view article Article Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries +7 4 days ago • 43
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published about 1 month ago • 216 • 9
Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training Paper • 2602.05933 • Published Feb 5 • 5
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning Paper • 2602.01058 • Published Feb 1 • 41