VisionTasker - Mobile Task Automation Using Vision-Based UI Understanding and LLM Task Planning
Association for Computing Machinery (ACM) via YouTube
Overview
Watch a 12-minute conference talk from the 37th Annual ACM Symposium on User Interface Software and Technology (UIST 2024) exploring an innovative approach to mobile task automation that combines vision-based UI understanding with LLM task planning capabilities to streamline and enhance user interactions on mobile devices.
Syllabus
VisionTasker: Mobile Task Automation Using Vision Based UI Understanding and LLM Task Planning
Taught by
ACM SIGCHI