prof_pic.jpg

Aaron Lou

I am a research scientist at OpenAI.

Previously, I was a CS PhD student advised by Stefano Ermon, where I am currently on leave. Before that, I received a B.A. in Math and Computer Science from Cornell University, where I was advised by Chris De Sa.

I develop generative models from first mathematical principles.

news

Jul 23, 2024 Our paper “Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution” won a best paper award at ICML 2024!
Jun 18, 2024 I joined OpenAI as a research scientist!

selected publications

  1. sedd.gif
    Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
    Aaron Lou, Chenlin Meng, and Stefano Ermon
    In International Conference on Machine Learning, 2024
    Best Paper Award
    arXiv Blog Code
  2. refldiff.gif
    Reflected Diffusion Models
    Aaron Lou, and Stefano Ermon
    In International Conference on Machine Learning, 2023
    arXiv Blog Code
  3. nmode.gif
    Neural Manifold Ordinary Differential Equations
    Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, and Christopher De Sa
    In Neural Information Processing Systems, 2020
    arXiv Code
  4. frechet.png
    Differentiating through the Fréchet Mean
    Aaron Lou, Isay Katsman, Qingxuan Jiang, Serge Belongie, Ser-Nam Lim, and Christopher De Sa
    In International Conference on Machine Learning, 2020
    arXiv Code