3 papers
cs.CV2026
FiSeR: Fine-Grained Source Representations for Cross-Domain AI Image Detection
Shan Zhang, Yongxin He, Mingming Zhang +2
Real-world synthetic image detectors often generalize poorly under domain shift despite strong in-domain performance. Using unsupervised UMAP projections, we find that natural and…
cs.CL2025
DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
Yongxin He, Shan Zhang, Yixuan Cao +2
Detecting AI-involved text is essential for combating misinformation, plagiarism, and academic misconduct. However, AI text generation includes diverse collaborative processes (AI-…
cs.CL2024
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
Xun Guo, Shan Zhang, Yongxin He +4
Current techniques for detecting AI-generated text are largely confined to manual feature crafting and supervised binary classification paradigms. These methodologies typically lea…