News
- New preprint: Kastor, an efficient fine-tuning strategy for generative emulation of PDE simulations, with colleagues at Google DeepMind.
- The DiffusionGemma technical report is out: an open-weight discrete-diffusion language model obtained by fine-tuning Gemma 4.
- Talk at MathSTIC (USPN) on Understanding diffusion models requires rethinking (again) generalization.
- Two new preprints: Understanding diffusion models requires rethinking (again) generalization (with Pierre Marion) and MIND, a sample-efficient alternative to FID.
- Optimal Stopping in Latent Diffusion Models accepted at ICML 2026.
- Poster at Lemanth 2026, EPFL Bernoulli Center, on MIND.
- Talk at the PriGM workshop in Copenhagen on optimal stopping in latent diffusion models.
- New preprint: Optimal Stopping in Latent Diffusion Models.
- Talk at COLT 2025, ENS Lyon, presenting Taking a Big Step.
- Talk at the Journées de Statistique 2025 in Marseille.
- New preprint: Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization, later accepted at COLT 2025.
- Started my PhD at LPSM, Sorbonne University, co-advised with Google DeepMind.
- Implicit regularization of deep residual networks towards neural ODEs accepted at ICLR 2024.