AI Paper Atlas

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

Reweighted Flow Matching via Unbalanced Optimal Transport for Label-free Long-tailed Generation

Hyunsoo Song, Minjung Gim, Jaewoong Choi

NeurIPS 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 summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes UOT-RFM, a label-free reweighted flow matching method using unbalanced optimal transport to counter majority bias in long-tailed generative modeling.

Problem

Standard flow matching over-represents dominant modes on long-tailed distributions, hurting tail-class fidelity and distributional accuracy.

Approach

Reweights flow matching training using unbalanced optimal transport so that tail-class samples are emphasized without requiring class labels.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add UOT-based inverse majority-score reweighting to flow matchingflow matching · CIFAR-10-LT (I=0.01, LT->LT)FID: 14.25 -> 11.03Improved
add UOT-RFM on CIFAR-100-LT with I=0.001flow matching · CIFAR-100-LT (I=0.001, LT->LT)FID: 31.83 -> 18.40Improved
use UOT-RFM instead of OT-CFMflow matching · CIFAR-10-LT (I=0.01) class distributionmean NCRE: 1.02 -> 0.40Improved
use UOT-RFM instead of UOT-CFMflow matching · CIFAR-10-LT (I=0.01, LT->LT)Precision: 0.73 -> 0.62Hurt
use UOT-RFM instead of UOT-CFMflow matching · CIFAR-10-LT (I=0.01, LT->LT)Recall: 0.29 -> 0.41Improved
increase correction order k from 1 to 8 (tau=2.0) (ablation)UOT-RFM · CIFAR-10-LT (I=0.01, LT->LT)FID: 13.77 -> 11.37Improved
increase tau from 2.0 to 6.0 (k=8) (ablation)UOT-RFM · CIFAR-10-LT (I=0.01, LT->LT)FID: 11.37 -> 12.41Hurt
increase correction order k (tau=2.0) in LT->Balanced (ablation)UOT-RFM · CIFAR-10-LT (I=0.01, LT->Balanced)FID: 25.02 -> 24.54 (k=4), 24.76 (k=8)Mixed
use UOT-RFM (k=1) instead of OT-CFM on balanced CIFAR-100flow matching · CIFAR-100 (balanced)FID: 6.14 -> 6.54Hurt
use UOT-RFM (k=1) instead of UOT-CFM on balanced CIFAR-10flow matching · CIFAR-10 (balanced)FID: 3.62 -> 3.58No clear effect

Experimental setup

Builds on: flow matching

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