RAVE: Re-Allocating Visual Attention in Large Multimodal Models 文章

ArXiv CS.CV2026-05-27NEWSen作者: Xi Leng, Xinhong Ma, Ziqiang Dong, Feng Zhang, Xiaoying Tang, Yang Yang, Guanjun Jiang
查看原文 →
关系图谱

RAVE: Re-Allocating Visual Attention in Large Multimodal Models · 相关技术

相关技术

TTEODEPLA远程代码执行（RCE）多模态softmax attentionself-attentiondivide-and-conquer partitioningattentionVQATokenStanQueryParts-of-Speech (POS) tagsOCRMECLarge Multimodal ModelsLMMARGANN