Diffusion models
PulseAugur coverage of Diffusion models — every cluster mentioning Diffusion models across labs, papers, and developer communities, ranked by signal.
-
New AID method improves image inpainting with diffusion models
Researchers have developed a new method called Amortized Inpainting with Diffusion (AID) for image inpainting using pretrained diffusion models. AID trains a small, reusable guidance module offline, which can then be ap…
-
FlowSR achieves single-step image super-resolution with diffusion models
Researchers have developed FlowSR, a new method for image super-resolution that significantly speeds up the process using diffusion models. This approach reformulates super-resolution as a rectified flow from low-resolu…
-
He Kai Ming's team advances flow matching for faster image generation
He Kai Ming's team has published several papers challenging the dominance of diffusion models in image generation, proposing flow matching as a more efficient alternative. Their work introduces methods like JiT, which d…
-
Masked Generative Transformers offer faster, more precise image editing
Researchers have introduced EditMGT, a novel image editing framework utilizing Masked Generative Transformers (MGTs) as an alternative to dominant diffusion models. This MGT-based approach offers localized token predict…
-
Diffusion models and NeRF combine for probabilistic 3D scene reconstruction
Researchers have developed a novel method for 3D scene reconstruction by integrating diffusion models with Neural Radiance Fields (NeRF). This approach treats 3D reconstruction as a probabilistic problem, using a stocha…
-
New diffusion model enhances MRI reconstruction and coil sensitivity estimation
Researchers have developed a new method for reconstructing magnetic resonance images (MRIs) using diffusion models, which are known for generating high-quality images. This approach addresses limitations of existing tec…
-
Generative models learn rules across two distinct training timescales
Researchers have identified two distinct timescales in generative model training: the point at which generations become rule-valid ($\tau_{\mathrm{rule}}$) and the point at which models begin reproducing training sample…
-
New research explores one-step generative models via Wasserstein flows
Two new research papers explore novel approaches to generative modeling, aiming to significantly speed up the process. One paper introduces W-Flow, a framework that uses Wasserstein gradient flows to compress complex ev…