Information Spreading in Diffusion Models from Effective Field Theory
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
We study score-matching diffusion models with a convolutional architecture. We argue that the inductive bias of locality means that the machinery of effective field theory from physics can be usefully applied to describe the denoising dynamics. We apply this formalism first to a simple toy example which permits an analytical description, and thereafter to MNIST, and show that in both cases, the mutual information between two points grows in a manner predicted by a simple effective field theory of Brownian motion.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 16 of its 24 references that are in the map. First posted on arXiv 14 Aug 2026.
Builds on
16 of 24 references.
Closest ancestors · 10
Same direction, newest first
- 2026How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models20 Mar
- 2025Locality in Image Diffusion Models Emerges from Data Statistics11 Sep
- 2024Dynamical Regimes of Diffusion Models28 Feb
- 2023Spontaneous Symmetry Breaking in Generative Diffusion Models31 May
- 2023Information-Theoretic Diffusion7 Feb
- 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
- 2021Diffusion Models Beat GANs on Image Synthesis11 May
- 2021Improved Denoising Diffusion Probabilistic Models18 Feb
- 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
- 2020Denoising Diffusion Probabilistic Models19 Jun
Other references · 6
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2016Group Equivariant Convolutional Networkscited by 1,165
- 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 677
- 2024An analytic theory of creativity in convolutional diffusion modelscited by 104
- 2023Diffusion Models for Non-autoregressive Text Generation: A Surveycited by 44
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Local Diffusion Models and Phases of Data Distributions
- 2026A theory of learning data statistics in diffusion models, from easy to hard
- 2026Feature Information Dynamics in Diffusion
- 2026Rethinking the Diffusion Model from a Langevin Perspective
- 2025Diffusion Models: A Mathematical Introduction
- 2025Generalization through variance: how noise shapes inductive biases in diffusion models
- 2025Information-Theoretic Proofs for Diffusion Sampling
- 2026An exact information theory of generalization phase transitions in Bayesian diffusion models