How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models

ArXi:2603.20092v1 Announce Type: new In this work, we propose a theoretical framework that interprets the generation process in trained diffusion models as an instance of out-of-equilibrium phase transitions. We argue that, rather than evolving smoothly from noise to data, reverse diffusion passes through a critical regime in which small spatial fluctuations are amplified and seed the emergence of large-scale structure.