Code for "MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training" at ICML 2026
-
Updated
May 13, 2026 - Python
Code for "MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training" at ICML 2026
A brain-computer interface (BCI) for decoding speech phonemes from EEG signals using a hybrid CNN-LSTM model, with interactive Streamlit visualizations and Docker support.
Syllable-balanced Mandarin reading corpus for BCI speech decoding
How much a speech brain-computer interface decoder degrades after being trained once on early sessions, what changes in the neural signal, and whether small labeled recalibration can restore it. 20 months, 45 sessions, T15 Brain-to-Text '25 dataset.
To associate your repository with the speech-decoding topic, visit your repo's landing page and select "manage topics."