AI Paper Atlas

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

Structure-aware Granular-Ball based Information Bottleneck for Multi-modal Clustering

Zhengzheng Lou, Yuhan Zhan, Mingyang Lv, Yingxuan Li, Yuyang Du, Shizhe Hu

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion

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 granular-ball representation (vs sample-level IB) (ablation)SGB-IB · BBCACC: 81.29 -> 87.64Improved
add granular-ball representation (vs sample-level IB) (ablation)SGB-IB · ReutersACC: 50.71 -> 52.84Improved
add structure-aware weight SG on top of GB generation (ablation)SGB-IB · BBCACC: 87.64 -> 90.95Improved
add structure-aware weight SG on top of GB generation (ablation)SGB-IB · WVUACC: 62.44 -> 65.23Improved
add structure-aware weight SG on top of GB generation (ablation)SGB-IB · COIL100ACC: 52.86 -> 53.94Improved
add both GB and SG versus neither (ablation)SGB-IB · SOCCERACC: 53.64 -> 55.71Improved
vary beta in {100, 500, 700, 900} and alpha in [0, 0.4] (ablation)SGB-IB · five MMC datasetsACCNo clear effect
vary purity threshold tau and minimum size nmin (ablation)SGB-IB · five MMC datasetsACCNo clear effect

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