AI Paper Atlas

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

Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment

Haobin Li, Yijie Lin, Peng Hu, Mouxing Yang, Xi Peng

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 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
apply RULE instead of best baseline, inherent noise, non-name attributesRULE · ICEWS-WIKI Non-nameH@1: 53.5 -> 64.2Improved
apply RULE under 50% injected noise, non-nameRULE · Non-name avg over 5 datasetsAvg H@1: 54.0 -> 64.3Improved
apply RULE under 50% injected noise, all attributesRULE · All-attributes avg over 5 datasetsAvg H@1: 94.7 -> 97.9Improved
increase injected noise from inherent to 50% (baselines degrade much more)MEAformer · Non-name avg over 5 datasetsAvg H@1: 67.0 -> 54.0Hurt
increase injected noise from inherent to 50% for RULERULE · Non-name avg over 5 datasetsAvg H@1: 73.8 -> 64.3Hurt
add Dually Robust Learning (uncertainty or consensus) over plain MSE loss (ablation)RULE · ICEWS-WIKIH@1Improved
add test-time correspondence reasoning combining MLLM rethinking scores with prior similarity (ablation)RULE · ICEWS-WIKIH@1Improved
add Dually Robust Fusion module (ablation)RULE · ICEWS-WIKIH@1Improved

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