AI4Meder

AI4Meder 站内搜索

搜索医学 AI 论文与资源

按论文、数据资源、技术竞赛、投稿截止日期和课程资源检索社区内容,快速进入对应详情页。

1 条结果

输入关键词或点击标签,按论文、数据资源、竞赛截止日期、征稿与课程缩小范围。 标签:Biosignal Foundation Models 范围:论文

清空筛选
论文ICLR 2026 Poster2026 年trustworthy medical AI

用时频 motif 学习对单通道 EEG 进行 token 化

ICLR 2026 Poster accepted paper at ICLR 2026. Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from *single-channel* EEG signals and encodes them into discrete tokens. We propose a dual-path architecture with time–frequency masking to capture robust motif representations, and it is model-agnostic, supporting both lightweight transformers and existing foundation models for downstream tasks. Our study demonstrates three key benefits: *Accuracy:* Experiments on four diverse EEG benchmarks demonstrate consistent performance gains across both single- and multi-dataset pretraining settings, achieving up to $11\%$ improvement in Cohen’s Kappa over strong baselines. Code/project link: https://github.com/Jathurshan0330/TFM-Tokenizer