Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing 事件

Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing arXiv:2605.04733v2 Announce Type: replace Abstract: Text-based role-playing models can imitate character styles, but often fail to capture scene atmosphere and evolving tension, which are crucial for immersive applications such as VR games and interactive narratives. We study video-grounded role-playing dialogue and introduce EBM-RL (Eye--Brain--Mouth Reinforcement Learning), a decoupled GRPO-based framework that separate