AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Bridging Vision and Language Concepts through Optimal Transport Semantic Flow

Chenyang Zhang, Anqi Dong, Guangming Zhu, Nuoye Xiong, Siyuan Wang, Lin Mei, Liang Zhang

ECCV 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 1 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
replace similarity-based concept inference with classical OT (ablation)Vanilla-CBM · ImageNetaccuracy: 79.17 -> 80.42Improved
replace similarity-based concept inference with classical OT (ablation)Vanilla-CBM · CIFAR-100accuracy: 80.04 -> 85.23Improved
use Vision-Language OT instead of classical OT (ablation)Vanilla-CBM + OT · CUBaccuracy: 80.31 -> 84.31Improved
use Vision-Language OT instead of classical OT (ablation)Vanilla-CBM + OT · Places365accuracy: 47.7 -> 50.59Improved
add inverse OT learned cost (ablation)Vanilla-CBM + VLOT · CUBaccuracy: 84.31 -> 87.44Improved
add inverse OT learned cost (ablation)Vanilla-CBM + VLOT · ImageNetaccuracy: 82.68 -> 84.87Improved
add semantic flow with velocity-based activation (ablation)Vanilla-CBM + VLOT + IoT · CUBaccuracy: 87.44 -> 89.92Improved
add semantic flow with velocity-based activation (ablation)Vanilla-CBM + VLOT + IoT · AwA2accuracy: 96.56 -> 98.88Improved
add semantic flow with velocity-based activation (ablation)Vanilla-CBM + VLOT + IoT · Places365accuracy: 52.99 -> 55.13Improved
use learned IoT cost instead of cosine distance or W2^2 (ablation)OT alignment · Cost learning (TRE)TRE: 2.371 -> 0.824Improved
use UOT instead of balanced OT in learned flow matching (ablation)IoT + OT Flow Matching · Semantic flow modelingVMSE: 1.782 -> 1.000Improved
use UOT instead of balanced OT in learned flow matching (ablation)IoT + OT Flow Matching · Semantic flow modelingNPE: 0.197 -> 0.021Improved

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