HF Daily Papers
· Papers
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy. We identify a simple structural signature of this drift: across three post-training methods (NFT, AWM, DPO), RL f