daVinci-LLM: Advancing AI Pretraining Science Openly
Explore daVinci-LLM's open approach to AI pretraining, combining industrial-scale resources and research freedom to enhance model capabilities.
MediHive: Decentralized AI for Advanced Medical Reasoning
Discover MediHive, a decentralized multi-agent AI system enhancing medical reasoning with autonomous roles and iterative consensus for accurate healthcare...
Why Semantic Memory Systems Inevitably Forget Info
Discover why semantic memory systems in AI face forgetting and interference, revealing the tradeoffs in memory retrieval and accuracy.
Asymmetric Effects of Multi-Agent Feedback in Logic Tutoring
Explore how multi-agent feedback impacts learning in logic proof tutoring and the challenges posed by complexity and verification accuracy.
FormalProofBench: AI Models Creating Verified Graduate Math Proofs
Explore FormalProofBench, a benchmark testing AI models' ability to generate formally verified graduate-level math proofs using Lean 4.