng Zhao, and Zhi-Hua Zhou.
In: Advances in Neural Information Processing Systems 37 (NeurIPS 2024), Vancouver, Canada, 2024.
Page: 55858--55883.
-
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition. [PDF, arXiv]
Long-Fei Li, Peng Zhao, and Zhi-Hua Zhou.
In: Proceedings of the 27th International Conference on Artificial Intelligence and Statistics
(AISTATS 2024), Valencia, Spain, 2024. Page: 3061--3069.
-
Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation. [PDF]
Long-Fei Li, Peng Zhao, and Zhi-Hua Zhou.
In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI 2024), Vancouver,
Canada, 2024. Page: 13572-13580.
-
Dynamic Regret of Adversarial Linear Mixture MDPs. [PDF]
Long-Fei Li, Peng Zhao, and Zhi-Hua Zhou.
In: Advances in Neural Information Processing Systems 36 (NeurIPS 2023), New Orleans, Louisiana,
2023. Page: 60685-60711.
-
Tracking Treatment Effect Heterogeneity in Evolving Environments. [PDF]
Tian Qin, Long-Fei Li, Tian-Zuo Wang, and Zhi-Hua Zhou.
In: Machine Learning, 2023. Page: 1-21.
-
Dynamic Regret of Online Markov Decision Processes. [PDF, arXiv, full version]
Peng Zhao, Long-Fei Li, and Zhi-Hua Zhou.
In: Proceedings of the 39th International Conference on Machine Learning (ICML 2022), Baltimore,
Maryland, 2022. Page: 26865-26894.
-
Knowledge Consistency between Neural Networks and Beyond. [PDF, arXiv, Code]
Ruofan Liang, Tianlin Li, Long-Fei Li, Jing Wang and Quanshi Zhang.
In: Proceedings of the 8th International Conference on Learning Representations (ICLR 2020),
Online, 2020.
Awards & Honors
-
Outstanding Graduates of Nanjing University, 2025.
-
Outstanding Doctoral Dissertation Award of the School of Artificial Intelligence, 2025.
-
AISTATS Best Reviewer Award, 2025.
-
NeurIPS Scholar Award, 2024.
-
Excellent Graduate Student of Nanjing University, 2023.
-
LAMDA Excellent Student Award, 2023.
-
First Prize, DIGIX Global Campus AI Algorithm Competition, 2021.
-
Xu Xin International Student Exchange Scholarship, 2020.
-
President's Special Scholarship for Doctoral Students, 2020.
-
Outstanding Graduate of Shanghai Jiaotong University, 2020.
Academic Service
- Reviewer for ICML(2022, 2023, 2024), NeurIPS(2023, 2024), ICLR(2024), AAAI(2024), AISTATS(2023, 2024,
2025), UAI(2023, 2024).
Correspondence
Email:
lilf@lamda.nju.edu.cn
Office:
Room 912, Computer Science Building, Xianlin Campus of Nanjing University
Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus
Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China
(In Chinese: 南京市栖霞区仙林大道163号, 南京大学仙林校区603信箱, 软件新技术国家重点实验室, 210023)