NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
NormGuard: 流匹配强化学习中保持奖励的范数约束
机构 * The Hong Kong University of Science and Technology(香港科技大学) ; Kuaishou Technology(快手科技) ; University of Chinese Academy of Sciences(中国科学院大学)
AI总结 针对流生成器强化学习后训练中感知质量下降的问题,提出NormGuard方法,通过铰链惩罚约束速度范数,在保持奖励的同时提升图像质量和真实性。
Comments v5: Fixed PDF rendering compatibility issue affecting Apple PDFKit (macOS Preview/iOS PDF viewer). No changes to technical content compared to v4