AI Paper Atlas

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

WFR-FM: Simulation-Free Dynamic Unbalanced Optimal Transport

Qiangwei Peng, Zihan Wang, Junda Ying, Yuhao Sun, Qing Nie, Lei Zhang, Tiejun Li, Peijie Zhou

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow matching and flow sampling · 5 citations (OpenAlex)

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
use WFR-FM instead of VGFMVGFM · Synthetic Dyngen (5D)W1 distance: 0.598 -> 0.135Improved
use WFR-FM instead of DeepRUOTDeepRUOT · Synthetic Gene (2D)W1 distance: 0.043 -> 0.019Improved
use WFR-FM instead of TIGON on high-dimensional dataTIGON · Synthetic Gaussian (1000D)W1 distance: 2.263 -> 2.233Improved
use WFR-FM instead of UOT-FMUOT-FM · Synthetic Gaussian (1000D)relative mass error: 0.033 -> 0.044Hurt
use WFR-FM instead of DeepRUOTDeepRUOT · Hold-one-out EB (50D)mean W1 over held-out times: 10.075 -> 10.157Hurt
use WFR-FM instead of VGFMVGFM · Hold-one-out EMT (10D)mean W1 over held-out times: 0.301 -> 0.298Improved
use WFR-FM instead of DeepRUOTDeepRUOT · Hold-one-out Mouse (50D)mean W1 over held-out times: 6.847 -> 6.586Improved
use WFR-FM instead of VGFMVGFM · Hold-one-out CITE (50D)mean W1 over held-out times: 37.386 -> 37.221Improved
use WFR-FM instead of Var-RUOT for path actionVar-RUOT · Path action, Genepath action: 1.208 -> 1.305Hurt
use WFR-FM instead of DeepRUOT for path actionDeepRUOT · Path action, Dyngenpath action: 14.070 -> 9.410Improved
use WFR-FM instead of Action Matching for growthAction Matching · Simulation Gene growth rategrowth rate correlation: 0.5851 -> 0.9913Improved
use WFR-FM instead of TIGON for growthTIGON · Simulation Gene growth rategrowth rate correlation: 0.9705 -> 0.9913Improved

Later papers that compared with this method

2 later accepted papers report WFR-FM as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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