.png){kind=icon}
.png){kind=icon}
Return
A Language-Guided Multimodal Foundation Model for Zero-Shot and Multi-Task Brain Signal Analysis
.png){kind=icon}
OA
AI
M
Y
G
DOI：10.1002/aisy.70486.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Brain signal analysis is essential for both neuroscience research and clinical diagnostics, yet current approaches face critical limitations. End-to-end models require task-specific retraining and exhibit limited generalization, while pre-trained models lack semantic depth and still depend on extensive fine-tuning. Meanwhile, general-purpose multimodal foundation models, though powerful in other domains, struggle to interpret brain signals due to representational misalignment and lack of domain knowledge. This study introduces a Multimodal foundation modEl for zero-shoT and multI-taSk brain signal analysis (METIS) through a unified language-signal alignment framework. METIS is pretrained on the largest and most diverse brain-signal corpus to date, comprising over 70 000 h of recordings from more than 11 000 subjects across 20 datasets. In a comprehensive zero-shot evaluation across 12 datasets, METIS outperformed the leading generalist model by over 20.9% in average accuracy. Remarkably, without any fine-tuning, METIS's performance matches or exceeds that of supervised, task-specific models. Furthermore, METIS demonstrates exceptional data efficiency and strong generalization, achieving an average AUROC advantage of over 16.0% in few-shot settings and 15.9% in cross-dataset transfer. This work establishes a new paradigm for general-purpose brain signal analysis, paving the way for next-generation neurotechnology. The code is available at https://github.com/mingzhi-c/metis-brain-signal-foundation-model.
Keywords:
brain signal analysis
foundation models
language-signal alignment
zero-shot learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.1
Papers:
1.9K
Citations:
8.4K
Organization
Cited Papers