Mobile UI

Mobile UI research focuses on improving the understanding and interaction with mobile device interfaces, primarily aiming to enhance accessibility, automation, and design. Current efforts leverage multimodal large language models (LLMs) and computer vision techniques, often incorporating architectures like Mixture of Experts (MoE) and employing methods such as visual saliency analysis and UI grammar to improve model accuracy and explainability. This research is significant for advancing both the usability of mobile applications for diverse users and the efficiency of mobile app development, particularly in areas like automated testing and accessibility assessment.

Papers