mlsanityData to 14 Oct 2026

Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection

arXiv 2607.03817 ↗First posted 4 Jul 2026cs.CVcited by 0

On the map: Multimodal LLMs / vision-language models → Chart understanding and anomaly detection

Abstract (arXiv)

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 & Logic Stream, where SAM 3 extracts partially checkable visual facts, with a Fine-Grained & 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 35 of its 45 references that are in the map. First posted on arXiv 4 Jul 2026.

Builds on

35 of 45 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization6 Aug
  2. 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?27 Jan
  3. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection12 Oct

Other references · 32

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2025Qwen3-VL Technical Reportcited by 2,793
  5. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,510
  6. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  7. 2025SAM 3: Segment Anything with Conceptscited by 906
  8. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learningcited by 410
  9. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  10. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  11. 2025Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learningcited by 278
  12. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
20 more
  1. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 245
  2. 2025MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipecited by 186
  3. 2016Revisiting Active Perceptioncited by 94
  4. 2024Perception Tokens Enhance Visual Reasoning in Multimodal Language Modelscited by 71
  5. 2024Injecting New Knowledge into Large Language Models via Supervised Fine-Tuningcited by 58
  6. 2024What Makes Multimodal In-Context Learning Work?cited by 56
  7. 2025Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Surveycited by 51
  8. 2024Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learningcited by 50
  9. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  10. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  11. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extractioncited by 25
  12. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  13. 2025IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detectioncited by 17
  14. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 12
  15. 2025EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Modelscited by 11
  16. 2025LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detectioncited by 9
  17. 2025LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoningcited by 9
  18. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8
  19. 2025AutoIAD: Manager-Driven Multi-Agent Collaboration for Automated Industrial Anomaly Detectioncited by 3
  20. 2025ABounD: Adversarial Boundary-Driven Few-Shot Learning for Multi-Class Anomaly Detectioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
  2. 2026JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA
  3. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
  4. 2026ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection
  5. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  6. 2026Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?
  7. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
  8. 2026EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models