MVPruner: Dynamic Token Pruning for Accelerating Multi-view Vision-Language Models in Autonomous Driving
MVPruner: 用于加速自动驾驶中多视图视觉语言模型的动态令牌剪枝
机构 * School of Information Engineering, Chang’an University, China(长安大学信息工程学院) ; School of Artificial Intelligence, Shanghai Jiaotong University, China(上海交通大学人工智能学院)
AI总结 提出MVPruner,一种两阶段自适应令牌剪枝方法,通过动态分配剪枝预算和基于指令的令牌选择,在保持精度的同时大幅降低计算量,实现多视图视觉语言模型的高效推理。
Comments accepted by ECCV26