AI Paper Atlas

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

Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis

Wenjing Liu, Qin Ren, Wen Zhang, Yuewei Lin, Chenyu You

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 5 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 Together stage (shared prototypes + UOT alignment) (ablation)TTA baseline · TCGA average over 5 cohortsC-index: 0.643 -> 0.662Improved
add Apart stage (anchor refiner + contrastive objective) (ablation)TTA baseline · TCGA average over 5 cohortsC-index: 0.643 -> 0.666Improved
add both Together and Apart (ablation)TTA baseline · TCGA average over 5 cohortsC-index: 0.643 -> 0.693Improved
add Apart stage on CRC (ablation)Together-only TTA · TCGA CRCC-index: 0.587 -> 0.685Improved
use shared prototypes instead of modality-specific (ablation)TTA Together stage · TCGA average over 5 cohortsC-index: 0.681 -> 0.684Improved
add joint UOT over concatenated prototypes (ablation)TTA Together stage · TCGA average over 5 cohortsC-index: 0.684 -> 0.693Improved
add anchor refinement alone (ablation)TTA Apart stage · TCGA average over 5 cohortsC-index: 0.662 -> 0.669Improved
add contrastive regularization alone (ablation)TTA Apart stage · TCGA average over 5 cohortsC-index: 0.662 -> 0.672Improved
combine anchor refinement and contrastive regularization (ablation)TTA Apart stage · TCGA average over 5 cohortsC-index: 0.662 -> 0.693Improved
use UOT assignment instead of hard KMeans (ablation)TTA · TCGA average over 5 cohortsC-index: 0.681 -> 0.693Improved
use UOT instead of general OT (ablation)TTA · TCGA average over 5 cohortsC-index: 0.683 -> 0.693Improved
add curriculum mass rho (ablation)TTA UOT · TCGA average over 5 cohortsC-index: 0.686 -> 0.693Improved

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