Diffusion models and stochastic quantisation in lattice field theory

Abstract

Diffusion models are currently the leading generative AI approach used for image generation in e.g. DALL-E and Stable Diffusion. In this talk we relate diffusion models to stochastic quantisation in field theory and employ it to generate configurations for scalar fields on a two-dimensional lattice. We end with some speculations on possible applications.

Comments: 7 pages + references. Proceedings of the 41st International Symposium on Lattice Field Theory (Lattice 2024), July 28th - August 3rd, 2024, University of Liverpool, UK