PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models
Effective multimodal reasoning requires a model to reliably utilize visual information while sufficiently exploring diverse reasoning paths. To achieve this goal, prior work combines visual dependency and token entropy to reshape sequence-level advantages, but scaling the contribution of token entropy by visual depende...
Jun-Xin Wang, Ying-Feng Luo, Xiang-Chen Song et al.
· 0 citations