Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)
-
Updated
Jun 29, 2026 - JavaScript
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)
Android Mobile GUI Agent plugin for DeepSeek Harness with ADB control, iterative verification, approvals, and a Web mobile view
Code for CaptchaArena: a live dataset server for 20 interactive CAPTCHA types, a screenshot-only computer-use agent, and tools for browsing the 50K-puzzle dataset and agent trajectories.
To associate your repository with the gui-agent topic, visit your repo's landing page and select "manage topics."