Zoom-In to Sort AI-Generated Images Out

Yikun Ji; Yan Hong; Bowen Deng; jun lan; Huijia Zhu; Weiqiang Wang; Liqing Zhang; Jianfu Zhang

Zoom-In to Sort AI-Generated Images Out

Yikun Ji, Yan Hong, Bowen Deng, jun lan, Huijia Zhu, Weiqiang Wang, Liqing Zhang, Jianfu Zhang

15 Sept 2025 (modified: 14 Nov 2025)ICLR 2026 Conference Withdrawn SubmissionEveryoneRevisionsBibTeXCC BY 4.0

Keywords: Image & Video Synthesis, Multi-modal Large Language Models

TL;DR: We fine-tune VLMs to identify key regions on potentially AI-generated images that, upon closer observation, can yield a more grounded, explainable and accurate classification result..

Abstract: na

Primary Area: foundation or frontier models, including LLMs

Submission Number: 6032

Loading