Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published Sep 27 • 34
Running Featured 87 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems 📝 87 Who needs 1T parameters? Olympiad proofs with a 4B model
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning Paper • 2602.01058 • Published Feb 1 • 45