mlsanityData to 7 Oct 2026

MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models

arXiv 2604.10971 ↗First posted 13 Apr 2026cs.CV cs.AIcited by 1

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

Abstract (arXiv)

In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multimodal Large Language Models (MLLMs) have shown great promise in achieving general anomaly detection due to their revolutionary visual understanding and language reasoning capabilities. However, MLLM's general AD ability remains underexplored due to: (1) MLLMs are pretrained on amounts of data sourced from the Web, these data still have significant gaps with the data in AD scenarios. Moreover, the image-text pairs during pretraining are also not specifically for AD tasks. (2) The current mainstream AD datasets are image-based and not yet suitable for post-training MLLMs. To facilitate MLLM-based general AD research, we present MMR-AD, which is a comprehensive benchmark for both training and evaluating MLLM-based AD models. With MMR-AD, we reveal that the AD performance of current SOTA generalist MLLMs still falls far behind the industrial requirements. Based on MMR-AD, we also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data in MMR-AD and is further enhanced by reinforcement learning. Extensive experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 51 of its 67 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

51 of 67 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment10 Jul
  2. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models11 Feb
  3. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection30 Sep
  4. 2023GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection5 Nov
  5. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models29 Aug

Other references · 46

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2025Qwen2.5-VL Technical Reportcited by 5,418
  6. 2024GPT-4o System Cardcited by 4,467
  7. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  9. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  10. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  11. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  12. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
34 more
  1. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  2. 2025Gemma 3 Technical Reportcited by 1,686
  3. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,573
  4. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  5. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  6. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  7. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  8. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  9. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 419
  10. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  11. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  12. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  13. 2022A Unified Model for Multi-class Anomaly Detectioncited by 267
  14. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 174
  15. 2024Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputscited by 148
  16. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  17. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 92
  18. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 88
  19. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  20. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  21. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 47
  22. 2023Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Leadcited by 40
  23. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detectioncited by 33
  24. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  25. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28
  26. 2024MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objectscited by 26
  27. 2024ResAD: A Simple Framework for Class Generalizable Anomaly Detectioncited by 24
  28. 2023Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrievalcited by 22
  29. 2023PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentationcited by 21
  30. 2022MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detectioncited by 19
  31. 2024Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoningcited by 19
  32. 2024FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queriescited by 12
  33. 20253CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomalycited by 10
  34. 2024CableInspect-AD: An Expert-Annotated Anomaly Detection Datasetcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
  2. 2025IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection
  3. 2026Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
  4. 2025AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
  5. 2025Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?
  6. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection
  7. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
  8. 2025Can Multimodal LLMs Perform Time Series Anomaly Detection?