Aaron Lou

I am a third year CS PhD student advised by Stefano Ermon. Previously, I received a B.A. in Math and Computer Science from Cornell University, where I was advised by Chris De Sa. I’m supported by the NSF GRFP.

I develop deep generative models (such as diffusion models) that incorporate geometric inductive biases, with applications in vision, language, and natural science data.


Aug 23, 2021 I started my PhD at Stanford University.
May 28, 2021 I graduated from Cornell University.

selected publications

  1. Preprint
    Discrete Diffusion Language Modeling by Estimating the Ratios of the Data Distribution
    Aaron Lou, Chenlin Meng, and Stefano Ermon
    In Preprint, 2023
  2. refldiff.gif
    Reflected Diffusion Models
    Aaron Lou, and Stefano Ermon
    In International Conference on Machine Learning, 2023
  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
  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