ELF无需预训练编码器，仍能高效解析心电图。
ELF: A Family of Encoder-Free ECG-Language Models
- 摒弃传统编码器，直接用语言模型处理心电图信号
- 在两个数据集上表现优于或媲美现有最先进模型
- 架构简单、训练成本低，适合临床快速部署
心电图-语言模型（ELMs）将多模态大语言模型（MLLMs）的进展拓展至心电图自动解读。然而，多数现有ELM沿用视觉-语言模型（VLM）的设计，依赖预训练心电图编码器，带来显著的结构与训练复杂性。受无编码器视觉-语言模型启发，我们提出ELF，一个包含三种无编码器设计的ELM家族，在两个数据集上表现媲美甚至超越先前最优模型，同时具备更简单的架构和训练流程。所有代码与数据均公开于github.com/ELM-Research/ECG-Language-Models。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。