Speaker
Prof.
Gert Aarts
(Swansea University)
Description
Diffusion models are currently one of the leading generative AI approaches for image generation used by e.g. DALL-E and Stable Diffusion. A formulation familiar to physicists uses stochastic differential equations. We review this formulation and relate it to stochastic quantisation in quantum field theory. We demonstrate the approach for scalar and abelian gauge fields in two dimensions and end with some speculation on further applications in physics.
Authors
Prof.
Gert Aarts
(Swansea University)
Mr
Diaa Habibi
(Swansea University)
Dr
Lingxiao Wang
(RIKEN)
Prof.
Kai Zhou
(Chinese University of Hong Kong - Shenzhen (CUHK-Shenzhen))
Mr
Qianteng Zhu
(Shanghai Jiao Tong University)
