Diffusion models are the main driver of progress in image and video synthesis, but suffer
from slow inference speed. Distillation methods, like the recently introduced adversarial …

Diffusion models and flow-matching models have enabled generating diverse and realistic
images by learning to transfer noise to data. However, sampling from these models involves …

Diffusion models (DMs) are capable of generating remarkably high-quality samples by
iteratively denoising a random vector, a process that corresponds to moving along the …

We propose Diffusion Model Predictive Control (D-MPC), a novel MPC approach that learns
a multi-step action proposal and a multi-step dynamics model, both using diffusion models …

Training generative models to sample from unnormalized density functions is an important
and challenging task in machine learning. Traditional training methods often rely on the …

Abstract This work introduces Variational Diffusion Distillation (VDD), a novel method that
distills denoising diffusion policies into Mixtures of Experts (MoE) through variational …

Current video diffusion models achieve impressive generation quality but struggle in
interactive applications due to bidirectional attention dependencies. The generation of a …

Diffusion models achieve high-quality sample generation at the cost of a lengthy multistep
inference procedure. To overcome this, diffusion distillation techniques produce student …

Diffusion probabilistic models have shown significant progress in video generation;
however, their computational efficiency is limited by the large number of sampling steps …

Diffusion models excel at generative modeling (eg, text-to-image) but sampling requires
multiple denoising network passes, limiting practicality. Efforts such as progressive …