Brain2Qwerty v2: Meta releases new surgery-free method for decoding text from brain waves
Original title:From Brain Waves to Words: Brain2Qwerty Offers a New Path to Communication Without Surgery
AI summary
Meta released Brain2Qwerty v2, an end-to-end AI pipeline that decodes sentences in real time from non-invasive brain recordings without surgical implants, achieving 61% word accuracy and 78% for the best participant, far above the 8% level of other non-invasive methods. The research trained on 10 hours of MEG data from each of 9 volunteers; Meta has open-sourced the full training code for v1 and v2, and partner BCBL released the v1 dataset.
Key Takeaways
- Meta released Brain2Qwerty v2,an end-to-end AI pipeline that decodes sentences in real time from…
- The research trained on 10 hours of MEG data from each of 9 volunteers
- Meta has open-sourced the full training code for v1 and v2,and partner BCBL released the v1 dataset.
Quick Facts
- Published
- Updated
- Source
- Meta AI:Blog(网页)
- Category
- Papers & Research
- AI score
- 70
Meta 的 Brain2Qwerty 展示了不用开颅就能把脑电波转成文字,对渐冻症患者和未来人机交互来说是个重要信号,但离产品化还有距离。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Brain2Qwerty v2: Meta releases new surgery-free method for decoding text from brain waves. June 29, 2026. https://new.nat6.net/en/news/cms3dp55g0ak3ro3f690yownt/