Rectified Flow
PulseAugur coverage of Rectified Flow — every cluster mentioning Rectified Flow across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New flow matching methods enhance generative models for design and imaging · 6 sources tracked
Researchers are exploring advanced flow matching techniques to enhance generative models for inverse design problems and image generation. Conditional Flow Matching (CFM) shows promise in engineering inverse design, out…
-
New research offers geometric and residual-based perspectives on flow matching for generative models
Two new research papers explore advancements in flow matching techniques for generative modeling. The first paper, "Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective,"…
-
New framework Bridge Graphical Models improves generative AI design
Researchers have introduced Bridge Graphical Models (BGMs) as a new framework to analyze and improve continuous-time generative models. BGMs decouple design choices such as endpoint coupling, bridge law, and Markovian p…
-
New method erases unwanted concepts in AI image generation models
Researchers have developed a new tuning-free method for concept erasure in Multimodal Diffusion Transformers (MM-DiTs), which are advanced text-to-image generation models. This technique directly manipulates the model's…
-
Signed Rectified Flow enables negativity-controlled AI generation
Researchers have introduced Signed Rectified Flow (Signed RF), a novel generative modeling technique that extends Rectified Flow by targeting a signed measure. This method allows for the promotion of desired distributio…
-
FlowSonic enables stable zero-shot music editing with diffusion transformers
Researchers have developed FlowSonic, a new framework for zero-shot music editing using diffusion transformers trained with rectified flow. This method aims to balance semantic changes with the preservation of a music r…
-
New optimal self-distillation method improves generative model training
Researchers have developed a method called optimal self-distillation (SD) for rectified flow (RF) models, aiming to improve generative model training. This technique involves training a student model on a mix of true RF…
-
New research advances Rectified Flow and Flow Matching generative models · 10 sources tracked
Researchers are exploring new methods within the framework of Rectified Flow (RF) and Flow Matching (FM) generative models. One approach, Self-Consistent Flow (SC-Flow), unifies velocity and endpoint prediction to stabi…
-
FlowUpscaler offers rapid latent image upscaling for Flux.2
A new latent upscale model called FlowUpscaler has been developed for Flux.2 and its Klein variants. This model utilizes a Rectified Flow approach, allowing it to upscale images from 512x512 to 1024x1024 in just 8 milli…
-
Generative models adapted for faster lossy compression
Researchers have developed a novel method to adapt few-step generative models for lossy compression tasks. By leveraging frameworks like reverse channel coding (RCC), models such as Rectified Flow, Consistency Trajector…
-
User distills flow matching models for faster, CFG-free image generation
A user has developed a method to distill flow matching models into a "rectified flow" model, enabling faster image generation with fewer steps and without classifier-free guidance. This process involves fine-tuning a tr…
-
New GMF method boosts multimodal fusion trustworthiness
Researchers have developed a new method called Geometry-based Multimodal Fusion (GMF) to improve the trustworthiness of systems that combine data from multiple sources. Unlike existing methods that rely on a model's own…
-
Researchers rethink text-based segmentation using Rectified Flow over diffusion models
Researchers have developed RLFSeg, a new framework that utilizes Rectified Flow for text-based image segmentation. This approach aims to improve upon diffusion models by learning a direct mapping from images to segmenta…
-
LangPrecip uses language to improve weather forecasting accuracy
Researchers have developed LangPrecip, a novel framework for short-term precipitation forecasting that integrates meteorological text with radar data. This language-aware approach treats textual descriptions of weather …