Post-Trained MoE Can Skip Half Experts via Self-Distillation Paper • 2605.18643 • Published 4 days ago • 29
Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published 9 days ago • 154
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Paper • 2604.13016 • Published Apr 14 • 105