Interested in how the brain actually transforms the representation of a sentence into a sequence of motor action? Go check our companion Neuroscience paper:
🧵6/7

Brain2Qwerty consists of 3 modules: convolutions, transformer and character-level language model.
It achieves ~20% character-error-rate (CER) on the best individuals. That’s a huge leap from EEG-based methods (67% CER)!
🧵4/7

Here, we develop a non-invasive method to decode text from brain activity.
We recorded 35 volunteers while they typed sentences in the MEG scanner and trained Brain2Qwerty to decode their keystrokes.
🧵3/7

The past five years have been marked by a rapid progress in brain-computer-interfaces.
Electrodes implanted inside the motor cortex can now be input to an AI system to restore communication: www.nature.com/articles/s41...
However, this approach requires neurosurgery.
🧵2/7

🔥”Brain-to-Text Decoding” is now out on ArXiv: arxiv.org/abs/2502.17480
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

Join me every Monday on LinkedIn during my PhD for a series of posts exploring ideas and readings of a PhD student's life—beyond my research into neuroscience and AI. Looking forward to your thoughts!
I am taking the risk Elon!
www.linkedin.com/in/jarod-lévy-645b4214b