Post
2373
Introducing GUICourse! π
By leveraging extensive OCR pretraining with grounding ability, we unlock the potential of parsing-free methods for GUIAgent.
π Paper: ( GUICourse: From General Vision Language Models to Versatile GUI Agents (2406.11317))
π Github Repo: (https://github.com/yiye3/GUICourse)
π Dataset: ( yiye2023/GUIAct) / ( yiye2023/GUIChat) / ( yiye2023/GUIEnv)
π― Model: ( RhapsodyAI/minicpm-guidance) / ( RhapsodyAI/qwen_vl_guidance)
By leveraging extensive OCR pretraining with grounding ability, we unlock the potential of parsing-free methods for GUIAgent.
π Paper: ( GUICourse: From General Vision Language Models to Versatile GUI Agents (2406.11317))
π Github Repo: (https://github.com/yiye3/GUICourse)
π Dataset: ( yiye2023/GUIAct) / ( yiye2023/GUIChat) / ( yiye2023/GUIEnv)
π― Model: ( RhapsodyAI/minicpm-guidance) / ( RhapsodyAI/qwen_vl_guidance)
