Reproduce “Thought-deciphering via hierarchical EEG-to-text alignment” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiaopeng Mao, Morten Mørup, Xin Xu, Sang Wan Lee, Sadasivan Puthusserypady
The hierarchical EEG-to-sentence retrieval method first predicts a broad semantic category, such as a book chapter, then ranks candidate sentences within that category. On ChineseEEG’s The Little Prince, it achieves 62.6% ± 1.0% top-5 retrieval accuracy, versus 50.3% ± 2.3% with pairwise-only alignment. This is bounded retrieval among known sentences, not free-form thought decoding or practical communication.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.