← Search

Qiao Qin

2 accepted papers

2026

CausalCLIP: Causally-Informed Feature Disentanglement and Filtering for Generalizable Detection of Generated Images

AAAI 2026technical

The rapid advancement of generative models has increased the demand for generated image detectors capable of generalizing across diverse and evolving generation techniques. However, existing methods, including those leveraging pre-trained vision-language models, often produce highly entangled repres

Cited by 4SourcePDFScholar
2026

Diversity over Uniformity: Rethinking Representation in Generated Image Detection

CVPR 2026

With the rapid advancement of generative models, generated image detection has become an important task in visual forensics. Although existing methods have achieved remarkable progress, they often rely, after training, on only a small subset of highly salient forgery cues, which limits their ability

Cited by 0SourcecodeScholar