mlsanityData to 7 Oct 2026

DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Models

arXiv 2606.16601 ↗First posted 15 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Industrial anomaly localization aims to accurately identify and localize abnormal regions in industrial products, addressing the critical challenge of detecting unseen defect categories in real-world scenarios. Traditional closed-set methods often suffer from poor cross-scenario generalization, while existingMultimodal Large Language Model (MLLM)-based approachesface two core limitations: they either adopt QA-style paradigmsmisaligned with the practical demands of localization, or relyon standard optimization techniques such as Group RelativePolicy Optimization (GRPO), which fails to deliver effectivelearning signals for subtle defects. To tackle these issues, thispaper proposes DifferAD-R1, an MLLM-augmented reinforcement learning framework tailored for industrial anomaly localization. We design a Difference-Guided dual-image paradigm,which reformulates the localization task as a one-shot difference grounding problem to effectively explore cross-scenarioanomalies. A Dual-Consistency Localization Reward is developedfor hard-to-detect anomalies, enhancing optimization stabilityand robustness. Additionally, we integrate a difficulty-awarestrategy with adaptive reweighting and group-wise resamplingto prioritize learning on challenging instances. To facilitateevaluations in real-world industrial settings, we construct theAD-DualDiff dataset, comprising 13K paired images across 20categories. Experimental results demonstrate that DifferADR1 significantly outperforms existing baselines and achievescompetitive performance compared to large-scale models likeQwen3-VL (235B parameters). Our code is publicly availableat: https://github.com/Rong2026/work-1.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 67 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

52 of 67 references.

References · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2025Qwen3-VL Technical Reportcited by 2,534
  7. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  8. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  9. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  10. 2023Vision Transformers Need Registerscited by 844
  11. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  12. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
38 more
  1. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  2. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  3. 2024InternLM2 Technical Reportcited by 391
  4. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  5. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  6. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  7. 2024mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Modelscited by 285
  8. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  9. 2025LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Trainingcited by 233
  10. 2024MANTIS: Interleaved Multi-Image Instruction Tuningcited by 212
  11. 2025MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipecited by 174
  12. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 169
  13. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  14. 2022CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localizationcited by 135
  15. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  16. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  17. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  18. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  19. 2025UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learningcited by 83
  20. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  21. 2022The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localizationcited by 55
  22. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  23. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  24. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationcited by 49
  25. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  26. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detectioncited by 46
  27. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  28. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  29. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  30. 2024Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Propertiescited by 26
  31. 2019Online PCB Defect Detector On A New PCB Defect Datasetcited by 25
  32. 2025Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Modelscited by 22
  33. 2022MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detectioncited by 19
  34. 2025OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoningcited by 18
  35. 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?cited by 17
  36. 2025EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPOcited by 11
  37. 2025LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoningcited by 9
  38. 2025Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Processcited by 8

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection
  2. 2026IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
  3. 2026Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space
  4. 2026Reasoning-Driven Anomaly Detection and Localization with Image-Level Supervision
  5. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
  6. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
  7. 2026A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
  8. 2025IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning