Open source our work TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials; https://github.com/TongUI-agent/TongUI-agent
🔄 In a Training Loop
Bofei Zhang
Bofeee5675
AI & ML interests
Vision Language Model & Agentic Task & Computer-Use
Organizations
datasets 11
Bofeee5675/GUI-Net-Video
Viewer • Updated • 50 • 806
Bofeee5675/OSWorld-verfied-files
Updated • 133
Bofeee5675/Pix2Fact100Subset
Viewer • Updated • 100 • 74 • 1
Bofeee5675/GUI-Net-1M-extended
Updated • 2.25k
Bofeee5675/GUI-Net-1M-absolute-annotations
Viewer • Updated • 588k • 333 • 2
Bofeee5675/GUI-Net-1M-relative-annotations
Viewer • Updated • 580k • 587
Bofeee5675/GUI-Net-Benchmark
Preview • Updated • 33 • 2
Bofeee5675/GUI-Net-Crawler
Updated • 89 • 2
Bofeee5675/GUI-Net-1M
Viewer • Updated • 895k • 2.27k • 18
Bofeee5675/GUI-Net-Nano
Viewer • Updated • 4.52k • 39 • 2