Research
Hugging Face Papers research proposes a persistent AI research team for discovering linear attention architectures
A team of persistent AI researchers, each grounded in a different discipline and keeping private histories, reportedly outperforms GDN2 at 1.3B scale on language modeling and retrieval tasks.
Every outlet that ran it 1 article
Hugging Face PapersResearchLead
Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures