8 papers
SaTPO: Text-to-Image Safety Alignment via Transition Preference Optimization
Ziyi Fang, Jingzhi Li, Xiaojun Jia +3
Safety alignment of text-to-image diffusion models aims to suppress harmful content without compromising useful generation capabilities. However, preferences over completed images…
RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection
Chao Huang, Pengfei Wei, Benfeng Wang +5
Intermediate-layer features from multimodal large language models have shown strong potential for video anomaly detection (VAD), yet the origin of their discriminative power remain…
Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection
Chao Huang, Pengfei Wei, Kaige Li +4
Multimodal Large Language Models (MLLMs) provide a natural way to make video anomaly detection more explainable. However, their final decisions do not always fully use the discrimi…
Multi-tier Differential Private Query Release
Shaowei Wang, Jinn Li, Yun Peng +5
Answering statistical queries over sensitive data under differential privacy (DP) is a common task in many settings, including databases, mobile computing, and data markets. In the…
SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
Chao Huang, Pengfei Wei, Penfei Wei +6
Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos. Existing methods universally depend on large…
Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning
Peng Chen, Chao Huang, Yunkang Cao +7
Industrial anomaly detection demands precise reasoning over fine-grained defect patterns. However, existing multimodal large language models (MLLMs), pretrained on general-domain d…
Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method
Chao Huang, Benfeng Wang, Wei Wang +5
Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in t…
FaceInsight: A Multimodal Large Language Model for Face Perception
Jingzhi Li, Changjiang Luo, Ruoyu Chen +4
Recent advances in multimodal large language models (MLLMs) have demonstrated strong capabilities in understanding general visual content. However, these general-domain MLLMs perfo…