Work

ELF: A Family of Encoder-Free ECG-Language Models

Year: 2026

Type: preprint

Abstract: ECG-Language Models (ELMs) extend recent advances in Multimodal Large Language Models (MLLMs) to automated ECG interpretation. However, most existing ELMs inherit Vision-Language Model (VLM) design choices and rely on pretrained ECG encoders, introducing substantial architectural and training complexity. Inspired by encoder-free VLMs, we introduce ELF, a family of three encoder-free ELMs that remain competitive with, and often outperform, prior state-of-the-art ELMs across two datasets despite substantially simpler architectures and training pipelines. All code and data are available at github.com/ELM-Research/ECG-Language-Models.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2601.18798

Authors: Han, William, Chen, Tony, Duan, Chaojing, Song, Xiaoyu, Yao, Yihang, Yang, Yuzhe, Rosenberg, Michael A., Liu, Emerson, Zhao, Ding

Institutions: Carnegie Mellon University, Allegheny Health Network, University of California, Los Angeles, University of Colorado System

Language: English

Topic: ECG Monitoring and Analysis

Subfield: Cardiology and Cardiovascular Medicine

Field: Medicine

Domain: Health Sciences

Open Access status: green

OpenAlex ID: W7125954545

Cites: 26

Cited by: 1

Related to: 10