Hugging Face Daily Papers·· 2026-10-12AI score24
SyncReward: A Human-Aligned Synchronization Reward Model for Audio-Video Generation
SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation
AI briefing
The research team proposes SyncReward, a reward model for evaluating and optimizing synchronization in audio-video generation, and releases the SyncReward-Data-80K dataset with 80K professional synchronization ratings and the SyncReward-Bench benchmark of 1K clips. The model achieves the highest agreement with human ratings in evaluations and can improve generation synchronization through inference-time best-of-N selection and reinforcement learning post-training. Data, benchmark, model and code will be open-sourced.
Open original arxiv.org