@misc{you2024ferret,
  title={Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs},
  author={Keen You and Haotian Zhang and Eldon Schoop and Floris Weers and Amanda Swearngin and Jeffrey Nichols and Yinfei Yang and Zhe Gan},
  year={2024},
  eprint={2404.05719},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2404.05719}
}