AI News HubLIVE
原文2 min read

Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling

This study introduces a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data, systematically evaluating four fusion strategies on pulmonary embolism mortality and cardiovascular disease outcome prediction tasks. Results show that contrastive multimodal fusion provides the most consistent improvements, while task-specific fusion strategies are crucial for robust generalization.

SourcearXiv AIAuthor: Zhemin Zhang, Weijie Chen, David Le, Amara Tariq, Alex Wallace, Matthew Stib, Juan Maria Farina, Chadi Ayoub, Reza Arsanjani, Imon Banerjee

[2606.15038] Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling

[Submitted on 13 Jun 2026]

Title:Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling

View a PDF of the paper titled Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling, by Zhemin Zhang and 9 other authors

View PDF HTML (experimental)

Abstract:Accurate time-to-event (TTE) prediction from multimodal clinical data remains challenging due to modality imbalance and distribution shift. We introduce a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data, designed to generalize across tasks and institutions. CT and EHR modalities are encoded independently using domain-specific foundation models and aligned in a shared latent space through four principled fusion strategies: late fusion, contrastive alignment, cross-attention, and co-attention. We evaluate two clinically distinct TTE tasks: pulmonary embolism (PE) mortality and cardiovascular disease (CVD) outcomes, on large-scale multi-institutional cohorts (PE: N=3,099 train; 1,098 internal; 435 external; CVD: N=2,951 train; 837 internal; 682 external). Fusion consistently improves concordance index by 1.5-5.4% over unimodal baselines when modalities contribute comparably. Overall, contrastive multimodal fusion, particularly with CLMBR representations, provided the most consistent and statistically robust improvements, especially for PE mortality prediction. For MACE, cross-attention (one-hot) achieved the highest internal performance and image-guided co-attention achieved the best external performance. We therefore introduce a generalizable foundation model-based cross-modal alignment framework and provide the first systematic analysis of fusion behavior under modality imbalance in TTE prediction. Our results establish task-aware multimodal alignment as a necessary design principle for robust generalization and scalable clinical deployment.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.15038 [cs.AI]

(or arXiv:2606.15038v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.15038

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zhemin Zhang [view email] [v1] Sat, 13 Jun 2026 00:44:59 UTC (3,289 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modeling, by Zhemin Zhang and 9 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)