AI RESEARCH
AdaZoom-GUI: Adaptive Zoom-based GUI Grounding with Instruction Refinement
arXiv CS.CV
•
ArXi:2603.17441v1 Announce Type: new GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural language instructions. However, grounding on GUI screenshots remains challenging due to high-resolution images, small UI elements, and ambiguous user instructions. In this work, we propose AdaZoom-GUI, an adaptive zoom-based GUI grounding framework that improves both localization accuracy and instruction understanding. Our approach