activity
20242026
collaborators
Showing cs.LGShow all

11 papers · 1 filter

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

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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.…