نسخة أولية وصول مفتوح
MEND: RL For Flow Models via Proximal Velocity Matching
Reward post-training of flow models either reweights the model's own samples under a KL penalty or a frozen reference, often for thousands of updates, or backpropagates the reward and moves every sample without checking that the move is worth its size. We introduce MEND, a reinforcement learning method built on proxima …