Author

Raphaël Urfin

Observed name: Urfin, Raphaël

Institutions: Centre National de la Recherche Scientifique, Université Paris Cité, Université Paris Sciences et Lettres, École Normale Supérieure - PSL, Sorbonne Université, Laboratoire de Physique de l'Ecole Normale Supérieure

Observed institutions: Centre National de la Recherche Scientifique, Université Paris Cité, Université Paris Sciences et Lettres, École Normale Supérieure - PSL, Sorbonne Université, Laboratoire de Physique de l'Ecole Normale Supérieure

OpenAlex ID: A5145235847

Why diffusion models do not memorize: the role of implicit dynamical regularization in training

2026 · Tony Bonnaire, Raphaël Urfin, et al. · Journal of Statistical Mechanics Theory and Experiment · 42

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

2025 · Tony Bonnaire, Raphaël Urfin, et al. · neural information processing systems · 12

Weighting Schedules Govern What and When Score-Based Generative Models Learn from Multimodal Data

2026 · Klinger, Jérémie, Urfin, Raphaël, et al. · arXiv (Cornell University) · 1

First Learn, Then Memorize: The Spectral Bias of Diffusion Models

2026 · Urfin, Raphaël, Bonnaire, Tony, et al. · arXiv (Cornell University) · 1

Double Descent and Malign Overfitting in Diffusion Models

2026 · Urfin, Raphaël, Bonnaire, Tony, et al. · arXiv (Cornell University) · 1

Works count: 5

Citation count: 57

H-index: 2

I10-index: 2