Visual sensitivity is not claim retractability: persistence-aware credit assignment for multimodal reinforcement learning
Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies to rely on visual evidence. Yet relying on the image does not guarantee that visual claims are supported by it. Before RL training, 27.81% of the corre...
Zhong-An Bi, Ke-Peng Lin, Xuan-Ang Gao et al.
· 0 citations