A Roadmap for MEG Foundation Models
Organizations: Cognitive and Computational Neuroscience Laboratory (CoCo Lab), Université de Montréal, Montréal, QC, Canada · Department of Psychology, Université de Montréal, Montréal, QC, Canada · Mila – Quebec Artificial Intelligence Institute, Montréal, QC, Canada · IMT Atlantique, Brest, F-29238, France ·
Abstract
Foundation models are beginning to reshape brain-signal analysis by moving the field beyond task-specific decoding pipelines toward reusable models pretrained on broad neural datasets. Magnetoencephalography (MEG) is a compelling but still underdeveloped target for this shift: it captures human cortical dynamics at millisecond resolution while offering stronger spatial interpretability than EEG, making it especially valuable for source-resolved studies of perception, language, cognition, and clinical brain function. Yet MEG foundation models remain at an early stage, with only a small number of MEG-specific and MEG-inclusive multi-modal models, modest pretraining corpora, and emerging but still limited benchmarks. This perspective lays down the basic concepts needed to understand MEG foundation models and provides a didactic overview of the field's key design choices, including tokenization, sensor- versus source-space representations, sensor-geometry encoding, backbone architectures, self-supervised objectives, and pretraining data. We then offer a roadmap for future development, organized around native MEG pretraining, adaptation of EEG foundation models, transfer from generic time-series models, and multi-modal integration with EEG, fMRI, MRI, behaviour, and stimulus features. We highlight the need for coordinated infrastructure, including diverse and reusable MEG datasets, rigorous evaluation across subjects, sites, tasks, and clinical settings, and responsible data-sharing practices that address consent, privacy, access, and governance.
Figures & tables
| Term | Definition |
|---|---|
| Core concepts for MEG foundation models | |
| Foundation model | A general-purpose model pretrained on broad and diverse data, then adapted to many downstream tasks rather than trained from scratch for each new task. |
| Pretraining | The initial large-scale training stage, usually on mostly unlabeled data, in which the model learns general representations before being adapted to specific tasks. |
| Fine-tuning | Updating some or all of a pretrained model’s parameters on a downstream task so that the model becomes specialized for a new dataset, question, or application. |
| Linear probing | Evaluating a pretrained model by freezing its internal representations and training only a simple linear classifier or regressor on top of them. |
| Downstream task | Any task performed after pretraining, such as cognitive-state decoding, clinical classification, speech decoding, or behavioral prediction. |