@misc{gou2024navigating, title={Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents}, author={Boyu Gou and Ruohan Wang and Boyuan Zheng and Yanan Xie and Cheng Chang and Yiheng Shu and Huan Sun and Yu Su}, year={2024}, eprint={2410.05243}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2410.05243} }