arXiv Computer Vision

Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?

The paper investigates whether in‑domain training alone can enable multimodal large language models (MLLMs) to perform fine‑grained industrial anomaly understanding (MM‑IAU). It shows that even specialized MLLMs fail to match human experts on defect localization and detection, and that combining different MLLMs does not eliminate this shortfall. To address this, the authors propose SiGMA, a spatially grounded multi‑agent framework that splits tasks among heterogeneous MLLM agents and a dedicated visual defect expert, achieving 85.2% accuracy on the MMAD benchmark—close to human performance and surpassing the best trained specialist.

arXiv Computer Vision

Sep 25

Industrial Anomaly Detection via Defect-Grounded Reasoning in Visual Latent Space

The paper introduces Anomaly‑LR, a defect‑grounded latent reasoning framework for industrial anomaly detection that builds a global understanding of an image and then refines anomaly‑relevant representations directly in visual latent space. It also presents IAD‑LR‑22K, a new instruction dataset with 22,228 image‑question pairs and detailed annotations. Experiments demonstrate that Anomaly‑LR outperforms comparable‑scale methods on multiple IAD benchmarks without needing external references or tools.

By Jaron Yeh, Yen-Wei Chang, Jiang Liu, Shao-Yuan Lo

llms diffusion multimodal benchmarks

arXiv AI

Jul 21

RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants

arXiv:2607. 16243v1 Announce Type: cross Abstract: Multimodal industrial anomaly inspection assistants are a critical component of next-generation smart factories, enabling interactive vision-language-based querying.

By Anushiya Arunan, Xin Li, Yan Qin, U-Xuan Tan, Nhu Khue Vuong, Xiaoli Li, Chau Yuen

llms multimodal benchmarks safety

Hugging Face Trending Papers

Aug 10

ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection

Industrial anomaly detection (IAD) requires identifying fine-grained deviations from normal visual patterns. Multimodal large language models (MLLMs) can improve recognition accuracy by comparing query images with references at inference time, but these benefits rely on additional retrieval and processing.

llms efficiency multimodal benchmarks

arXiv AI

Jun 2

A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision

arXiv:2606. 01992v1 Announce Type: cross Abstract: Industrial anomaly detection has historically been a unimodal task.

By Stefano Samele, Eugenio Lomurno, Teodora Jovanovic, Sanjay Shivakumar Manohar, Alberto Crivellaro, Matteo Matteucci

llms rag multimodal benchmarks

arXiv AI

Jul 22

OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation

arXiv:2607. 18850v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning.

By Shuimu Chen, Jing Jin, Nan Su, Hongbo Xu, Zebang Cheng, Wenming Yang, Fei Ma, Guijin Wang

llms efficiency multimodal

arXiv AI

Oct 1

TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization

The paper introduces TED (Text-Axis Evidence Decomposition), a post‑hoc scoring method that improves anomaly localization in CLIP‑based detectors without altering the backbone or prompts. TED evaluates whether ambiguous responses are better supported by defect patches or normal patches, thereby distinguishing true defects from visually complex normal regions. Experiments show that TED significantly enhances pixel‑level localization across frozen VLM backbones and adapted hosts, especially under hard‑false‑positive competition.

By JinYoung Kim, Geonho Kim, GiJeong Park, Geonu Lee, YoungJoon Yoo

llms multimodal

arXiv AI

Jun 26

MMGist: A Comprehensive Multimodal Benchmark for 2027

arXiv:2606. 22437v2 Announce Type: replace-cross Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results.

By Wenzhen Yuan, Jiacheng Ruan, Wutao Xiong, Chengping Zhao, Ting Liu, Yuzhuo Fu

multimodal benchmarks

arXiv Computer Vision

Aug 24

AGIDefect-4K: A Richly Annotated Dataset for AI-Generated Image Defect Detection, Localization and Explanation

arXiv:2608.20713v1 Announce Type: new Abstract: Generative AI can now produce highly realistic images, yet current models still exhibit subtle but critical defects that undermine their reliability. W...

By Xiangfei Sheng, Weidong Zou, Tianjiao Gu, Zhichao Yang, Pengfei Chen, Leida Li

llms computer-vision multimodal benchmarks

arXiv AI

Oct 9

IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generation

IAD-Unify is a unified architecture that connects a multimodal language model, a dense visual expert, and a diffusion editor via task‑specific token interfaces to perform industrial anomaly inspection tasks such as explaining defects, localizing pixels, and generating controlled edits. It uses a multi‑reference DINOv2 pathway to create a dense anomaly field, compresses it into structured evidence tokens, and feeds these tokens to Qwen3.5 for grounded answers and semantic residuals, while a separate query interface integrates with Stable Diffusion for localized generation. The system is trained in stages—first aligning dense evidence with language, then calibrating segmentation, and finally pre‑training the diffusion editor—while also building a large, quality‑controlled dataset of anomaly evidence and edit pairs.

By Haoyu Zheng, Jiang Liu, Jiaqi Zhu, Feifei Shao, Zheqi Lv, Wenqiao Zhang

llms diffusion computer-vision multimodal

arXiv Computer Vision

4d ago

CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis

arXiv:2610.19610v1 Announce Type: new Abstract: Industrial anomaly detection (AD) is bottlenecked by the scarcity of anomalous samples, making high-fidelity anomaly synthesis crucial for improving do...

By Haoxiang Rao, Fang Zhao, Zhao Wang, Weijia Li, Chenyang Si, Caifeng Shan

multimodal

arXiv Computer Vision

Sep 1

InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection

arXiv:2608.29783v1 Announce Type: new Abstract: Industrial anomaly detection is a critical component of modern manufacturing. Most traditional unsupervised methods rely on modelling normal feature di...

By Weifei Chen, Honghao Zhang, Zhiyuan You, Xinyi Le

llms computer-vision fine-tuning multimodal benchmarks

Hugging Face Trending Papers

Sep 30

TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization

CLIP is a powerful vision-language model, but it was not designed for fine-grained defect localization; CLIP-based anomaly detectors therefore adapt it with prompts or lightweight modules to increase...

llms multimodal

Related stories