Xurui Li (李煦蕤)

• 2025.09 - present, 博士（硕博连读），华中科技大学.
• 2025.06 - 2025.08, Intern at Tencent YouTu Lab.
• 2023.09 - 2025.06, 硕士（转博），华中科技大学.
• 2019.09 - 2023.06, 本科，华中科技大学.

WeChat: 19807226240

🔥 Publications

# Contributed Equally

1. AnoCalib: Unified Anomaly-aware Feature Calibration for Zero-shot Industrial Anomaly Detection
   Tianyi Ma, Feng Xue, Dayou Huang, Xurui Li, Shilei Zeng, Yuyi Tian, Yu Zhou
   Pattern Recognition. (PR). 2026.
   [Paper] [Code]
   
2. DeCo: Zero-Shot Anomaly Generation through Decoupling and Recoupling
   Shilei Zeng, Xurui Li, Yaohan Tang, Yu Zhou
   European Conference on Computer Vision. (ECCV). 2026.
   [Paper] [Code]
   
3. UniScale: Arbitrary-Scale Anomaly Generation
   Shilei Zeng#, Linxin Guan#, Xurui Li, Yaohan Tang, Yu Zhou
   European Conference on Computer Vision. (ECCV). 2026.
   [Paper] [Code]
   
4. MuSc-V2: Zero-Shot Multimodal Industrial Anomaly Classification and Segmentation with Mutual Scoring of Unlabeled Samples
   Xurui Li, Feng Xue, Yu Zhou
   IEEE Transactions on Pattern Analysis and Machine Intelligence. (TPAMI). 2026.
   [Paper] [Code]
   
5. SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning
   Zhewei Dai#, Shilei Zeng#, Haotian Liu, Xurui Li, Feng Xue, Yu Zhou
   IEEE Conference on International Conference on Computer Vision. (ICCV). 2025.
   [Paper] [Code]
   
6. RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images
   Xurui Li, Zhongsheng Jiang, Tingxuan Ai, Yu Zhou
   CVPR2025 VAND3.0 challenge Track 1 (Second place).
   [Paper] [Code]
   
7. AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios
   Ziming Huang#, Xurui Li#, Haotian Liu#, Feng Xue, Yuzhe Wang, Yu Zhou
   IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2025.
   [Paper] [Code]
   
8. MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
   Xurui Li#, Ziming Huang#, Feng Xue, Yu Zhou
   The Twelfth International Conference on Learning Representations (ICLR). 2024.
   [Paper] [Code]
   

🔥 Other papers

# Contributed Equally

1. Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classification
   Xurui Li, Enjie Xu, ChenZhou Li, Shilei Zeng, Dayou Huang, Tianyi Ma, Yu Zhou
   arXiv. 2026.
   [Paper] [Code]
   
2. AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection
   Dayou Huang, Feng Xue, Xurui Li, Yu Zhou
   arXiv. 2025.
   [Paper] [Code]
   

🎖 Honors and Awards

• 2025.05 CVPR2025 workshop VAND3.0 challenge (Second place)
• 2024.11 第十九届“挑战杯”全国大学生课外学术科技作品竞赛“揭榜挂帅”专项赛（全国一等奖）
• 2024.10 硕士生国家奖学金
• 2024.09 “华为杯”第六届中国研究生人工智能创新大赛（全国一等奖，团队队长）

Interests

• 我当前的研究内容为工业缺陷检测（industrial anomaly detection）、工业缺陷多分类（multi-type anomaly classification）、零/少样本学习（zero/few-shot learning）。
• 场景：布匹瑕疵检测、Mura缺陷检测、汽车铸件3D缺陷检测、PCB缺陷检测、X光机时序状态异常检测等。