Metraipolis › archive › dc_7b5cecc99be4

MEG-Mamba: A Scalable State-Space Foundation Model for Magnetoencephalography — arXiv:2610.00746

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.00746
License (as archived): CC0-1.0
Archived: 2026-10-07T12:22:49.167Z
SHA-256 of the archived text: 4b3df411d4b1d200a7c42f131101e61bd17457e5960b38469acea869c8731c95
Stable URL of this page: https://metraipolis.com/documento/dc_7b5cecc99be4

How to cite

MEG-Mamba: A Scalable State-Space Foundation Model for Magnetoencephalography — arXiv:2610.00746 — arXiv (en), https://arxiv.org/abs/2610.00746 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b5cecc99be4 (Metraipolis archive dc_7b5cecc99be4, sha256 4b3df411d4b1d200a7c42f131101e61bd17457e5960b38469acea869c8731c95)

BibTeX

@misc{dc7b5cecc99be4,
  title = {MEG-Mamba: A Scalable State-Space Foundation Model for Magnetoencephalography — arXiv:2610.00746},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00746},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b5cecc99be4; sha256 4b3df411d4b1d200a7c42f131101e61bd17457e5960b38469acea869c8731c95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00746. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Magnetoencephalography (MEG) is an imaging technique that offers a non-invasive, millisecond-resolution view of human brain activity. The increasing availability of MEG data presents an opportunity to take advantage of a recent advance in artificial intelligence, namely self-supervised foundation models. Existing foundation models for MEG (and electroencephalography) have been built on a transformer architecture. Here, we introduce MEG-Mamba: a generative foundation model for neural activity (source reconstructed, parcellated MEG) built on a Mamba architecture. MEG-Mamba is trained to predict the next token of a discretised MEG signal, conditioned on a brain region and recording session. MEG-Mamba surpasses the generative fidelity of a transformer-based alternative (MEG-GPT) while pre-training in less time (22 vs 400 GPU-hours) and modelling a longer context (4 vs 0.32 s). We evaluate MEG-Mamba by examining the spatio-spectral characteristics of the data it generates and by interpreting its learned embeddings. Furthermore, we demonstrate that lightweight stimulus conditioning (LoRA) can be used to generate realistic task-evoked responses that are not included in pre-training. Our results suggest that Mamba is a promising backbone for scaling neural foundation models.

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-10-02 in q-bio.NC).
Categorie arXiv: Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2610.00746 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:55:45.032Z dalla pagina https://arxiv.org/catchup/q-bio.NC/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).