Diffusion models currently dominate the field of data-driven image synthesis with their
unparalleled scaling to large datasets. In this paper we identify and rectify several causes for …

Diffusion models (DMs) have recently emerged as a promising method in image synthesis.
However, to date, only little attention has been paid to the detection of DM-generated …

Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …

This paper presents a new exploration into a category of diffusion models built upon state
space architecture. We endeavor to train diffusion models for image data, wherein the …

Transformers have catalyzed advancements in computer vision and natural language
processing (NLP) fields. However, substantial computational complexity poses limitations for …

We introduce a diffusion-based generative model to describe the distribution of galaxies in
our Universe directly as a collection of points in 3D space (coordinates) optionally with …

Diffusion models have emerged as the de facto choice for generating visual signals.
However, training a single model to predict noise across various levels poses significant …

The evolution of diffusion models has greatly impacted video generation and understanding.
Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the …

Building upon score-based learning, new interest in stochastic localization techniques has
recently emerged. In these models, one seeks to noise a sample from the data distribution …

Diffusion models have recently been increasingly applied to temporal data such as video,
fluid mechanics simulations, or climate data. These methods generally treat subsequent …