Sungik Choi

Researcher, LG AI Research

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Training-free Detection of AI-generated images via Cropping Robustness

#1105 · Sungik Choi, Hankook Lee, Moontae Lee

Self-supervised models learn robust representation of real images under cropping and resizing, which can be applied to detect AI-generated images without training.