MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jayalath, Dulhan, Jones, Oiwi Parker
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914547098451968
author Jayalath, Dulhan
Jones, Oiwi Parker
author_facet Jayalath, Dulhan
Jones, Oiwi Parker
contents Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-efficient generalisation by learning statistical priors across subjects, but these priors critically depend on context. While natural speech might unfold gradually over minutes, most methods pre-train with only a few seconds of context. Thus, we propose MEG-XL, a model pre-trained with 2.5 minutes of MEG context per sample, 5-300x longer than prior work, and equivalent to 191k tokens, capturing extended neural context. Fine-tuning on the task of word decoding from brain data, MEG-XL matches supervised performance with a fraction of the data (e.g. 1hr vs 50hrs) and outperforms brain foundation models. We find that models pre-trained with longer contexts learn representations that transfer better to word decoding. Our results indicate that long-context pre-training helps exploit extended neural context that other methods unnecessarily discard. Code, model weights, and instructions are available at https://github.com/neural-processing-lab/MEG-XL .
format Preprint
id arxiv_https___arxiv_org_abs_2602_02494
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
Jayalath, Dulhan
Jones, Oiwi Parker
Machine Learning
Neurons and Cognition
Clinical brain-to-text interfaces are designed for paralysed patients who cannot provide extensive training recordings. Pre-training improves data-efficient generalisation by learning statistical priors across subjects, but these priors critically depend on context. While natural speech might unfold gradually over minutes, most methods pre-train with only a few seconds of context. Thus, we propose MEG-XL, a model pre-trained with 2.5 minutes of MEG context per sample, 5-300x longer than prior work, and equivalent to 191k tokens, capturing extended neural context. Fine-tuning on the task of word decoding from brain data, MEG-XL matches supervised performance with a fraction of the data (e.g. 1hr vs 50hrs) and outperforms brain foundation models. We find that models pre-trained with longer contexts learn representations that transfer better to word decoding. Our results indicate that long-context pre-training helps exploit extended neural context that other methods unnecessarily discard. Code, model weights, and instructions are available at https://github.com/neural-processing-lab/MEG-XL .
title MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
topic Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2602.02494