Hao Wu, Yingqi Fan, Jinyang Dai, Junlong Tong, Yunpu Ma, Xiaoyu Shen

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early …

arXiv:2602.23699v1 Announce Type: cross Abstract: The quadratic computational cost of processing vision tokens in Multimodal Large Language Models (MLLMs) hinders their widespread adoption. While progressive …