activity
20242026
most citedDynamical Regimes of Diffusion Models

48 citations · 56 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Double Descent and Malign Overfitting in Diffusion Models

Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1

Conventional wisdom in deep learning holds that overparameterization---having more parameters than training samples ---is benign: larger models generalize better and, even w…

cs.LG2026

Theory of Speciation Transitions in Diffusion Models with General Class Structure

Beatrice Achilli, Marco Benedetti, Giulio Biroli +1

Diffusion Models generate data by reversing a stochastic diffusion process, progressively transforming noise into structured samples drawn from a target distribution. Recent theore…

cs.LG2025★ 2 cited

Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training

Tony Bonnaire, Raphaël Urfin, Giulio Biroli +1

Diffusion models have achieved remarkable success across a wide range of generative tasks. A key challenge is understanding the mechanisms that prevent their memorization of traini…

cs.LG2025

Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms

Krunoslav Lehman Pavasovic, Jakob Verbeek, Giulio Biroli +1

Classifier-Free Guidance (CFG) is a widely adopted technique in diffusion and flow-based generative models, enabling high-quality conditional generation. A key theoretical challeng…

cs.LG2025

Optimizing Noise Schedules of Generative Models in High Dimensionss

Santiago Aranguri, Giulio Biroli, Marc Mezard +1

Recent works have shown that diffusion models can undergo phase transitions, the resolution of which is needed for accurately generating samples. This has motivated the use of diff…

cs.LG2024★ 2 cited

Kernel Density Estimators in Large Dimensions

Giulio Biroli, Marc Mézard

This paper studies Kernel Density Estimation for a high-dimensional distribution . Traditional approaches have focused on the limit of large number of data points and fix…