News
2026
-
Our paper Weighting Schedules Govern What and When Score-Based Generative Models Learn from Multimodal Data,
with Jérémie Klinger, Giulio Biroli and Marylou Gabrié, was accepted as a poster at the NeurIPS 2026 workshop
Geometric Distributional Deep Learning.
Come see our poster in Paris!
-
Looking forward to presenting Double Descent and Malign Overfitting in Diffusion Models at the
GdR IASIS day on generative models at ENS Lyon.
-
Two new preprints out:
First Learn, Then Memorize: The Spectral Bias of Diffusion Models,
with Tony Bonnaire, Giulio Biroli and Marc Mézard; and
Weighting Schedules Govern What and When Score-Based Generative Models Learn from Multimodal Data,
with Jérémie Klinger, Giulio Biroli and Marylou Gabrié.
-
New preprint: Double Descent and Malign Overfitting in Diffusion Models, with Tony Bonnaire,
Giulio Biroli and Marc Mézard. Available on
arXiv.
-
Our paper was selected for the JSTAT special issue
Machine Learning 2026.
2025
-
Our paper Why Diffusion Models Don’t Memorize was featured by
LPENS,
CNRS INSU, and
IAS Paris-Saclay.
-
Our paper Why Diffusion Models Don’t Memorize received an Oral and a Best Paper Award at NeurIPS 2025.
-
Started my PhD at ENS–PSL with Giulio Biroli and Marc Mézard.
