AI Paper Atlas

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

IBMA: Information Bottleneck-Based Multimodal Alignment

Yancheng Wang, Zeyu Dong, Dongfang Sun, Alvin C Silva, Teresa Wu, Yingzhen Yang

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

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
add modality-specific representation alignment (ablation)IBMA · CheXpertmAUC (%): 89.7 -> 91.1Improved
add modality-specific representation alignment (ablation)IBMA · MIMIC-CXRmAUC (%): 71.4 -> 72.7Improved
use IBB instead of CLUB bound (ablation)IBMA · CheXpertmAUC (%): 90.0 -> 91.1Improved
use IBB instead of VIB bound (ablation)IBMA · CREMA-Daccuracy: 63.9 -> 65.4Improved
use IBB instead of APIB (ablation)IBMA · CREMA-Daccuracy: 63.8 -> 65.4Improved
use IBB instead of CLUB for training cost (ablation)IBMA · CREMA-Dtraining time (min/epoch): 3.8 -> 2.0Improved
add modality-specific IB alignment lowers IB loss (ablation)IBMA · MIMIC-CXRmultimodal IB loss: -0.035 -> -0.058Improved
use IBMA instead of OMIBIBMA · CREMA-Daccuracy: 63.6 -> 65.4Improved
use IBB instead of VIB (ablation)IBMA · CREMA-Dtraining time (min/epoch): 1.9 -> 2.0Hurt

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