collaborators
Showing cs.CVShow all

16 papers · 1 filter

cs.CV2026

AgentFoX: LLM Agent-Guided Fusion with eXplainability for AI-Generated Image Detection

Yangxin Yu, Yue Zhou, Bin Li +4

The realism of AI-generated images (AIGI) poses increasing challenges for reliable forensic detection, where heterogeneous expert detectors may produce conflicting predictions acro…

cs.CV2026

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…

cs.CV2026

FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection

Leqi Zhu, Junyan Ye, Kaiqing Lin +3

The development of generative artificial intelligence technologies has propelled the visual realism of synthetic images to an unprecedented level. Although current interpretable de…

cs.CV2026

Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models

Yue Zhou, Xinan He, Kaiqing Lin +3

While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse in realistic, in-th…

cs.CV2026

Towards Policy-Adaptive Image Guardrail: Benchmark and Method

Caiyong Piao, Zhiyuan Yan, Haoming Xu +4

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolvi…

cs.CV2026

Unified Multimodal Models as Auto-Encoders

Zhiyuan Yan, Kaiqing Lin, Zongjian Li +10

Image-to-text (I2T) understanding and text-to-image (T2I) generation are two fundamental, important yet traditionally isolated multimodal tasks. Despite their intrinsic connection,…