MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
This addresses the challenge of limited training data for clinical brain-to-text systems, offering a more efficient solution for paralyzed patients, though it appears incremental as it builds on pre-training methods with extended context.
The paper tackles the problem of data-efficient brain-to-text interfaces for paralyzed patients by proposing MEG-XL, a model pre-trained with 2.5 minutes of MEG context per sample, which matches supervised performance with much less data (e.g., 1 hour vs. 50 hours) and outperforms other brain foundation models.
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 .