🧵6/7
🧵6/7
It achieves ~20% character-error-rate (CER) on the best individuals. That’s a huge leap from EEG-based methods (67% CER)!
🧵4/7
It achieves ~20% character-error-rate (CER) on the best individuals. That’s a huge leap from EEG-based methods (67% CER)!
🧵4/7
Our paper from AI at Meta and @bcbl.bsky.social presents Brain2Qwerty, an AI model that decodes text from non-invasive recordings of the brain.
Below a detailed thread 🧵1/7
Our paper from AI at Meta and @bcbl.bsky.social presents Brain2Qwerty, an AI model that decodes text from non-invasive recordings of the brain.
Below a detailed thread 🧵1/7