iiinova — where your digital self keeps evolving

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 21/04/2026

New package release from our amazing team 🎉🎉🎉 Using NeuralSet, you can go from a directory of downloaded data files to analysis-ready / AI-ready tensors with only a couple of lines of code Time to power up 💪

061

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 08/04/2026

Proud to have worked jointly with @juliengadonneix.bsky.social on this new paper. Check it out!

010

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 11/08/2025

Excited to be with my team at #ccn2025 this week! I’ll be presenting part of the workshop on Thursday. Come say hi!

051

Reposted by Lucy (Mingfang) Zhang

Jarod Levy @jarodlevy.bsky.social · 26/02/2025

🔥”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

1135

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

This research was made possible by our great team @jarodlevy.bsky.social, Stéphane d'Ascoli, Jérémy Rapin, F.-Xavier Alario, Pierre Bourdillon, Svetlana Pinet, @jeanremiking.bsky.social at AI at Meta, @bcbl.bsky.social, @cnrs.fr , @psl-univ.bsky.social, and Hôpital Fondation Rothschild! 8/8

020

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Interested in efficiently decoding these brain signals? Go check out our companion AI paper: ai.meta.com/research/pub... 7/8

100

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Result 4: This dynamic code is observed for all levels of the language hierarchy. Critically, it is level-dependent: context representations “move” more slowly in brain activity than letter representations, allowing a seamless unfolding of language representations. 6/8

110

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Result 3: How does the brain avoid the interference induced by such overlapping representations? Thanks to a dynamic code! The representations of successive letters continuously move across different neural subspaces.

120

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Result 2: Paradoxically, the representations of letters last much longer than their respective corresponding actions, resulting in a representational overlap of successive letters in brain activity. 4/8

100

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Result 1: We find that, before typing each word, the brain activity is marked by a top-down sequence of representations: context-level representations can be decoded before those of words, syllables, and letters. 3/8

110

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Method: We used MEG to record the brain activity of participants while they typed sentences. Using linear decoding, we then evaluate whether the brain represents a hierarchy of linguistic features before each word is typed. 2/8

120

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

Our paper from AI at Meta and @bcbl.bsky.social is out on arxiv 🔥 “From Thought to Action: How a Hierarchy of Neural Dynamics Supports Language Production” arxiv.org/abs/2502.07429 How does the brain transform a thought into a sequence of motor actions? Results summarized in 🧵1/8

1208

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

000

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

100

Lucy (Mingfang) Zhang @lucyzmf.bsky.social · 18/02/2025

100