Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher Paper • 2608.26872 • Published 4 days ago • 69
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation Paper • 2605.25378 • Published May 25 • 62
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Paper • 2602.06422 • Published Feb 6 • 47