activity
20242026
collaborators

11 papers

cs.LG2026

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

Guillaume Couairon, Alexis Jacq, Yu-Han Wu +4

Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fa…

cs.CL2026

DiffusionGemma Technical Report

DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41

We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at…

cs.LG2026

Diffusion Fine-tuning with Rewarded Moment Matching Distillation

Alexis Jacq, Guillaume Couairon, Valentin De Bortoli +3

Distillation and Reinforcement Learning (RL) fine-tuning are the primary pillars of diffusion post-training. While traditionally studied in isolation, the interaction between these…

cs.LG2026

MIND: Monge Inception Distance for Generative Models Evaluation

Quentin Berthet, Yu-Han Wu, Clement Crepy +3

We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Fréchet Inception Distance (FID). Th…

stat.ML2026

Fair regression under localized demographic parity constraints

Arthur Charpentier, Christophe Denis, Romuald Elie +2

Demographic parity (DP) is a widely used group fairness criterion requiring predictive distributions to be invariant across sensitive groups. While natural in classification, full…

stat.ML2026

Optimal Stopping in Latent Diffusion Models

Yu-Han Wu, Quentin Berthet, Gérard Biau +3

We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arg…