Реклама

VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation

#VA-Judger #Reward #Modeling #Human #Preference

arXiv:2608.18607v1 Announce Type: new Abstract: Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual quality dimensions, including audio quality, visual fidelity, and…