
Before UCSD, I completed my M.S. in Machine Learning at MBZUAI under Kun Zhang. During that time, I was also a visiting student at CMU, working with Peter Spirtes. I worked on causal learning and identification problems, with using them to improve downstream generative models and scientific discovery. My master’s thesis can be found here.
Prior to MBZUAI, I obtained my Bachelor from UESTC, advised by Jie Shao, and also interned in the NLP group at Shanghai AI Lab, led by Lingpeng Kong.
My research centers on inverting observation-generation to unveil the hidden world. I explore: (1) how to identify a hidden world based on the assumed generative mechanism, and (2) how such a hidden world instructs the observed world evolving in response to the environment?
Oct 2025. Will present our work on The 5th Measurement Errors and Latent Variables Workshop at Economics Department, Johns Hopkins University. Thanks to Dean. Hu for invitation!
Sep 2025. Two papers on Identifiability of Hierarchical Model and Online Representation Learning were accepted to NeurIPS 2025.




Conference: CVPR 2026; ICLR 2026; NeurIPS 2025; BMVC 2023.
Journal: IEEE Transactions on Image Processing (TIP) 2024