@article{sparsevlmvisualtokensparsificationfor,
  title = {SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference},
  author = {Yuan Zhang and Chun-Kai Fan and Junpeng Ma and Wenzhao Zheng and Tao Huang and Kuan Cheng and Denis Gudovskiy and Tomoyuki Okuno and Yohei Nakata and Kurt Keutzer and Shanghang Zhang},
  year = {2024},
  eprint = {2410.04417},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.04417v2},
}