Yongkang Zhang — accepted AI-conference papers

2026

VMD-FACT: A New Video Dataset and MLLM-based method for Detecting Realistic AI-Generated Video Misinformation

Yongkang Zhang, Dongyu She, Baiyu Ji, Qichuan Geng, Zhong Zhou, Yan Wang

CVPR 2026

The rapid evolution of generative AI, including such models as Sora, has intensified the threat of video misinformation. A critical challenge in detecting these AI-generated video misinformation lies in a fundamental disconnect between existing datasets and practical deception tactics. Current datas

Cited by 0 Source ↗Scholar ↗

2025

Adaptive Prompt Learning via Gaussian Outlier Synthesis for Out-of-distribution Detection

Yongkang Zhang, Dongyu She, Zhong Zhou

ICCV 2025poster

Out-of-distribution (OOD) detection aims to distinguish whether detected objects belong to known categories or not. Existing methods extract OOD samples from In-distribution (ID) data to regularize the model's decision boundaries. However, the decision boundaries are not adequately regularized becau…

Cited by 0 Source ↗PDF ↗Scholar ↗