@misc{cai2024llava,
  title={LLaVA-KD: A Framework of Distilling Multimodal Large Language Models},
  author={Yuxuan Cai and Jiangning Zhang and Haoyang He and Xinwei He and Ao Tong and Zhenye Gan and Chengjie Wang and Xiang Bai},
  year={2024},
  eprint={2410.16236},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2410.16236}
}