Yang Li
Welcome to my homepage! I'm an associate professor at the School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen).
My research focuses on developing trustworthy machine learning systems for uncertain, heterogeneous and dynamic data from the real world. Specically, my research interests include:
Transferability estimation in transfer learning, efficient domain and model adaptation, continual learning
Interpretable representation learning, compositional learning, topological data analysis
Trustworthy methods for medical image understanding and clinical AI
See the Research page for highlights about my past and current projects.
I obtained my PhD. degree in Computer Science from Stanford University in 2017, advised by Leonidas Guibas. My dissertation explores how to find shared structures in large GPS trajectories under uncertainty, and how the shared structures can be used to solve challenging problems. I obtained my undergradudate degree in Computer Science and Mathematics from Smith College in 2011, advised by Ileana Streinu. I was also a contributor to the KINARI project. Previously, I have worked at Tsinghua Berkeley Shenzhen Institute (TBSI) and Tsinghua Shenzhen International Graduate School.
News
(2026/3) I joined the School of AI at The Chinese University of Hong Kong, Shenzhen as an Associate Professor. My group is now based at CUHK-Shenzhen. I am recruiting Fall 2026 and Fall 2027 PhD and MPhil students (see the Research Group page for details).
(2026/1/18) Two papers accepted to ICASSP 2026. Congratulations to Zixi Zhao and Enming Zhang!
(2026/1) I will attend AAAI 2026 this month and present our paper on optimal visual prompt ensemble learning. See you in Singapore!
(2025/9/27) Two conference and two workshop papers presented at MICCAI’25. Congratulations to Jingyun Yang for receiving the Best Presentation Award at MICCAI’25 HAIC Workshop.
(2025/9/20) Two papers (preprint: [1] [2]) accepted at NeurIPS 2025 on optimizing learning strategy in continual learning and multi-source transfer learning. Congrats to Yanru Wu and Qingyue Zhang!
(2025/5/25) I will be presenting a tutorial entitled “Information-Theoretic Measures for Multi-Expert Foundation Model Adaptation” with my colleague Shao-Lun Huang at Conference on Lifelong Agents (CoLLAs) 2025, which will be held at UPenn in Augst 11-14, 2025.
(2025/4/18) I gave a guest talk on trustworthy transfer learning at the computer science departement of University of Texas, Austin
(2025/4/6-17) I persented our papers at ICASSP 2025 (1,2) and ISBI 2025 (3,4)
(2025/4/3) I gave a computer science colloquium seminar entitled “Trustworthy Multi-Expert Transfer through Transferability Estimation” at City University of Hong Kong
(2024/10) I started a Wechat channel for my research group. Subscribe to us on WeChat @TsinghuaSIGS李阳课题组 for the latest updates!
(2024/7) We are organizing the 2024 Workshop on Learning & Information Theory in Shenzhen, China on August 19-20. Check out the website for more information!
(2024/2) I gave an AI seminar lecture on Transferability Guided Transfer Learning at The Hong Kong University of Science and Technology (Guangzhou)
Contact
Email:
Address:
School of Artificial Intelligence, Office TX-B117
The Chinese University of Hong Kong, Shenzhen
Longxiang Avenue 2001, Longgang District
Shenzhen, Guangdong, China