Brain-to-Text Decoding with Only Minutes of Labelled Data Using MEG-XL
MEG-XL adapts to new subjects with less labelled data and offers a strong baseline for the 2026 PNPL competition’s broad track.
Competition Leaderboard Announcement
A potential source of cross-track leakage in the public broad-track leaderboard has come to our attention. Public leaderboards stay as they are; final rankings will be based on code-reviewed submissions.
Measuring Progress by Asking: What Can Thought-to-Text Interfaces Communicate?
Progress in thought-to-text with speech decoding BCIs is becoming increasingly difficult to compare. How can we standardise scores and measure progress?
Language-Inspired Approaches to Phoneme Classification
A linguistics-driven strategy for classifying phonetic features from MEG, and mapping back to ARPABET phonemes.
Phase 2 (Phoneme Classification) is Now Live!
We are excited to announce that Phase 2 of the LibriBrain Competition is now accepting submissions for the Phoneme Classification task.
Brain-Inspired Approaches to Speech Detection
Neuroscience-informed approaches to speech detection for the LibriBrain competition, including STG sensor analysis, spatial and temporal strategies, and architectural recommendations.
The Speech Detection task and the reference model
Exploring the Speech Detection task and the reference model architecture used in the LibriBrain competition, including insights into our 'Start Simple' approach and future research directions.
Phase 1 (Speech Detection) is Now Live!
We are excited to announce that Phase 1 of the LibriBrain Competition is now accepting submissions for the Speech Detection task.
Building a Collaborative Foundation for Non-Invasive Speech BCIs: The 2025 PNPL Competition
Exploring the motivation behind the 2025 PNPL Competition and how we're building towards non-invasive speech brain-computer interfaces through deep MEG datasets and collaborative research.