VAttnPO: Visual Attention-Guided Policy Optimization
Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal distinguishes overall response quality but leaves changes in visual-evidence use across generated tokens implicit. We introduce VAttnPO (Visual Attention-Guided Policy Optim...
Li-Hao Zheng, Zhen-Wei Shao, Zhou Yu et al.
· 0 citations