activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network

Grigory Bartosh, David Ruhe, Emiel Hoogeboom +3

Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network.…

cs.LG2026

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD

Emiel Hoogeboom, David Ruhe, Jonathan Heek +2

It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps…

cs.LG2026

Unified Latents (UL): How to train your latents

Jonathan Heek, Emiel Hoogeboom, Thomas Mensink +1

We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the…

cs.LG2024

Multistep Consistency Models

Jonathan Heek, Emiel Hoogeboom, Tim Salimans

Diffusion models are relatively easy to train but require many steps to generate samples. Consistency models are far more difficult to train, but generate samples in a single step.…

cs.LG2024

Model Integrity when Unlearning with T2I Diffusion Models

Andrea Schioppa, Emiel Hoogeboom, Jonathan Heek

The rapid advancement of text-to-image Diffusion Models has led to their widespread public accessibility. However these models, trained on large internet datasets, can sometimes ge…

cs.LG2024

Multistep Distillation of Diffusion Models via Moment Matching

Tim Salimans, Thomas Mensink, Jonathan Heek +1

We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of th…