Grayson Lee

prof_pic.jpg

I am a Msc student in Computing Science at University of Alberta, under the supervision of Xiaoqi Tan. I completed my Bachelor’s degree in Computing Science from Simon Fraser University.

My research interests span generative modeling, reinforcement learning, and control theory. I focus on combining these areas to develop principled approaches for sequential decision-making. In particular, I’m interested in how generative models can be integrated with control-theoretic tools to build robust and efficient methods.

During my undergrad I had the privilege of conducting research with Martin Ester, where I worked on Generative Flow Networks (GFlowNets) for structure-based drug discovery. I later worked with Ke Li and Mo Chen on applying generative models to model predictive control, and on multi-agent collision avoidance with Hamilton-Jacobi reachabilty.

Reach out at: graysonl [at] sfu.ca

news

Jan 31, 2026 One paper is accepted to ICRA.
Sep 03, 2024 One paper is accepted to TMLR.
May 28, 2024 One paper is accepted (spotlight) to MoML 2024.

selected publications

  1. Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control
    Grayson Lee, Minh Bui, Shuzi Zhou, and 3 more authors
    IEEE International Conference on Robotics and Automation (ICRA), 2026
  2. TacoGFN: Target-conditioned GFlowNet for Structure-based Drug Design
    Tony Shen, Seonghwan Seo, Grayson Lee, and 5 more authors
    Transactions on Machine Learning Research (TMLR), 2024