自适应奖励路由：联合音视频扩散的前向过程RL多奖励优化
原标题：Paper page - Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL
AI 摘要
该论文提出自适应奖励路由（Adaptive Reward Routing）方法，用于联合音视频扩散模型的前向过程强化学习（DiffusionNFT）。方法包含两个组件：跨模态影响引导路由，利用双向交叉注意力响应动态调整更新位置；偏好保持的模态感知重加权，在预热后以分支特定奖励梯度交互作为残差修正来协调多奖励冲突。实验表明该方法在模态质量、语义一致性和音视频同步上优于强RL基线。
正文节选
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL Abstract Multi-reward guided reinforcement learning (i.e., RL) offers a promising way to improve joint audio-video diffusion models along several complementary objectives, including modality-specific quality, cross-modal semantic alignment, and temporal synchronization. Its effectiveness, however, depends on two quantities that change during training: where reward-driven updates shou