@article{hiprunehierarchicalattentionforefficient, title = {HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models}, author = {Jizhihui Liu and Feiyi Du and Guangdao Zhu and Niu Lian and Jun Li and Bin Chen and Weili Guan and Yaowei Wang}, year = {2025}, eprint = {2508.00553}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.00553}, }