AD-Copilot

This is the official repository for the paper:

AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison

[Paper]  |  [Model]  |  [Thinking Model]

---

News

• [2026-03] Paper released on arXiv: arXiv:2603.13779
• [Coming Soon] MMAD-BBox dataset will be released soon.
• [Coming Soon] Chat-AD will be open-sourced upon paper acceptance.

---

Models

Model	Description	Link
AD-Copilot	Base vision-language model for anomaly detection	jiang-cc/AD-Copilot
AD-Copilot-Thinking	Thinking variant with enhanced reasoning	jiang-cc/AD-Copilot-Thinking

---

Citation

If you find this work useful, please cite our paper:

@article{jiang2026ad,
  title   = {AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison},
  author  = {Jiang, Xi and Guo, Yue and Li, Jian and Liu, Yong and Gao, Bin-Bin and Deng, Hanqiu and Liu, Jun and Zhao, Heng and Wang, Chengjie and Zheng, Feng},
  journal = {arXiv preprint arXiv:2603.13779},
  year    = {2026}
}