3 papers
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
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.CV2025
CAD: A General Multimodal Framework for Video Deepfake Detection via Cross-Modal Alignment and Distillation
Yuxuan Du, Zhendong Wang, Yuhao Luo +4
The rapid emergence of multimodal deepfakes (visual and auditory content are manipulated in concert) undermines the reliability of existing detectors that rely solely on modality-s…