10 papers
EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment
ZiAn Wang, Ruiqi Liu, Zhengbo Zhang +10
Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality Assessment: given an image an…
ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration
Yuchen Bao, Chao Wen, Haowei Wang +10
Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity. Existing m…
LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals
Haozhen Yan, Ruoxin Chen, Jiahui Zhan +6
Modern generators faithfully model macroscopic semantics, producing synthetic images that appear highly realistic. Consequently, decisive forensic cues reside in subtle non-semanti…
Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models
Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen +8
Multimodal large language models (MLLMs) have been increasingly adopted in forensics for their robust semantic understanding. As AI-generated images become realistic, semantic-leve…
MIRROR: Manifold Ideal Reference ReconstructOR for Generalizable AI-Generated Image Detection
Ruiqi Liu, Manni Cui, Ziheng Qin +12
High-fidelity generative models have narrowed the perceptual gap between synthetic and real images, posing serious threats to media security. Most existing AI-generated image (AIGI…
Align, Don't Blend: Orthogonal Supervision Disentanglement As the Key to Generalizable AI-Generated Image Detection
Ruoxin Chen, Jiahui Gao, Kaiqing Lin +5
Recent advances in AI-Generated Image (AIGI) detection have largely focused on model architectures, loss design, and training strategies, while overlooking a more fundamental facto…
Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection
Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen +7
Detecting AI-generated images with multimodal large language models (MLLMs) has gained increasing attention, due to their rich world knowledge, common-sense reasoning, and potentia…
Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
Ruoxin Chen, Junwei Xi, Zhiyuan Yan +8
Existing detectors are often trained on biased datasets, leading to the possibility of overfitting on non-causal image attributes that are spuriously correlated with real/synthetic…
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
Zheng Yang, Ruoxin Chen, Zhiyuan Yan +8
The exponential growth of AI-generated images (AIGIs) underscores the urgent need for robust and generalizable detection methods. In this paper, we establish two key principles for…
Decoupled Data Augmentation for Improving Image Classification
Ruoxin Chen, Zhe Wang, Ke-Yue Zhang +5
Recent advancements in image mixing and generative data augmentation have shown promise in enhancing image classification. However, these techniques face the challenge of balancing…