I am an assistant professor in the School of Computing and Data Science at The University of Hong Kong and The HKU Musketeers Foundation Institute of Data Science. I am generally interested in machine learning, stochastic optimization, and graph learning, with a special focus on the theoretical and empirical understanding of deep learning, especially foundation models. I am also interested in developing AI/ML methods for practical problems in areas such as signal processing, intelligent transportation, and mathematics.
Previously, I obtained my Ph.D. in the Computer Science department at the University of California, Los Angeles (UCLA), supervised by Prof. Quanquan Gu. I obtained my master’s degree in electrical engineering and bachelor’s degree in applied physics, both from the University of Science and Technology of China (USTC).
Open positions. I welcome enquiries from prospective PhD students, postdoctoral researchers, and research assistants. Please email a CV and a brief description of your research interests.
News
One paper is accepted to ACL 2026.
Five papers are accepted to ICML 2026.
One paper is accepted to ACL 2026.
Seven papers are accepted to ICLR 2026.
Our paper on Interpretability vs. Utility for SAEs in LLMs was accepted to the NeurIPS 2025 ResponsibleFM Workshop as an oral presentation and received an Outstanding Paper Award.
Two papers are accepted to AAAI 2026.
Seven papers are accepted to NeurIPS 2025.
Welcoming new PhD students Yufei Zhao, Xuan Tang, Bingqing Jiang, Dechen Zhang, and Xu Wang.
One paper is accepted to EMNLP 2025.
One paper is accepted to ACL 2025.