notesum.ai

Published at December 5

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

cs.CL

Released Date: December 5, 2024

Authors: Yiheng Xu1, Zekun Wang1, Junli Wang1, Dunjie Lu1, Tianbao Xie1, Amrita Saha2, Doyen Sahoo2, Tao Yu1, Caiming Xiong2

Aff.: 1University of Hong Kong; 2Salesforce Research

Arxiv: http://arxiv.org/pdf/2412.04454v1