EmoReward校准情感视频生成奖励
一篇新论文提出EmoReward,这是一种自进化强化学习机制,可从奖励轨迹中估计情感线索的可靠性,并据此校准多种奖励权重。作者称,该方法在HunyuanVideo 1.5上的多个强化学习算法中取得改进,并在SD 3.5和FLUX的消融与迁移实验中提供支持。该论文于2026年11月4日提交至arXiv。
EmoReward为生成模型训练如何对齐主观情感意图提供了一种具体方案,无需继续依赖固定奖励权重。
Computer Science > Computer Vision and Pattern Recognition
arXiv:2611.06518 (cs)
[Submitted on 4 Nov 2026]
Title:EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL
Authors:Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu, Yunyang Ge, Sihui Ji, Yunlong Lin, Kaihang Pan, Hongru Yan, Sixiang Chen, Dianyi Wang, Julian Zhang, Weijie Kong, Changlin Li, Lanqing Guo, Zhao Zhong, Qifeng Chen, Harry Yang
View a PDF of the paper titled EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL, by Mingzhe Zheng and 21 other authors
#EmoReward#Group Relative Policy Optimization#SAGE-GRPO#HunyuanVideo 1.5#SD 3.5#FLUX