AI Paper Atlas

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

H2-Surv: Hierarchical Hyperbolic Multimodal Representation Learning for Survival Prediction

Jiaqi Yang, Wenting Chen, Xiangjian He, Yuanbai Li, Sen Yang, Linlin Shen, Xiaohan Xing

CVPR 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 HyMap hyperbolic mapping (ablation)MOTCat baseline · Overall six cohortsmean C-index: 0.668 -> 0.680Improved
add H2M hierarchical constraints on top of HyMap (ablation)H2-Surv · Overall six cohortsmean C-index: 0.680 -> 0.694Improved
add TOCL on top of HyMap (ablation)H2-Surv · Overall six cohortsmean C-index: 0.680 -> 0.693Improved
add TOCL alone (ablation)MOTCat baseline · Overall six cohortsmean C-index: 0.668 -> 0.682Improved
combine HyMap, H2M and TOCL (ablation)H2-Surv · Overall six cohortsmean C-index: 0.694 -> 0.716Improved
add H2M on top of HyMap for TCGA-LUAD (ablation)H2-Surv · TCGA-LUADC-index: 0.681 -> 0.681No clear effect
use H2-Surv over best baselines PIBD/PANTHERH2-Surv · Overall six cohortsmean C-index: 0.684 -> 0.716Improved
use hyperbolic space instead of Euclidean space (ablation)H2-Surv · Efficiencytest time (ms): 11.85 -> 10.34 ms; GPU 13.04 -> 13.30 GBMixed

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