collaborators

6 papers

cs.CL2026

Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization

Yurui Pan, Ke Xu, Bo Peng

Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scal…

cs.CV2026

Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection

Wenbing Zhu, Jianing Liang, Linjie Cheng +7

Industrial Anomaly Detection (IAD) is critical for quality control, but existing methods struggle with subtle, geometric defects. Standard 2D (RGB) images are sensitive to texture…

cs.CV2026

Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era

Wenbing Zhu, Chengjie Wang, Bin-Bin Gao +12

Industrial Anomaly Detection (IAD) is a cornerstone for ensuring operational safety, maintaining product quality, and optimizing manufacturing efficiency. However, the advancement…

cs.CV2025

Pro-AD: Learning Comprehensive Prototypes with Prototype-based Constraint for Multi-class Unsupervised Anomaly Detection

Ziqing Zhou, Yurui Pan, Lidong Wang +4

Prototype-based reconstruction methods for unsupervised anomaly detection utilize a limited set of learnable prototypes which only aggregates insufficient normal information, resul…

cs.CV2025

Real-IAD D3: A Real-World 2D/Pseudo-3D/3D Dataset for Industrial Anomaly Detection

Wenbing Zhu, Lidong Wang, Ziqing Zhou +14

The increasing complexity of industrial anomaly detection (IAD) has positioned multimodal detection methods as a focal area of machine vision research. However, dedicated multimoda…

cs.CV2025

PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness

Yurui Pan, Lidong Wang, Yuchao Chen +3

In industrial anomaly detection (IAD), accurately identifying defects amidst diverse anomalies and under varying imaging conditions remains a significant challenge. Traditional app…