11 papers · 1 filter
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…
Accelerating Speculative Diffusions via Block Verification
Alexander Soen, Hisham Husain, Valentin De Bortoli +1
Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribu…
On the Wasserstein Gradient Flow Interpretation of Drifting Models
Arthur Gretton, Li Kevin Wenliang, Alexandre Galashov +3
Recently, Deng et al. (2026) proposed Generative Modeling via Drifting (GMD), a novel framework for generative tasks. This note presents an analysis of GMD through the lens of Wass…
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…
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…
Distributional Diffusion Models with Scoring Rules
Valentin De Bortoli, Alexandre Galashov, J. Swaroop Guntupalli +4
Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted.…