AK· @_akhaliq · X·· 2 小时前AI 评分24
AI 导读
Adaptive Reward Routing 通过前向过程 RL 实现音视频联合扩散的动态多奖励优化 paper: https://huggingface.co/papers/2609.37200
正文
Adaptive Reward Routing
Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
paper: https://huggingface.co/papers/2609.37200
来源：AK · x.com