Abstract: Graphical User Interface (GUI) based testing is a commonly used practice in industry. Although valuable and, in many cases, necessary, it is associated with challenges such as high cost and ...
GUICourse is a group of complete datasets to train visual-based GUI agents from general VLMs, through improving VLMs' fundamental abilities and GUI knowledge. GUICourse is composed of three datasets: ...
MobiZen-GUI is an extensible mobile automation framework that uses vision-language models to control Android devices through natural language instructions. The name combines "Mobile" and "Zen" (禅), ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results