#artificial intelligence
May 2026
Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
EBM-RL (Eye--Brain--Mouth Reinforcement Learning), a decoupled GRPO-based framework that separates observation (), reasoning (), and utterance generation, mimics the human See-Think-Speak process, enabling the model to ground dialogue in visual perception before reasoning and response generation.
Miaosen Wang, Yu-Ling Shi, Yijiang Li et al.
· arXiv.org · 0 citations