Bingliang Zhang

prof_pic.jpg

I am a second-year Ph.D. student at Caltech in the CMS department. I’m excited to be a part of the Computational Camera Lab under the guidance of Katie Bouman, and co-advised by Yisong Yue and Yang Song. My research focuses on controlled generation and solving scientific inverse problems with diffusion models.

I earned my B.S. in Computer Science from the Yao Class at Tsinghua University, where I had the privilege of working with Yi Wu and Yang Gao. During a visit to Carnegie Mellon University, I worked with Jun-Yan Zhu, Eli Shechtman, and Richard Zhang.

news

Jun 10, 2025 Attending CVPR in Nashville.
Apr 01, 2025 Our paper DAPS received an oral presentation at CVPR 2025!

selected publications

  1. CVPR (Oral)
    daps.png
    Improving diffusion inverse problem solving with decoupled noise annealing
    Bingliang ZhangWenda Chu, Julius Berner, Chenlin Meng, Anima Anandkumar, and Yang Song
    In Proceedings of the Computer Vision and Pattern Recognition Conference , 2025
  2. ICLR (Spotlight)
    inv-bench.png
    InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems
    Hongkai ZhengWenda ChuBingliang ZhangZihui Wu, Austin Wang, Berthy Feng, Caifeng Zou, Yu Sun, and 3 more authors
    In The Thirteenth International Conference on Learning Representations , 2025
  3. NeurIPS
    pnpdm.png
    Principled probabilistic imaging using diffusion models as plug-and-play priors
    Zihui Wu, Yu Sun, Yifan Chen , Bingliang ZhangYisong Yue, and Katherine Bouman
    Advances in Neural Information Processing Systems, 2024
  4. CVPR
    custom-diffusion.png
    Multi-concept customization of text-to-image diffusion
    Nupur KumariBingliang ZhangRichard ZhangEli Shechtman, and Jun-Yan Zhu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2023
  5. ICCV
    concept-ablation.png
    Ablating concepts in text-to-image diffusion models
    Nupur KumariBingliang Zhang, Sheng-Yu Wang, Eli ShechtmanRichard Zhang, and Jun-Yan Zhu
    In Proceedings of the IEEE/CVF International Conference on Computer Vision , 2023