11 papers
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…
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…
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…
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…
Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
Despite the remarkable empirical success of score-based diffusion models, their statistical guarantees remain underdeveloped. Existing analyses often provide pessimistic convergenc…
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…