AI Paper Atlas

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

M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model

Yihang Liu, Longzhen Yang, Jiaxiong Yang, Ying Wen, Lianghua He, Heng Tao Shen

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 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
add MoE projector alone to unified CL (ablation)Unified CL baseline · APTOS (ablation)downstream score (%): 90.36 -> 87.97Hurt
add MoE projector alone to unified CL (ablation)Unified CL baseline · RSNA (ablation)downstream score (%): 87.42 -> 88.31Mixed
add MoE projector alone to unified CL (ablation)Unified CL baseline · HAM10000 (ablation)downstream score (%): 92.77 -> 90.86Hurt
add routing-consistency loss L_route to MoE (ablation)MoE projector · RSNA (ablation)downstream score (%): 88.31 -> 91.45Improved
add routing-consistency loss L_route to MoE (ablation)MoE projector · APTOS (ablation)downstream score (%): 87.97 -> 93.46Improved
add routing-consistency loss L_route to MoE (ablation)MoE projector · Mitosis (ablation)downstream score (%): 88.64 -> 91.75Improved
add intra-modality contrastive loss L_cst (ablation)MoE + L_route · RSNA (ablation)downstream score (%): 91.45 -> 93.23Improved
add intra-modality contrastive loss L_cst (ablation)MoE + L_route · Mitosis (ablation)downstream score (%): 91.75 -> 95.62Improved
add intra-modality contrastive loss L_cst (ablation)MoE + L_route · OCTID (ablation)downstream score (%): 98.84 -> 99.34Improved
add all M-IDoL components (MoE, L_route, L_cst) to unified CL baseline (ablation)Unified CL baseline · HAM10000 (ablation)downstream score (%): 92.77 -> 97.96Improved
increase number of MoE experts beyond one per modality (ablation)M-IDoL · downstream tasksperformanceNo clear effect
use M-IDoL (unified, multimodal) instead of modality-specific Panderm on ISIC2016Panderm · ISIC2016 (downstream)ACC (%): 87.88 -> 86.39Hurt

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