Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
Referring, grounding, and reasoning capabilities for understanding mobile user interfaces.
BibTeX citation
@inproceedings{ferretui2024,
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},
booktitle = {ECCV},
year = {2024},
url = {https://arxiv.org/abs/2404.05719}
}