@misc{zhu2024focusllava,
  title={FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression},
  author={Yuke Zhu and Chi Xie and Shuang Liang and Bo Zheng and Sheng Guo},
  year={2024},
  eprint={2411.14228},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2411.14228}
}