Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped. Existing analyses often impose restrictive assumptions on the estimated velocity field and yield convergence rates that fail to reflect the intrinsic low-dimensional structure common in r...
Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett· 6 citations· ⚡1
The Control Variate Score Identity (CVSI) is introduced, an unbiased estimator with an analytically optimal, state- and time-dependent control coefficient that theoretically minimizes variance over the entire diffusion process in data-free sampler learning and training-free diffusion sampling.
Khaled Kahouli, R. Élie, Klaus-Robert Müller et al.· arXiv.org· 5 citations· ⚡1
This paper proposes Kastor, a comprehensive methodology to adapt a deterministic physics foundation model into a highly efficient and accurate generative surrogate, and introduces a two-stage inference scheme that combines a large-stride causal auto-regressive model with a non-causal temporal super-resolution network,...
Guillaume Couairon, Alexis Jacq, Yu-Han Wu et al.· 0 citations
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 a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel, avoiding the sequential decoding bottleneck of conventional au...
DiffusionGemma Team Adrien Ali Taïga, James Assiene, Daniele Calandriello et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
