🏢 ByteDance Seed, Tsinghua University
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
·4964 words·24 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Multimodal Learning
Human-AI Interaction
🏢 ByteDance Seed, Tsinghua University
UI-TARS, a novel native GUI agent, achieves state-of-the-art performance by solely using screenshots as input, eliminating the need for complex agent frameworks and expert-designed workflows.