# ECG-Soup: Harnessing Multi-Layer Synergy for ECG Foundation Models

**Authors:** Phu X. Nguyen, Huy Phan, Hieu Pham, Christos Chatzichristos, Bert Vandenberk, Maarten De Vos

arXiv: 2509.00102 · 2025-10-27

## TL;DR

This paper introduces ECG-Soup, a transformer-based foundation model that leverages multi-layer synergy to improve ECG analysis across various applications.

## Contribution

It proposes a novel multi-layer synergy approach for ECG foundation models, enhancing their performance and generalization capabilities.

## Key findings

- Achieved state-of-the-art results on multiple ECG benchmarks.
- Demonstrated improved downstream task performance.
- Showed robustness across diverse ECG datasets.

## Abstract

Transformer-based foundation models for Electrocardiograms (ECGs) have recently achieved impressive performance in many downstream applications.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/2509.00102/full.md

## Figures

13 figures with captions in the complete paper: https://tomesphere.com/paper/2509.00102/full.md

## References

55 references — full list in the complete paper: https://tomesphere.com/paper/2509.00102/full.md

---
Source: https://tomesphere.com/paper/2509.00102