Research

Research statement

My research is driven by the goal of building generative models that can truely understand the physical world. To achieve the goal, I seek statistical machine learning methods to model the underlying data distribution. My experience thus far has focused on deep generative models, such as diffusion models and normalizing flows, in solving inverse problems.

Looking ahead, I am excited to explore cutting-edge developments in generative models such as flow matching, rectified flows, and stochastic interpolants. I am eager to contribute to their theoretical and practical advancements.

List of publications

• (NeurIPS 2024) An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations Weimin Bai, Yifei Wang, Wenzheng Chen and He Sun. paper

• (Arxiv preprint) Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images Yifei Wang, Weimin Bai, Weijian Luo, Wenzheng Chen and He Sun. paper