Diffusion Models Live Event

The Annotated Diffusion Model

A Mathematical Introduction to Diffusion Models

arXiv:2607. 01693v1 Announce Type: new Abstract: These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics to modern diffusion samplers, their error analysis, and inference-time control.

Japanese Stable Diffusion

Information Spreading in Diffusion Models from Effective Field Theory

The paper investigates score‑matching diffusion models that use a convolutional architecture, arguing that their locality bias allows effective field theory from physics to describe denoising dynamics. The authors first apply this framework to a toy example with an analytical solution, then to MNIST, demonstrating that in both settings the mutual information between two points increases as predicted by a simple effective field theory of Brownian motion.

VQ-Diffusion

Simplifying, stabilizing, and scaling continuous-time consistency models

We’ve simplified, stabilized, and scaled continuous-time consistency models, achieving comparable sample quality to leading diffusion models, while using only two sampling steps.