arXiv Machine Learning June 10, 2026 By Zahra Kadkhodaie, Aram-Alexandre Pooladian, Sinho Chewi, Eero Simoncelli

Blind denoising diffusion models and the blessings of dimensionality

Read the original on arXiv Machine Learning →

arXiv:2602. 09639v2 Announce Type: replace Abstract: Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline remain poorly understood.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 10

The Emergence of Reproducibility and Generalizability in Diffusion Models

arXiv:2310. 05264v5 Announce Type: replace Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs.

By Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu

diffusion fine-tuning safety

arXiv Machine Learning

Aug 10

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.

By Iskander Azangulov, George Deligiannidis, Judith Rousseau

diffusion benchmarks

arXiv Machine Learning

Jul 14

Low-dimensional adaptation of diffusion models: Convergence in total variation

arXiv:2501. 12982v3 Announce Type: replace-cross Abstract: This paper investigates how diffusion generative models leverage (unknown) low-dimensional structure to accelerate sampling.

By Jiadong Liang, Zhihan Huang, Yuxin Chen

diffusion benchmarks

arXiv Machine Learning

Jul 14

Conservation Laws for Diffusion Models

arXiv:2607. 10067v1 Announce Type: new Abstract: While autoregressive models optimize the exact data likelihood via the chain rule, diffusion models are typically trained with denoising objectives.

By Ziv Aharoni, Henry D. Pfister

diffusion benchmarks

arXiv Machine Learning

Jun 2

Diffusion Models, Denoiser Architecture and Creativity

arXiv:2605. 16415v3 Announce Type: replace-cross Abstract: The creativity of diffusion models refers to their ability to generate highly realistic images that are different from their training data.

By Itamar Levine, Yair Weiss

diffusion safety

arXiv AI

Jul 7

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

arXiv:2602. 02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed.

By Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan

diffusion

Related stories

The Emergence of Reproducibility and Generalizability in Diffusion Models

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

Low-dimensional adaptation of diffusion models: Convergence in total variation

Conservation Laws for Diffusion Models

Diffusion Models, Denoiser Architecture and Creativity

A Random Matrix Theory Perspective on the Consistency of Diffusion Models