UI-TARS 72B is an open-source multimodal AI model designed specifically for automating browser and desktop tasks through visual interaction and control. The model is built with a specialized vision architecture enabling accurate interpretation and manipulation of on-screen visual data. It supports automation tasks within web browsers as well as desktop applications, including Microsoft Office and VS Code.
Core capabilities include intelligent screen detection, predictive action modeling, and efficient handling of repetitive interactions. UI-TARS employs supervised fine-tuning (SFT) tailored explicitly for computer control scenarios. It can be deployed locally or accessed via Hugging Face for demonstration purposes. Intended use cases encompass workflow automation, task scripting, and interactive desktop control applications.
Modalities
Context
33K
Released
Mar 26, 2025
Knowledge Cutoff
Jan 2025
Token volume and request traffic to this model over time.
UI-TARS 72B is an open-source multimodal AI model designed specifically for automating browser and desktop tasks through visual interaction and control. The model is built with a specialized vision architecture enabling accurate interpretation and manipulation of on-screen visual data.
UI-TARS 72B has a 32,768 token context window.
UI-TARS 72B accepts text and images as input and returns text.
UI-TARS 72B was released on March 26, 2025. Its knowledge cutoff is January 31, 2025.