Analyzing and improving the training dynamics of diffusion models
T Karras, M Aittala, J Lehtinen… - Proceedings of the …, 2024 - openaccess.thecvf.com
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 …
unparalleled scaling to large datasets. In this paper we identify and rectify several causes for …
Towards the detection of diffusion model deepfakes
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 …
However, to date, only little attention has been paid to the detection of DM-generated …
Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions
Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …
particularly in generating texts, images, and videos using models trained from offline data …
Scalable diffusion models with state space backbone
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 …
space architecture. We endeavor to train diffusion models for image data, wherein the …
Diffusion-rwkv: Scaling rwkv-like architectures for diffusion models
Transformers have catalyzed advancements in computer vision and natural language
processing (NLP) fields. However, substantial computational complexity poses limitations for …
processing (NLP) fields. However, substantial computational complexity poses limitations for …
Point cloud approach to generative modeling for galaxy surveys at the field level
C Cuesta-Lazaro, S Mishra-Sharma - Physical Review D, 2024 - APS
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 …
our Universe directly as a collection of points in 3D space (coordinates) optionally with …
Improved Noise Schedule for Diffusion Training
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 …
However, training a single model to predict noise across various levels poses significant …
Spectral motion alignment for video motion transfer using diffusion models
The evolution of diffusion models has greatly impacted video generation and understanding.
Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the …
Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the …
Stochastic Localization via Iterative Posterior Sampling
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 …
recently emerged. In these models, one seeks to noise a sample from the data distribution …
Rolling Diffusion Models
Diffusion models have recently been increasingly applied to temporal data such as video,
fluid mechanics simulations, or climate data. These methods generally treat subsequent …
fluid mechanics simulations, or climate data. These methods generally treat subsequent …