Evann Courdier

@noorchauhn @francoisfleuret We are working on an arXiv version of this thread. The full codebase for the discrete diffusion process will be released at the same time. The Unet model we used is the one linked from lucidrains. The maze generation is done with: fleuret.org/git/picoclvr

@francoisfleuret Do we have some code to reproduce these professor?

We train a discrete diffusion denoising model to find paths in a maze. The visualization of the evolution of x_0|x_t (last message in the thread) is very cool IMO.

Diffusion models are surprisingly good at solving algorithmic tasks. With @francoisfleuret and @evanncourdier, we use discrete diffusion to find shortest paths in mazes represented as images. 1/5