Information Spreading in Diffusion Models from Effective Field Theory

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions

arXiv:2409. 18804v3 Announce Type: replace-cross Abstract: Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more applications in science and beyond.

Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data

arXiv:2603. 22962v3 Announce Type: replace Abstract: We study the theoretical behavior of denoising score matching--the learning task associated to diffusion models--when the data distribution is supported on a low-dimensional manifold and the score is parameterized using a random feature neural network.

Diffusion Models Live Event

The Annotated Diffusion Model

Wasserstein Convergence of ODE-Based Samplers in Decentralized Diffusion Model via Velocity Field Decomposition

arXiv:2606. 15835v1 Announce Type: cross Abstract: Diffusion models have achieved impressive empirical success in generative tasks, and their convergence theory is now relatively well understood.

Accelerating Stable Diffusion Inference on Intel CPUs

Score Approximation for Diffusion Models on Arbitrary Low-Dimensional Structures

arXiv:2606. 19894v1 Announce Type: new Abstract: The remarkable success of score-based diffusion models has spurred significant efforts to establish their theoretical foundations.

Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation

arXiv:2605. 22950v2 Announce Type: replace-cross Abstract: Score matching is an alternative to maximum likelihood estimation when the normalizing constant is unknown or too costly to evaluate.

On the Separability of Information in Diffusion Models

arXiv:2509. 23937v5 Announce Type: replace-cross Abstract: Diffusion models transform noise into data by injecting information that was captured in their neural network during the training phase.

Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors

arXiv:2606. 06179v1 Announce Type: cross Abstract: Score-based diffusion models are typically trained by minimizing the $L^2$ score matching error, and standard theoretical analyses rely on this quantity to bound the sampling discrepancy between the learned and target distributions.

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.

Understanding Latent Diffusability via Fisher Geometry

arXiv:2604. 02751v2 Announce Type: replace Abstract: Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood.