@ohmoussa2

Neurosci x AI PhD Student @mpi_sws_, supervised by @mtoneva1; CS@MaxPlanck -- ML and CogNeurosci Enthusiast -- Computer Engineering @AUC.

Joined October 2024
  • Tweets46
  • Following266
  • Followers102
16Media
🚨 Super excited to share our latest work: RABBiT: a foundation model for speech- and language-evoked brain activity.** 🧠🎧 W/ @mtoneva1 One model enables: ✅ accurate zero-shot brain prediction ✅ efficient few-shot adaptation with only 5-10 mins of subject data ✅ convenient in silico neuroscience experiments and it’s so lightweight that it enables real-time, in-browser inference (feel free to try for yourself!) Website: bridge-ai-neuro.github.io/ra… Here's the story. 🧵👇
2
5
3
24
2,685
Very happy to announce that RABBiT has been accepted at @NeurIPSConf, excited to present it at Sydney this year 🎉! We are also presenting this work at @SNLmtg tomorrow. If you are in Geneva, please drop by poster E58 at the 11am session tomorrow or feel free to reach out anytime! Looking forward to the feedback and discussions :")!
Omer Moussa
@ohmoussa2Sep 28
🚨 Super excited to share our latest work: RABBiT: a foundation model for speech- and language-evoked brain activity.** 🧠🎧 W/ @mtoneva1 One model enables: ✅ accurate zero-shot brain prediction ✅ efficient few-shot adaptation with only 5-10 mins of subject data ✅ convenient in silico neuroscience experiments and it’s so lightweight that it enables real-time, in-browser inference (feel free to try for yourself!) Website: bridge-ai-neuro.github.io/ra… Here's the story. 🧵👇
1
2
11
472
Replying to @ohmoussa2 @mtoneva1
12/ Third, Shared–Idiosyncratic Decomposition (SID) captures what responses share and how individuals differ. It gives us a population starting point, then lets us adapt only the small idiosyncratic heads. During few-shot adaptation, these idiosyncratic heads are the only part tuned in the model.
1
1
86
13/ We're making everything public. 📄 Paper: arxiv.org/abs/2607.05171 🌐 Interactive website + demos: bridge-ai-neuro.github.io/ra… 💻 Code: github.com/bridge-ai-neuro/r… We would love to hear from you after trying it! Huge thanks to @mtoneva1 for making this work possible.

RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning...

Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computational models that generalize across both....

arxiv.org
56
Omer Moussa retweeted
Mariya Toneva@mtoneva1Sep 24
🚨 Two open postdoc positions in the ERC-funded project BrainAlign at the Max Planck Institute in Saarbruecken, Germany: position #1 on NeuroAI: postdocprogram.mpg.de/node/5… position #2 on human-centered LLM evaluations: postdocprogram.mpg.de/node/5… Application deadline: Oct 13, 2026
1
37
104
6,504
Omer Moussa retweeted
Michael Hahn@mhahn29Apr 2
We have 1-2 more extra spots due to new funding -- apply by end of April!
Michael Hahn@mhahn2921 Nov 2025
We’re hiring PhD students and postdocs on LLM theory and interpretability! Topics: 1️⃣ abilities & limitations of transformers and other architectures; 2️⃣ LLM interpretability; 3️⃣ foundations of LLM reasoning; 4️⃣ foundations of AI safety.
5
31
161
28,770
Omer Moussa retweeted
Micha Heilbron@m_heilbMar 30
Interested in pursuing a PhD in NLP/cog-sci? Studying language learning in LMs from the perspective of human language acquisition? Check out this position -- few more days to apply!! (plz RT!) ⬇️⬇️⬇️
Micha Heilbron@m_heilbMar 10
📢 PhD position in Developmental Language Modelling (plz RT🙏) What can human language acquisition teach us about training language models? Join us as a PhD! 4 yrs, fully funded, MPI-NL; april 3 mpi.nl/career-education/vaca…
2
19
71
9,793
Omer Moussa retweeted
Micha Heilbron@m_heilbMar 10
📢 PhD position in Developmental Language Modelling (plz RT🙏) What can human language acquisition teach us about training language models? Join us as a PhD! 4 yrs, fully funded, MPI-NL; april 3 mpi.nl/career-education/vaca…
3
29
2
106
19,937
Load more