{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:02:18Z","timestamp":1789686138056,"version":"4.0.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370310","type":"print"},{"value":"9783032370327","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37032-7_26","type":"book-chapter","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:12:10Z","timestamp":1789683130000},"page":"475-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Common Sense: Grounding Logical Anomaly Detection in\u00a0Inspection Criteria"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7365-1158","authenticated-orcid":false,"given":"Yuanze","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2022-6774","authenticated-orcid":false,"given":"Shihao","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5490-4125","authenticated-orcid":false,"given":"Zimeng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9136-8481","authenticated-orcid":false,"given":"Ming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangming","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"26_CR1","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"26_CR2","unstructured":"Bai, S., et al..: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"issue":"4","key":"26_CR3","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1007\/s11263-022-01578-9","volume":"130","author":"P Bergmann","year":"2022","unstructured":"Bergmann, P., Batzner, K., Fauser, M., Sattlegger, D., Steger, C.: Beyond dents and scratches: logical constraints in unsupervised anomaly detection and localization. Int. J. Comput. Vision 130(4), 947\u2013969 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTec AD-a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592\u20139600 (2019)","DOI":"10.1109\/CVPR.2019.00982"},{"key":"26_CR5","unstructured":"Chao, Y., Liu, J., Tang, J., Wu, G.: Anomalyr1: A GRPO-based end-to-end MLLM for industrial anomaly detection. arXiv preprint arXiv:2504.11914 (2025)"},{"key":"26_CR6","unstructured":"Chen, G.H., et al.: ALLaVA: harnessing GPT4V-synthesized data for lite vision-language models. arXiv preprint arXiv:2402.11684 (2024)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: ShareGPT4V: improving large multi-modal models with better captions. In: European Conference on Computer Vision, pp. 370\u2013387. Springer (2024)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"26_CR8","unstructured":"DeepSeek-AI: Deepseek-V4: Towards highly efficient million-token context intelligence (2026)"},{"key":"26_CR9","unstructured":"Ding, L.: AdaRubric: task-adaptive rubrics for reliable LLM agent evaluation and reward learning. arXiv preprint arXiv:2603.21362 (2026)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: MANTA: a large-scale multi-view and visual-text anomaly detection dataset for tiny objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.02376"},{"key":"26_CR11","unstructured":"Google DeepMind: Gemini 3.1 pro: A smarter foundation for complex reasoning and agentic workflows. Tech. rep., Google DeepMind, technical Report (2026)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Z., Zhu, B., Zhu, G., Chen, Y., Tang, M., Wang, J.: AnomalyGPT: detecting industrial anomalies using large vision-language models. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 1932\u20131940 (2024)","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"26_CR13","unstructured":"Guan, W., Lan, J., Cao, J., Tan, H., Zhu, H., Wang, W.: EMIT: enhancing MLLMs for industrial anomaly detection via difficulty-aware GRPO. arXiv preprint arXiv:2507.21619 (2025)"},{"key":"26_CR14","unstructured":"Guo, D., et\u00a0al.: Deepseek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Y., Xu, L., Liu, J., Dan, Y., Qiu, S.: Segment policy optimization: Effective segment-level credit assignment in RL for large language models. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-3815"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Guo, Z., et al.: Integrating visual interpretation and linguistic reasoning for geometric problem solving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3988\u20133998 (2025)","DOI":"10.1109\/ICCV51701.2025.00380"},{"key":"26_CR17","unstructured":"Jiang, Q., et al.: Detect anything via next point prediction. arXiv preprint arXiv:2510.12798 (2025)"},{"key":"26_CR18","unstructured":"Kang, H., Lee, W., Kim, J., Park, H.: Judo: A juxtaposed domain-oriented multimodal reasoner for industrial anomaly QA. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"26_CR19","unstructured":"Kazemnejad, A., et al.: VinePPO: accurate credit assignment in RL for LLM mathematical reasoning. In: The 4th Workshop on Mathematical Reasoning and AI at NeurIPS\u201924 (2024)"},{"key":"26_CR20","unstructured":"Li, X., et\u00a0al.: DenseWorld-1M: towards detailed dense grounded caption in the real world. arXiv preprint arXiv:2506.24102 (2025)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Cao, Y., Liu, C., Xiong, Y., Dong, X., Huang, C.: IAD-R1: reinforcing consistent reasoning in industrial anomaly detection. arXiv preprint arXiv:2508.09178 (2025)","DOI":"10.1609\/aaai.v40i8.37588"},{"key":"26_CR22","unstructured":"Li, Y., et al.: Myriad: Large multimodal model by applying vision experts for industrial anomaly detection. arXiv preprint arXiv:2310.19070 (2023)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Triad: Empowering LMM-based anomaly detection with expert-guided region-of-interest tokenizer and manufacturing process. