Meta Revolutionizes Brain-Text Decoding with Brain2Qwerty V2
Meta says the upgraded system decoded typed sentences with 61% average word accuracy and used data from nine volunteers.
- On Monday, Meta unveiled Brain2Qwerty v2, an AI-powered system that translates brain activity into text without surgical implants, targeting patients with ALS and other paralyzing neurodegenerative disorders.
- Unlike invasive interfaces like Elon Musk's Neuralink, this system uses external Magnetoencephalography to read brain signals, trained on 22,000 typed sentences from nine volunteers wearing MEG scanners for roughly 10 hours.
- Brain2Qwerty achieves 61% average word accuracy, with top participants reaching 78% accuracy; by leveraging LLM, the system predicts complete sentences from noisy neural signals, far exceeding roughly 8% for previous non-invasive methods.
- Training at the Basque Center in Spain employed AI agents to optimize the decoding pipeline; researchers wrote agents were trained 'to iteratively change our code base to invent novel, better architectures.'
- Meta open-sourced the training code and dataset to accelerate neurological research, and while still experimental, researchers wrote the system offers a path to 'eventually obviate the need for neurosurgery.
16 Articles
16 Articles
Meta's non-surgical mind reading machine improves on prior projects, but still isn't great
For those who can't move their fingers to type, a brain-computer interface that can help them communicate by decoding neural activity is a lifeline. Researchers at Meta have been working on a noninvasive - no surgery required - brain-computer interface that is better than its predecessors, but still far from practically usable after more than a year of work. Meta announced the second iteration of its system designed to pick up and decode brain s…
Meta's new AI can turn your thoughts into text without a brain implant
Meta has unveiled Brain2Qwerty v2, an AI system that converts brain activity into written sentences without requiring surgery or implanted chips. While the technology is still experimental, it could one day help people who have lost the ability to speak communicate using only their thoughts.
Coverage Details
Bias Distribution
- 80% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
