OpenCUA: Open Foundations for Computer-Use Agents
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
A research prototype of a human-centered web agent
UFO³: Weaving the Digital Agent Galaxy