# High-Precision Positioning

UI-TARS is a next-generation native graphical user interface (GUI) agent model designed to seamlessly interact with GUIs through human-like perception, reasoning, and action capabilities.

A financial table question answering model based on the LayoutLM architecture, specifically designed to extract and answer structured questions from financial tables.

UGround is a powerful GUI visual positioning model trained with a streamlined recipe, developed by the Ohio State University NLP Group in collaboration with Orby AI.

A UI element detection model fine-tuned from PaliGemma 3B 896-resolution weights, specializing in object detection tasks

This is an image classification model capable of recognizing five different scenes: hospital, balcony, hallway, airport, and coffee house.