AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Flow Matching for Multimodal Distributions

Gaoxiang Luo, Frank Cole, Sihang Zhang, Yuxiang Wan, Yulong Lu, Ju Sun

CVPR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace Gaussian source with GMM source and mode couplingDiTDH-XL on DINOv2-B latents · ImageNet 256 unconditional, 80 epochs, no guidanceFID: 9.33 -> 3.18Improved
replace Gaussian source with GMM source and mode couplingDiTDH-XL · ImageNet 256 unconditional, 80 epochs, with autoguidanceFID: 5.82 -> 2.74Improved
GMM source without mode coupling (drop mode coupling) (ablation)MM-FM · ImageNet 256 unconditional, 80 epochs, no guidanceFID: 3.82 -> 3.18 (adding mode conditioning)Improved
use GMM source alone with independent coupling (ablation)Flow matching, toy R10 · Toy R10 spread datasquared 2-Wasserstein distance: 1.582 -> 1.631Hurt
add mode coupling on top of GMM source (ablation)Flow matching, toy R10 · Toy R10 spread dataaverage trajectory length: 2.30 -> 2.00Improved
increase number of GMM modes (ablation)MM-FM without mode conditioning · ImageNet 256 unconditionalFIDImproved
use MM-FM sampling with fewer ODE stepsDiTDH-XL · ImageNet 256 unconditionalODE steps for same FID: 25 -> 5 ODE stepsImproved
train on 10% of ImageNet with MM-FMDiTDH-S · ImageNet 256, 10% data, 400 epochsFID-50K: 24.65 -> 8.04Improved
vary GMM covariance type and assignment type (ablation)MM-FM · ImageNet 256 unconditionalFIDNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy