Guanghan Wang

prof_pic.jpg

I am a first-year Computer Science Ph.D. student at Cornell Tech in NYC, where I am fortunate to work with Prof. Volodymyr Kuleshov. My research interests center around probabilistic generative models and their applications in scientific domains. Lately, I have developed a strong interest in diffusion language models.

Before coming to Cornell, I earned my bachelor’s degree in Computer Science and Technology from Tsinghua University with honor (2020-2024). In 2023, I spent a wonderful summer at CMU collaborating with Prof. Jian Ma.

If you’d like to collaborate or discuss research, feel free to reach out at gw354@cornell.edu!

news

Mar 06, 2025 ReMDM has been accepted to DeLTa Workshop (ICLR 2025).
Jan 22, 2025 Our paper “Simple Guidance Mechanisms for Discrete Diffusion Models” has been accepted to ICLR 2025.
Aug 26, 2024 I have started my Ph.D. journey at Cornell working with Prof. Volodymyr Kuleshov.

selected publications

(* for equal contribution, see full list here)
  1. remdm.gif
    Remasking Discrete-Diffusion Models with Inference-Time Scaling
    Guanghan Wang*, Yair Schiff*, Subham Sekhar Sahoo, and Volodymyr Kuleshov
    arXiv preprint, 2025
    arXiv Blog Code
  2. udlm.gif
    Simple Guidance Mechanisms for Discrete Diffusion Models
    Yair Schiff*, Subham Sekhar Sahoo*, Hao Phung*, Guanghan Wang*, Sam Boshar, Hugo Dalla-torre, Bernardo P Almeida, Alexander Rush, Thomas Pierrot, and Volodymyr Kuleshov
    ICLR, 2025
    arXiv Video Blog Code