Hongkai Zheng

PhD student in Caltech CMS.

hz_pic-s.jpg
hzzheng (at) caltech (dot) edu

Biography: I am currently a PhD candidate at Caltech in Computing + Mathematical Sciences advised by Yisong Yue. Before Caltech, I received my Bachelor’s degree in Computer Science from Shanghai Jiao Tong University in 2020.

My research interests lie in the realm of deep generative modeling and inverse problems. I develop scalable and efficient generative models and design algorithms to solve ill-posed problems in a probabilistic framework.

I am supported by PIMCO Data Science Graduate Fellowship.

I enjoy photography in my spare time. You can find my photography portfolio on this website.

news

May 27, 2025 Starting internship at Adobe.
Oct 22, 2024 Invited talk at SIAM Conference on Mathematics of Data Science (MDS24)

selected publications

  1. InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems
    Hongkai Zheng*Wenda Chu*, Bingliang Zhang*, Zihui Wu*, Austin Wang, Berthy Feng, Caifeng Zou, Yu Sun , Nikola Borislavov Kovachki, Zachary E Ross, Katherine Bouman, and Yisong Yue
    In The Thirteenth International Conference on Learning Representations, Spotlight (top 5.1%) , 2025
  2. Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems
    Hongkai ZhengWenda Chu*, Austin Wang*, Nikola Kovachki, Ricardo Baptista, and Yisong Yue
    2025
  3. Fast Training of Diffusion Models with Masked Transformers
    Hongkai Zheng*Weili Nie*Arash Vahdat, and Anima Anandkumar
    Transactions on Machine Learning Research, 2024
  4. Fast sampling of diffusion models via operator learning
    Hongkai ZhengWeili NieArash Vahdat, Kamyar Azizzadenesheli, and Anima Anandkumar
    In International conference on machine learning, 2023