[2025-2] 백승우 - UI-TARS: Pioneering Automated GUI Interaction with Native Agents

UI-TARS: Pioneering Automated GUI Interaction with Native Agents

This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e.g., keyboard and mouse operations). Unlike prevailing agent frameworks that depend on heavily wrapped commercial

arxiv.org

'Multi-Modal' 카테고리의 다른 글

[2025-1] 백승우 - GUI Agent by Script-based Automation (0)	2025.07.04
[2025-1]박제우 - Scaling Language-Image Pre-training via Masking (1)	2025.05.17
[2025-1] 박제우 - CLIP : Learning Transferable Visual Models From Natural Language Supervision (1)	2025.05.06
[2025-1] 유경석 - Bag of Tricks for Developing Diabetic Retinopathy Analysis Framework to Overcome Data Scarcity (0)	2025.05.02
[2025-1] 유경석 - PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering (0)	2025.04.05

[2025-2] 백승우 - UI-TARS: Pioneering Automated GUI Interaction with Native Agents

'Multi-Modal' 카테고리의 다른 글

관련글

티스토리툴바