Brains and computers @ murtylab
Past -> runwayml, Aleph-Alpha
Research:
- TopoNets - Brain-like topographic structure in vision & language models (ICLR 2025 Spotlight)
- AtMan - Memory efficient explainability method for transformers (NeurIPS 2023 + featured in Scientific American, TED-AI Vienna)
- DORA - Cluster and explore outlier neurons in vision models (TMLR, ICLR trustworthy ML workshop)
Contact: Telegram or email: [email protected]