metaresearch/PapersRAG-1.5B
Text Generation • 2B • Updated • 771 • • 2
None defined yet.
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
Distilling LLM Feedback for Lean Theorem Proving
Through new experiences in Meta AI, and enhanced capabilities in Llama 4, we're creating the next generation of AI to help you discover new possibilities and expand your world.