AI Paper Atlas

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

MUST: Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing Modality

Kyungwon Kim, Dosik Hwang

CVPR 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 Stage 1 warm-up with noise injection (ablation)MUST · TCGA 5 datasets (complete data)C-index: BRCA 0.647 -> 0.690; UCEC 0.733 -> 0.768; LUAD 0.690 -> 0.686Improved
add class token [CLS] to LDM conditioning (ablation)MUST · TCGA BLCA (missing genomics)C-index: 0.665 -> 0.673Improved
add class token [CLS] to LDM conditioning (ablation)MUST · TCGA UCEC (missing pathology)C-index: 0.740 -> 0.748 (missing P); 0.746 -> 0.755 (missing G)Mixed
use shared subspace rank r=64 instead of 16, 32 or 128 (ablation)MUST · TCGA datasetsC-indexImproved
use MUST decomposition vs cross-attention without decomposition (CMTA)multimodal survival model · TCGA overall (complete data)C-index: 0.724 -> 0.742Improved
use MUST with missing genomics vs LD-CVAEmissing-modality handling · TCGA overall (missing genomics)C-index: 0.697 -> 0.716Improved
missing pathology instead of complete data (LDM reconstruction)MUST · TCGA BRCA/GBMLGG/LUADC-index: BRCA 0.690 -> 0.692; GBMLGG 0.864 -> 0.865; LUAD 0.686 -> 0.690No clear effect
missing genomics instead of complete dataMUST · TCGA overallC-index: 0.742 -> 0.716Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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