CV

Education

Ph.D in Applied Mathematics and Machine Learning, Sorbonne University, 2027 (expected)
Diploma of ENS in Applied Mathematics, Ecole Normale Supérieure, 2024
M.S. in Statistics and Machine Learning, University Paris-Saclay, 2023
B.S. in Applied Mathematics, University Paris-Cité, 2021
Classe préparatoire, Lycée Louis-Le-Grand, 2020

Publications

Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulation

Guillaume Couairon, Alexis Jacq, Yu-Han Wu, Renu Singh, Yana Hasson, Quentin Berthet and Romuald Elie (2026) Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations. arXiv:2608.06107.

DiffusionGemma

Taïga, DiffusionGemma Team Adrien Ali et al. “DiffusionGemma Technical Report.” (2026).

Understanding diffusion models requires rethinking (again) generalization

Pierre Marion and Yu-Han Wu (2026) Understanding diffusion models requires rethinking (again) generalization. arXiv:2605.06077.

MIND: Monge Inception Distance for Generative Models Evaluation

Quentin Berther, Yu-Han Wu, Clément Crepy, Romuald Elie, Klaus Greff & Michael Eli Sander (2026). MIND: Monge Inception Distance for Generative Models Evaluation. arXiv:2605.06797.

Optimal Stopping in Latent Diffusion Model

Yu-Han Wu, Quentin Berthet, Gérard Biau, Claire Boyer, Romuald Elie & Pierre Marion (2025). Optimal Stopping in Latent Diffusion Model. arXiv preprint arXiv:2510.08409.

Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization

Wu, Y. H., Marion, P., Biau, G., & Boyer, C. (2025). Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization. Proceedings of Thirty Eighth Conference on Learning Theory, PMLR 291:5718-5756

Implicit regularization of deep residual networks towards neural ODEs

Pierre Marion, Yu-Han Wu, Michael Eli Sander, & Gerard Biau (2024). Implicit regularization of deep residual networks towards neural ODEs. In The Twelfth International Conference on Learning Representations.

More on lines in Euclidean Ramsey theory

Conlon, D., & Wu, Y. H. (2023). More on lines in Euclidean Ramsey theory. Comptes Rendus. Mathématique, 361(G5), 897-901.

Work experience

Winter 2023: Research Intern
- Owkin
- Research topic: Federated Learning (FL) and Invariant Risk Minimization (IRM)
- Supervisor: Ulysse Marteau-Ferey
Summer 2023: Research Intern
- Sorbonne University
- Research topic: Implicit regularization of residual network
- Supervisor: Gérard Biau, Pierre Marion
Summer 2022: Research Intern
- California Institute of Technology
- Research topic: Extremal Combinatorics and Euclidean Ramsey Theory
- Supervisor: David Conlon

Skills

Mathemtatics
Python

Yu-Han Wu

CV