[논문리뷰] Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL본 논문은 Joint audio-video diffusion models의 multi-reward guided reinforcement learning (RL) 과정에서 발생하는 dynamic multi-reward optimization의 도전 과제를 해결하고자 합니다.#Review#Multi-reward Optimization#Diffusion Models#Reinforcement Learning#Audio-Video Generation#Adaptive Routing#Cross-Modal Influence#Preference-Preserving Reweighting2026년 10월 1일댓글 수 로딩 중