NormGuard adds a training-time hinge penalty on velocity norm inflation in flow-matching RL to improve MLLM-judged image quality and forensic realism while preserving reward across multiple setups.
Rewardsharpness-awarefine-tuningfordiffusionmodels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
NormGuard adds a training-time hinge penalty on velocity norm inflation in flow-matching RL to improve MLLM-judged image quality and forensic realism while preserving reward across multiple setups.