PulseAugur
EN
LIVE 14:41:35
ENTITY Flow Matching for Generative Modeling

Flow Matching for Generative Modeling

PulseAugur coverage of Flow Matching for Generative Modeling — every cluster mentioning Flow Matching for Generative Modeling across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
20
82 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
20
77 over 90d
TIER MIX · 90D
TOPICS
RELATIONSHIPS
TIMELINE
  1. 2026-05-14 research_milestone Publication of a research paper detailing a new flow-matching planner for autonomous driving. source
SENTIMENT · 30D

10 day(s) with sentiment data

RECENT · PAGE 1/7 · 124 TOTAL
  1. TOOL · CL_257083 ·

    Flow Matching Model Predicts Aircraft Trajectories with High Accuracy

    Researchers have developed FlowATC, a novel architecture for predicting aircraft trajectories using flow matching techniques. Trained on over a million Automatic Dependent Surveillance-Broadcast (ADS-B) trajectory windo…

  2. TOOL · CL_252109 ·

    New HELLO solver drastically improves large-scale optimal transport performance

    Researchers have developed HELLO, a novel hierarchical solver designed to tackle large-scale optimal transport (OT) problems. This method casts OT as an edge localization task, utilizing dual potentials for both initial…

  3. TOOL · CL_249110 ·

    Guide to Imitation Learning for Robotics Released

    This article provides a guide to implementing imitation learning (IL) for robotics, focusing on vision-based policies trained from scratch. It contrasts IL with classic explicit policies and reinforcement learning, high…

  4. TOOL · CL_247901 ·

    BridgeMatch: New generative solver for 3D deformable registration

    Researchers have developed BridgeMatch, a novel two-stage generative solver for 3D deformable registration. This method maintains a complete soft matching matrix at both coarse and high resolutions, unlike traditional c…

  5. TOOL · CL_245105 ·

    New dataset and framework advance 4D interaction forecasting from video

    Researchers have introduced Coherent4D, a large-scale dataset designed for continuous 4D interaction forecasting from egocentric video. This dataset, comprising approximately 233,000 samples across three domains, aims t…

  6. TOOL · CL_245047 ·

    New latent-to-latent flow method enhances medical volume segmentation

    Researchers have developed a novel latent-to-latent flow technique for stochastic segmentation of medical volumes. This method addresses the challenge of limited annotations in large-scale medical datasets, particularly…

  7. TOOL · CL_239297 ·

    New SCAPES model generates environmental sounds efficiently

    Researchers have developed SCAPES, a new generative model for environmental sounds that is lightweight and resource-efficient. This model synthesizes high-fidelity environmental textures using high-level semantic contro…

  8. TOOL · CL_235596 ·

    Dark matter sensitivity explored using flow matching on CMS Open Data

    Researchers have developed a method to study dark matter using flow matching techniques on CMS Open Data. The approach models backgrounds using a conditional flow-matching continuous normalizing flow trained on selected…

  9. TOOL · CL_233588 ·

    SliceBridge framework repairs corrupted MRI intervals using flow matching

    Researchers have developed SliceBridge, a novel framework designed to repair corrupted intervals within T1-weighted MRI scans. This method utilizes rectified flow matching, conditioned on the surrounding intact slices a…

  10. TOOL · CL_233545 ·

    Quantum MeanFlow enables single-step generative sampling on quantum hardware

    Researchers have introduced Quantum MeanFlow (QMF), a novel method for single-step generative sampling on quantum computers. This approach, an analogue of classical MeanFlow, learns an average velocity field over time i…

  11. TOOL · CL_231368 ·

    New GeoLAMP model tackles complex partial differential equations

    Researchers have developed GeoLAMP, a novel geometry-aware latent autoregressive generative model designed to solve complex partial differential equations (PDEs). This model utilizes a dual-encoder architecture on graph…

  12. TOOL · CL_229412 ·

    New method models stochastic dynamics without data samples

    Researchers have developed a novel method for modeling Schrödinger bridges, which are stochastic dynamical systems that connect two probability distributions. This new approach, termed data-to-energy IPF, allows for the…

  13. RESEARCH · CL_229334 ·

    AI uses language to guide crystal and molecular structure generation

    Two new research papers introduce novel methods for structure generation using language-informed flow matching. The first, TFMat, uses structured text to guide crystal structure generation, improving match rates and ali…

  14. TOOL · CL_229284 ·

    New method traces AI-generated samples to training data clusters

    Researchers have developed a new method to trace generated samples back to specific clusters within training data for flow-matching models. This approach uses a hybrid analytical-learned technique to derive trajectory-b…

  15. RESEARCH · CL_228809 ·

    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…

  16. RESEARCH · CL_241532 ·

    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,"…

  17. TOOL · CL_227261 ·

    Physics-Guided Flow Matching advances CT image reconstruction

    Researchers have developed a new method for CT image reconstruction using Physics-Guided Flow Matching, an alternative to diffusion models. This approach trains a high-resolution Flow Matching model on CT images, employ…

  18. TOOL · CL_226976 ·

    New 'trajectory balance' objective improves GFlowNet learning

    Researchers have introduced "trajectory balance," a novel learning objective for Generative Flow Networks (GFlowNets). This new objective aims to improve credit assignment in GFlowNets, which are used for generating com…

  19. RESEARCH · CL_221232 ·

    New deep learning methods accelerate MRI reconstruction

    Researchers have developed two novel deep learning approaches for accelerating Magnetic Resonance Imaging (MRI) reconstruction. The first, FlowMoDL, is an unrolled neural network that combines a learned denoiser with co…

  20. TOOL · CL_221157 ·

    Drift Variation Autoencoder unifies generation and representation learning

    Researchers have introduced the Drift Variation Autoencoder (DVAE), a novel framework that unifies generative modeling and representation learning. This approach trains a masked encoder and a conditional decoder using a…