Published several academic papers, including 'UltraTWD: Optimizing Ultrametric Trees for Tree-Wasserstein Distance', 'A Theory-Driven Approach to Inner Product Matrix Estimation for Incomplete Data: An Eigenvalue Perspective', and more. The paper 'Learning Sparse Binary Code for Maximum Inner Product Search' was a Best Short Paper Finalist.
Research Experience
Published research on efficient similarity and distance learning in conferences such as NeurIPS, WWW, and UAI; currently working on physical reasoning for (Multimodal) Large Language Models.
Education
Bachelor's degree in Physics from the University of Chinese Academy of Sciences (UCAS) in 2020; Ph.D. candidate at The Chinese University of Hong Kong, Shenzhen from September 2020 to October 2025, supervised by Prof. Jianfeng Mao and Prof. Wenye Li.
Background
Ph.D. candidate in Computer and Information Engineering at The Chinese University of Hong Kong, Shenzhen (CUHK-SZ), with research interests in AI for Science, (Multimodal) Large Language Models, and Statistics for AI.
Miscellany
CV available on his homepage in both Chinese and English.