AI Paper Atlas

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

A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs

Dongxiao He, Ankang Yang, Jitao Zhao, Di Jin

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 modality-specific GNN encoders instead of early fusion by mean pooling (ablation)CAME · Amazon-sportsMRR: 26.83 -> 37.68Improved
add modality-specific GNN encoders instead of early fusion by mean pooling (ablation)CAME · Amazon-clothMRR: 21.19 -> 28.88Improved
add dimension-wise gated fusion instead of average pooling (ablation)CAME · Amazon-clothMRR: 27.90 -> 28.88Improved
add modality-aware MoE instead of parameter-matched MLP fusion (ablation)CAME · Amazon-clothMRR: 26.37 -> 28.88Improved
add text-image alignment loss L_t,v (ablation)CAME · Amazon-clothMRR: 20.64 -> 28.88Improved
add text-fusion alignment loss L_t,f (ablation)CAME · Ele-fashionaccuracy: 85.04 -> 85.13No clear effect
use all three alignment losses instead of a single one (ablation)CAME · Ele-fashionaccuracy: 80.74 -> 85.13Improved
use CAME instead of UniGraph2 (mean of CLIP features)UniGraph2 · Amazon-sportsMRR: 29.52 -> 37.68Improved
use CAME on text-only graphUniGraph2 · Wiki-CS 1-shotaccuracy: 35.56 -> 47.65Improved
use CAME instead of UniGraph2UniGraph2 · WN18RRaccuracy: 75.20 -> 81.97Improved
vary weights of L_t,f and L_v,f (ablation)CAME · Ele-fashion and Amazon-clothperformanceMixed

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