71 citations · 276 across the 43 of their papers we have counts for
5 papers · 1 filter
Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi +1
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate…
Learn to Guide Your Diffusion Model
Alexandre Galashov, Ashwini Pokle, Arnaud Doucet +3
Classifier-free guidance (CFG) is a widely used technique for improving the perceptual quality of samples from conditional diffusion models. It operates by linearly combining condi…
On the Edge of Memorization in Diffusion Models
Sam Buchanan, Druv Pai, Yi Ma +1
When do diffusion models reproduce their training data, and when are they able to generate samples beyond it? A practically relevant theoretical understanding of this interplay bet…
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
Tara Akhound-Sadegh, Jungyoon Lee, Avishek Joey Bose +7
Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact scientific applications. A promising appro…
From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
Marien Renaud, Valentin De Bortoli, Arthur Leclaire +1
We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to d…