Anpeng Wang — accepted AI-conference papers

2026

ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoning

Kai Zhang, Zekai Zhang, Xihe Sun, Anpeng Wang, Jingmeng Nie, Qinghui Chen +3

CVPR 2026

Automatic vision inspection holds significant importance in industry inspection. While multimodal large language models (MLLMs) exhibit strong language understanding capabilities and hold promise for this task, their performance remains significantly inferior to that of human experts. In this contex

Cited by 0 Source ↗Scholar ↗

2026

Divide-and-Conquer Decoupled Network for Cross-Domain Few-Shot Segmentation

Runmin Cong, Anpeng Wang, Bin Wan, Cong Zhang, Xiaofei Zhou, Wei Zhang

AAAI 2026technical

Cross-domain few-shot segmentation (CD-FSS) aims to tackle the dual challenge of recognizing novel classes and adapting to unseen domains with limited annotations. However, encoder features often entangle domain-relevant and category-relevant information, limiting both generalization and rapid adapt

Cited by 0 Source ↗PDF ↗Scholar ↗