Published 'InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems' accepted to ICLR 2025 with Spotlight (top 5.1%) recognition, which explores the application of plug-and-play diffusion prior methods in scientific inverse problems and introduces a unified evaluation framework; another paper 'Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems' has been submitted to TMLR.
Research Experience
Starting internship at Adobe (May 27, 2025); Invited talk at SIAM Conference on Mathematics of Data Science (MDS24) (Oct 22, 2024).
Education
Received his Bachelor’s degree in Computer Science from Shanghai Jiao Tong University in 2020; now a PhD student in Computing + Mathematical Sciences at Caltech, advised by Yisong Yue.
Background
Currently a PhD candidate at Caltech in Computing + Mathematical Sciences, advised by Yisong Yue. His research interests lie in the realm of deep generative modeling and inverse problems, developing scalable and efficient generative models and designing algorithms to solve ill-posed problems in a probabilistic framework.
Miscellany
Enjoys photography in spare time, with a portfolio available on his personal website.