Zhiyuan Yan

All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning

LitExplorer: Training-Free Diffusion Guidance with Adaptive Exploration-Filtering Framework

Unified Multimodal Model as Auto-Encoder

Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection

Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes

$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes

$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals