1
RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs
多模态大模型提速新思路：按角色分区裁剪视觉token，兼顾效率与精度
arXiv:2608.07088v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) encode images as long visual token sequences, making prefil…