{"ID":5937942,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T11:02:02.505471457Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03817","arxiv_id":"2607.03817","title":"Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection","abstract":"Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but they often require many defective samples, which are unavailable in early deployment. We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification. GLLS uses a Part-Aware Visual-Logical Atlas to organize normal references and structured specifications in the inference context. It combines a Global \u0026 Logic Stream, where SAM 3 extracts partially checkable visual facts, with a Fine-Grained \u0026 Actions Stream, where MCTS selects local evidence crops under a fixed budget. Experiments on MMAD-QA and additional anomaly detection datasets show consistent gains over matched and general-purpose baselines, while keeping the final diagnostic decision traceable to explicit visual evidence throughout the inspection trace.","short_abstract":"Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but th...","url_abs":"https://arxiv.org/abs/2607.03817","url_pdf":"https://arxiv.org/pdf/2607.03817v1","authors":"[\"Runzhi Deng\",\"Yundi Hu\",\"Yiming Zhong\",\"Zhao Wang\",\"Xixi Liu\",\"Hongsong Wang\",\"Caifeng Shan\",\"Fang Zhao\"]","published":"2026-07-04T11:05:57Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}