GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models
Industrial inspection requires more than binary anomaly detection: a practical system should determine whether an anomaly exists, localize the defective region, identify the defect type, and provide interpretable visual evidence. Existing CLIP-based methods detect and localize anomalies well but offer limited language-level defect understanding, while instruction-tuned vision-language models can describe defects but do not natively produce pixel-level masks. We introduce GenAU, a Generalist vision-language framework for industrial Anomaly Understanding that unifies image-level detection, pixel
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownvlm-starter →
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “GenAU: Language-Grounded Industrial Anomaly Understanding wi” ≈ “VioletVision-3B””
- LinkedLinked via arxiv author · 85%Hongkuan Zhou →
“GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models”
- LinkedLinked via arxiv author · 85%Tristan Rehm →
“GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models”
- LinkedLinked via arxiv author · 85%Nadeem Nazer →
“GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models”
- LinkedLinked via arxiv author · 85%Lavdim Halilaj →
“GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models”
- LinkedLinked via arxiv author · 85%Jingcheng Wu →
“GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models”