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21917\u201321926 (2025)","DOI":"10.1109\/ICCV51701.2025.02035"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.52202\/075280-1516"},{"key":"26_CR25","unstructured":"Liu, S.Y., et\u00a0al.: GDPO: group reward-decoupled normalization policy optimization for multi-reward RL optimization. arXiv preprint arXiv:2601.05242 (2026)"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Liu, T., Xu, R., Yu, T., Hong, I., Yang, C., Zhao, T., Wang, H.: OpenRubrics: towards scalable synthetic rubric generation for reward modeling and LLM alignment. arXiv preprint arXiv:2510.07743 (2025)","DOI":"10.18653\/v1\/2026.acl-long.791"},{"key":"26_CR27","unstructured":"Liu, Y., et al.: ViSurf: visual supervised-and-reinforcement fine-tuning for large vision-and-language models. arXiv preprint arXiv:2510.10606 (2025)"},{"key":"26_CR28","unstructured":"Miao, J., Du, P., Liu, Y., Wang, Y., Wang, Y.: AgentiAD: tool-augmented single-agent for industrial anomaly detection. arXiv preprint arXiv:2512.13671 (2025)"},{"key":"26_CR29","unstructured":"Nakata, H., et al.: VID-AD: a dataset for image-level logical anomaly detection under vision-induced distraction. arXiv preprint arXiv:2603.13964 (2026)"},{"key":"26_CR30","unstructured":"Ni, M., Fan, Y., Zhang, L., Zuo, W.: Visual-O1: understanding ambiguous instructions via multi-modal multi-turn chain-of-thoughts reasoning. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Ni, M., et al.: Point-RFT: improving multimodal reasoning with visually grounded reinforcement finetuning. arXiv preprint arXiv:2505.19702 (2025)","DOI":"10.52202\/085713-0692"},{"key":"26_CR32","unstructured":"Ni, T., Chen, Z., Yang, Y.: Towards open-vocabulary industrial defect understanding with a large-scale multimodal dataset. arXiv preprint arXiv:2512.24160 (2025)"},{"key":"26_CR33","unstructured":"OpenAI: GPT-5.2 System Card: advances in Reasoning and Multi-step Planning. arXiv preprint arXiv:2601.03267 (2026)"},{"key":"26_CR34","unstructured":"Qwen Team: Qwen3.5: Towards native multimodal agents (2026)"},{"key":"26_CR35","unstructured":"Shao, Z., et\u00a0al.: DeepSeekMath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"26_CR36","unstructured":"Sheng, G., et al.: HybridFlow: a flexible and efficient RLHF framework. arXiv preprint arXiv: 2409.19256 (2024)"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Wang, C., Wu, W., Zheng, J.: Real-IAD: a real-world multi-view dataset for benchmarking versatile industrial anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: ReinAD: towards real-world industrial anomaly detection with a comprehensive contrastive dataset. In: Advances in Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-0651"},{"key":"26_CR39","unstructured":"Wang, Y., Xia, X., Wu, X., Zhai, X., Liu, N.: Learnable assessment skills for LLM-based automated scoring: rubric construction via iterative optimization. arXiv preprint arXiv:2605.29274 (2026)"},{"key":"26_CR40","unstructured":"Xie, W., et\u00a0al.: Step-wise rubric rewards for LLM reasoning. arXiv preprint arXiv:2605.17291 (2026)"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Xu, J., Lo, S.Y., Safaei, B., Patel, V.M., Dwivedi, I.: Towards zero-shot anomaly detection and reasoning with multimodal large language models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 20370\u201320382 (2025)","DOI":"10.1109\/CVPR52734.2025.01897"},{"key":"26_CR42","unstructured":"Yang, A., et al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Yao, H., Liu, M., Yin, Z., Yan, Z., Hong, X., Zuo, W.: GLAD: towards better reconstruction with global and local adaptive diffusion models for unsupervised anomaly detection. In: European Conference on Computer Vision (ECCV), pp. 1\u201317. Springer (2024)","DOI":"10.1007\/978-3-031-73209-6_1"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Zang, G., et al.: SAGE: a visual language model for anomaly detection via fact enhancement and entropy-aware alignment. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 5030\u20135039 (2025)","DOI":"10.1145\/3746027.3755725"},{"key":"26_CR45","unstructured":"Zhao, S., Lin, Y., Han, L., Zhao, Y., Wei, Y.: OmniAD: detect and understand industrial anomaly via multimodal reasoning. arXiv preprint arXiv:2505.22039 (2025)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et al.: LlamaFactory: unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics, Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Zhu, W., et\u00a0al.: Real-IAD variety: pushing industrial anomaly detection dataset to a modern era. arXiv preprint arXiv:2511.00540 (2025)","DOI":"10.1016\/j.patcog.2026.113354"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Zou, Y., Jeong, J., Pemula, L., Zhang, D., Dabeer, O.: Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20056-4_23"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37032-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:12:24Z","timestamp":1789683144000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37032-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370310","9783032370327"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37032-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"18 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}