About

I am a Lecturer at Artificial Intelligence and its Applications Institute, School of Informatics, University of Edinburgh, leading the Edinburgh Ventures for Intelligence and Economics. Within Edinburgh, I am also a Fellow of Generative AI Laboratory, and an Affiliate of the Institute for Adaptive and Neural Computation, Edinburgh Future Institute, and the Edinburgh Centre for Financial Innovations. I was the founding lead of the Trustworthy AI project at JD.com, Inc., a leading e-commerce and logistics firm in China. I received my BSc in statistics from the University of Science and Technology of China, MPhil and PhD in computer science from the University of Sydney. I am an Area Chair of leading conferences, ICML, NeurIPS, ICLR, UAI, and AISTATS, and on the Editorial Boards of journals Machine Learning and Pattern Recognition. My research is in (1) understanding AI behaviour, from both learning-theoretical and game-theoretical views, interpreting its generalisability, rationality, morality, privacy, fairness, etc. The scope includes both generic models and frontier GenAI, such as LLMs and diffusion models; (2) developing models and algorithms that leverage the intrinsic symmetries in data, task, environment, amongst others, aiming at more efficient and significant scalability beyond simply scaling the size of model, data, and compute; (3) collaboration and interactions between AI agents in decentralised and multi-agent settings; and (4) employing AI to solve game-theoretical, economic, and financial problems.

Research Performance Summary

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

Publication Venues and Collaboration

Research Impact by Period

Contact and Professional Links

Detected Research Keywords