justin-xzliu/GLIM

Official PyTorch implementation of research papaer "Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation".

33
/ 100
Emerging

This project helps neuroscientists and cognitive researchers translate raw electroencephalogram (EEG) signals directly into coherent, semantically faithful text. You input EEG recordings from subjects reading or processing information, and it outputs natural language sentences that summarize the core meaning of their brain activity. It's designed for researchers exploring brain decoding and brain-computer interfaces.

No commits in the last 6 months.

Use this if you need to reliably generate descriptive text from EEG data, specifically to understand the semantic content of brain activity without concerns about text 'hallucinations'.

Not ideal if your primary goal is verbatim reconstruction of stimulus texts or if you are not working with EEG data for language processing.

neuroscience EEG-decoding brain-computer-interface cognitive-science natural-language-generation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Jupyter Notebook

License

Last pushed

Jun 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/justin-xzliu/GLIM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.