Variation-aware Vision Token Dropping for Faster Large Vision-Language Models

@misc{chen2025variationawarevisiontoken,
      title={Variation-aware Vision Token Dropping for Faster Large Vision-Language Models},
      author={Junjie Chen and Zichen Wen and Siteng Huang and Honggang Chen and Xuyang Liu and Yiyu Wang},
      year={2025},
      eprint={2509.01552},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2509.01552},
}