arXiv Machine Learning June 2, 2026 By Hamza Cherkaoui, H\'el\`ene Halconruy, Antonio Ocello

Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training

Read the original on arXiv Machine Learning →

arXiv:2605. 13175v2 Announce Type: replace Abstract: Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity.

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

diffusion

arXiv Machine Learning

Jun 2

Self-Regulating Annealing in Heavy-Tailed Diffusion Models

arXiv:2606. 01645v1 Announce Type: cross Abstract: Diffusion models have emerged as a leading framework for deep generative modeling.

By Keito Wakatsuki, Hideaki Shimazaki

diffusion

arXiv AI

Jun 24

Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate

arXiv:2606. 23920v1 Announce Type: cross Abstract: The task of compositional generation involves using a conditional generative model, trained only on a subset of the possible conditions, to produce samples from compositionally-defined target distributions such as a geometric combination of the source distributions.

By Duncan Soiffer, Chandler Squires, Yuan Guan, Jason Hartford, Pradeep Ravikumar

diffusion

arXiv Machine Learning

Jul 22

ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.

By Chirag Vashist, Ke Li

llms diffusion safety

arXiv AI

Jul 14

Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models

arXiv:2607. 10810v1 Announce Type: cross Abstract: Deep generative models are increasingly used as simulators for downstream decision-making under data scarcity, but in risk-sensitive applications their usefulness depends on rare adverse scenarios rather than typical samples.

By Shuning Zhao, Patrick Wong, Leran Zhang, Xiaolin Hu

diffusion benchmarks safety

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 AI

Jun 2

Efficient Weighted Sampling via Score-based Generative Models

arXiv:2502. 04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more.

By Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

diffusion benchmarks

Related stories

Self-Regulating Annealing in Heavy-Tailed Diffusion Models

Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate

ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling

Diachronic Sample Integration: Robust Tail-Risk Estimation with Generative Models

The Emergence of Reproducibility and Generalizability in Diffusion Models

Efficient Weighted Sampling via Score-based Generative Models