I am now a Tenure-track Assistant Professor (Ph.D. Advisor) at Peking University. I am also a faculty member of ZERO Lab led by Prof. Zhouchen Lin. I got my Ph.D. degree from Department of Computer Science and Technology, Tsinghua University. I have visited Georgia Tech, USA, hosted by Prof. Le Song and Prof. Hongyuan Zha, and The University of Melbourne, Australia, hosted by Prof. James Bailey.
My research centers on Representation Learning, with a focus on deriving meaningful and robust representations from diverse data types--including unlabeled, noisy, and adversarial data--grounded in principled and theoretically driven methodologies. Specifically, we recently focus on Theoretical and Algorithmic Foundations of LLMs (e.g., Self-Supervised/Weakly-Supervised Learning, In-context Learning, Length Generalization, and Reasoning) and AI Safety (ensuring Trustworthy and Reliable AI Systems).
We have received the Best Paper Award of ECML-PKDD 2021, Best Paper Award of ICML 2024 Workshop, Silver Best Paper Award of ICML 2021 Workshop, 1st Place in the CVPR 2021 Adversarial Competitions, and Champion in the 2020 GeekPwn CAAD Competitions. We are also lucky to win the First Prize in the 22nd Teaching Competition of Peking University, Beijing Nova Talent Program, ACM Beijing Rising Star Award, Notable Area Chair at NeurIPS, and World's Top 2% Scientists.