Shenzhen University School of Mathematical Sciences  

Liyuan Scholars Colloquium Session 178

Title: Causal representation learning and causal generative AI

Speaker: Professor Kun Zhang (Carnegie Mellon University)

Time: 10:30–11:30, July 14, 2026

Location: Room 1, Huixing Building, Yuehai Campus, Shenzhen University

Abstract:  As a core pillar of science and engineering, causality is transforming our approach to modern machine learning and artificial intelligence.  Uncovering the causal process underlying observed data naturally helps answer 'why' and ‘what-if' questions, informs optimal decision-making, and enables adaptive prediction. In many scenarios, observed variables, such as image pixels and questionnaire responses, are often reflections of the underlying hidden causal variables rather than being causal variables themselves. Causal representation learning aims to reveal the underlying hidden causal variables and their relations.  In this talk, we show how the modularity property of causal systems makes it possible to recover the underlying causal representations from observational data with identifiability guarantees. We further demonstrate how identifiable causal representation learning can directly benefit generative AI, using image generation / editing and extrapolative data generation as illustrative examples.

Speaker Profile: Kun Zhang is a professor at Carnegie Mellon University (CMU) and a visiting professor at the Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) in the United Arab Emirates. His primary research interests include causal discovery based on tabular data, causal representation learning from multimodal data such as text, video, and images, and causal methods for emerging machine learning problems. His research is dedicated to addressing long-standing key scientific challenges, including: identifying causal structures in the presence of latent variables; using distribution information to distinguish causal direction; developing reliable nonparametric tests for conditional independence; handling measurement error and missing data; and elucidating how a causal perspective can advance the development of generative artificial intelligence. He has long served as a Senior Area Chair, Area Chair, or Senior Program Committee Member for top conferences in the fields of machine learning and artificial intelligence. He served as one of the General Chairs and Program Chairs for the inaugural Conference on Causal Learning and Reasoning (CLeaR 2022), as Program Chair for the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022) and the IEEE International Conference on Data Mining (IEEE International Conference on Data Mining 2024), and as one of the General Chairs for UAI 2023. He currently serves as an associate editor for journals including JASA, JMLR, IEEE TPAMI, and ACM Computing Surveys.

All faculty and students are welcome!  

School of Mathematical Sciences  

July 6, 2026