mlsanityData to 7 Oct 2026

GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models

arXiv 2607.01049 ↗First posted 1 Jul 2026cs.CVcited by 0

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

Abstract (arXiv)

Industrial inspection requires more than binary anomaly detection: a practical system should determine whether an anomaly exists, localize the defective region, identify the defect type, and provide interpretable visual evidence. Existing CLIP-based methods detect and localize anomalies well but offer limited language-level defect understanding, while instruction-tuned vision-language models can describe defects but do not natively produce pixel-level masks. We introduce GenAU, a Generalist vision-language framework for industrial Anomaly Understanding that unifies image-level detection, pixel-level segmentation, multi-type anomaly detection, and defect analysis in a single instruction-following model. GenAU augments a vision-language model with two segmentation tokens, [SEG_defect] and [SEG_normal], whose hidden states act as language-grounded queries over multi-scale visual features for pixel-level localization; the image-level score fuses this map with the decoder's textual normal/defect decision, while the language decoder produces structured defect-aware responses. Trained with a joint language-modeling and segmentation objective, GenAU covers all four tasks within one architecture and recipe, adding zero-shot multi-type detection and language-grounded defect analysis at a quantified cost to detection and segmentation. Across cross-dataset benchmarks, GenAU attains the strongest image-level detection among CLIP-based zero-shot methods on VisA and Real-IAD, with segmentation approaching but not surpassing specialized CLIP baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 18 of its 37 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

18 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models5 May
  2. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models11 Feb
  3. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models29 Aug

Other references · 15

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  5. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  6. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 311
  7. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  8. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 138
  9. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 128
  10. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  11. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  12. 2022MAEDAY: MAE for few and zero shot AnomalY-Detectioncited by 30
3 more
  1. 2025MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learningcited by 12
  2. 2023Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localizationcited by 10
  3. 2025Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learningcited by 4

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. 2024FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
  3. 2026A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision
  4. 2026AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
  5. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
  6. 2026OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation
  7. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  8. 2025ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoning