@misc{zong2024mova,
  title={MoVA: Adapting Mixture of Vision Experts to Multimodal Context},
  author={Zhuofan Zong and Bingqi Ma and Dazhong Shen and Guanglu Song and Hao Shao and Dongzhi Jiang and Hongsheng Li and Yu Liu},
  year={2024},
  eprint={2404.13046},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2404.13046}
}