Welcome to my website
Hi, I am Yu-Han. I have been a PhD student in LPSM at Sorbonne University since September 2024. I am supervised by Gérard Biau, Claire Boyer and Pierre Marion. I am also part of the co-advised PhD student program at Google DeepMind, co-advised by Quentin Berthet and Romu Ellie. My research interests include: diffusion models, regularizations, ratent representation learning.
Brief Curriculum Vitae
- 2024- : Sorbonne University and google DeepMind, co-advised PhD student
- 2020-2024: Ecole Normale Supérieure
- 2022-2023: University Paris-Saclay, Master degree (Mathematics of Randomness)
- 2018-2020: Lycée Louis-le-Grand, Prepatory classes
Publications
- Marion, P.* & Wu, Y.-H.* (2026). Understanding diffusion models requires rethinking (again) generalization. arXiv:2605.06077.
- Berthet, Q., Wu, Y.-H., Crepy, C., Elie, R., Greff, K. & Sander, M. E. (2026). MIND: Monge Inception Distance for Generative Models Evaluation. arXiv:2605.06797.
- Wu, Y.-H., Berthet, Q., Biau, G., Boyer, C, Elie, R., & Marion P. (2025). Optimal Stopping in Latent Diffusion Models. arXiv:2510.08409.
- 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.
- Marion, P.*, Wu, Y.-H.*, Sander, M. E., & Biau, G. (2024). Implicit regularization of deep residual networks towards neural ODEs. The Twelfth International Conference on Learning Representations.
- Conlon, D., & Wu, Y.-H. (2023). More on lines in Euclidean Ramsey theory. Comptes Rendus. Mathématique, 361(G5), 897-901.
Internships
- 2024: Sorbonne University, Research Internship
- 2023: Owkin, Research Internship
- 2023: Sorbonne University, Research Internship
- 2022: Caltech, Research Internship