Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
More on lines in Euclidean Ramsey theory
Published in Comptes Rendus. Mathématique, 2022
Recommended citation: Conlon, D., & Wu, Y. H. (2023). More on lines in Euclidean Ramsey theory. Comptes Rendus. Mathématique, 361(G5), 897-901.
Download Paper
Implicit regularization of deep residual networks towards neural ODEs
Published in ICLR2024, 2023
Recommended citation: 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.
Download Paper
Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization
Published in COLT2025, 2025
Recommended citation: 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
Download Paper | Download Slides
Optimal Stopping in Latent Diffusion Model
Published in ICML 2026, 2025
Recommended citation: 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.
Download Paper | Download Slides
MIND: Monge Inception Distance for Generative Models Evaluation
Published in arXiv, 2026
Recommended citation: 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.
Download Paper
Understanding diffusion models requires rethinking (again) generalization
Published in arXiv, 2026
Recommended citation: Pierre Marion and Yu-Han Wu (2026) Understanding diffusion models requires rethinking (again) generalization. arXiv:2605.06077.
Download Paper
DiffusionGemma
Published in arXiv:2608.00146, 2026
Recommended citation: Taïga, DiffusionGemma Team Adrien Ali et al. “DiffusionGemma Technical Report.” (2026).
Download Paper
Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulation
Published in arXiv:2608.06107, 2026
Recommended citation: 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.
Download Paper
talks
Journée de Statistique 2025
Published:
Slides. Oral Presentation of the work “Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevents Memorization”.
COLT 2025
Published:
Slides. Oral presentation of the work “Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevents Memorization”.
PriGM Workshop
Published:
Slides, Poster. Oral presentation of the work “Optimal stopping in Latent Diffusion Models”.
Lemanth2026
Published:
Poster. Poster presentation of the work “MIND: Monge Inception Distance for Generative Models Evaluation”.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.