AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Rank-Aware Hyperbolic Alignment for Vision–Language Dataset Distillation

Jongoh Jeong, Sun-Kyung Lee, KUK-JIN YOON

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 0 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 RAHA instead of CovMatch at larger budgetsRAHA · Flickr8kmean retrieval recall: 25.3 vs 18.8 (200 pairs); 30.7 vs 25.9 (500)Improved
use RAHA instead of CovMatch at 100 pairsRAHA · Flickr30kmean retrieval recall: 22.8 -> 20.7Hurt
use RAHA instead of LoRS at 100 pairsRAHA · Flickr30kmean retrieval recall: 27.4 -> 20.7Hurt
use RAHA instead of CovMatchRAHA · Flickr8k cross-architecturemean recall: 7.3 -> 6.9 (100); 7.2 -> 8.7 (200); 8.7 -> 12.7 (500)Mixed
use RAHA instead of CovMatchRAHA · Flickr8k image-side noisemean degradation: 4.6 -> 4.1 (100); 6.4 -> 6.8 (500)Mixed
add range relevance term to hyperbolic contrast (ablation)RAHA · Flickr8k 100 pairsmean retrievalImproved
use residual term alone (ablation)RAHA · Flickr8k 100 pairsmean retrievalHurt
combine range and residual with regularizers (ablation)RAHA · Flickr8k 100 pairsmean retrievalImproved
raise energy threshold rho from 0.95 to 1.0 (ablation)RAHA · retrievalmean retrievalHurt
use larger real batches (ablation)RAHA · retrievalmean retrievalImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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