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

William Han, Tony Chen, Chaojing Duan, Xiaoyu Song, Yihang Yao, Yuzhe Yang, Michael Rosenberg, Emerson Liu, Ding Zhao
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:550-583, 2026.

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 https://github.com/ELM-Research/ECG-Language-Models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-han26a, title = {ELF: A Family of Encoder-Free ECG-Language Models}, author = {Han, William and Chen, Tony and Duan, Chaojing and Song, Xiaoyu and Yao, Yihang and Yang, Yuzhe and Rosenberg, Michael and Liu, Emerson and Zhao, Ding}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {550--583}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/han26a/han26a.pdf}, url = {https://proceedings.mlr.press/v340/han26a.html}, 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 https://github.com/ELM-Research/ECG-Language-Models.} }
Endnote
%0 Conference Paper %T ELF: A Family of Encoder-Free ECG-Language Models %A William Han %A Tony Chen %A Chaojing Duan %A Xiaoyu Song %A Yihang Yao %A Yuzhe Yang %A Michael Rosenberg %A Emerson Liu %A Ding Zhao %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-han26a %I PMLR %P 550--583 %U https://proceedings.mlr.press/v340/han26a.html %V 340 %X 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 https://github.com/ELM-Research/ECG-Language-Models.
APA
Han, W., Chen, T., Duan, C., Song, X., Yao, Y., Yang, Y., Rosenberg, M., Liu, E. & Zhao, D.. (2026). ELF: A Family of Encoder-Free ECG-Language Models. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:550-583 Available from https://proceedings.mlr.press/v340/han26a.html.

Related Material