Sign in

Ebrahim Feghhi

@ebrahimfeghhi.bsky.social
11 followers 12 following 15 posts
PostsRepliesMedia
Ebrahim Feghhi @ebrahimfeghhi.bsky.social · 17/03/2026
Excited to introduce LightBeam, a CTC decoder for speech neuroprostheses that drastically cuts memory load while achieving state-of-the art (SOTA) results Paper: arxiv.org/abs/2603.14002 Code: github.com/ebrahimfeghh... Co-authors: @who-is-lionel.bsky.social, @nrhadidi.bsky.social, Jonathan Kao.
arxiv.org
LightBeam: An Accurate and Memory-Efficient CTC Decoder for Speech Neuroprostheses
A promising pathway for restoring communication in patients with dysarthria and anarthria is speech neuroprostheses, which directly decode speech from cortical neural activity. Two benchmarks, Brain-t...
010
Ebrahim Feghhi @ebrahimfeghhi.bsky.social · 13/02/2026
Our result that OASM, a trivial model of temporal autocorrelation, achieves higher neural predictivity than GPT2-XL on the Pereira2018 dataset has been replicated thanks to @kartikpradeepan.bsky.social! Interested if @mschrimpf.bsky.social thinks this changes conclusions from Schrimpf et al., 2021.
150
Reposted by Ebrahim Feghhi
Dan Goodman @neural-reckoning.org · 11/02/2026
This post has generated a super interesting debate between the authors of the paper @ebrahimfeghhi.bsky.social @nrhadidi.bsky.social and one of the authors of a paper they criticised @mschrimpf.bsky.social including an attempted reproduction of their results. This is such a great use of social media
3166
Reposted by Ebrahim Feghhi
Dan Goodman @neural-reckoning.org · 09/02/2026
This paper shows alignment between LLMs and brain data is outperformed by a null model. More evidence for the argument I've been making in talks lately that we shouldn't believe any computational paper that puts less effort into null than main model. www.biorxiv.org/content/10.1...
biorxiv.org
26610