AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

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

Xincheng Yao, Zefeng Qian, Chao Shi, Jiayang Song, Chongyang Zhang

CVPR 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Deep one-class and tabular anomaly detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add reasoning text (CoT) to training data (ablation)Anomaly-R1-7B · MVTecADdetection accuracy: 81.3 -> 88.8Improved
add reasoning text (CoT) to training data (ablation)Anomaly-R1-7B · VisAdetection accuracy: 66.1 -> 74.9Improved
add normal reference image to the input (ablation)Anomaly-R1-7B · MVTecADlocalization accuracy (IoU>=0.1): 62.1 -> 66.3Improved
add normal reference image to the input (ablation)Anomaly-R1-7B · VisAdetection accuracy: 62.5 -> 74.9Improved
add CoT cold-start SFT before RL (ablation)Anomaly-R1-7B · MVTecADlocalization accuracy (IoU>=0.1): 12.3 -> 66.3Improved
add CoT cold-start SFT before RL (ablation)Anomaly-R1-7B · VisAlocalization accuracy (IoU>=0.1): 5.3 -> 36.4Improved
add reinforcement learning (GRPO) after SFT (ablation)Anomaly-R1-7B · MVTecADdetection accuracy: 84.5 -> 88.8Improved
add reinforcement learning (GRPO) after SFT (ablation)Anomaly-R1-7B · VisAdetection accuracy: 73.3 -> 74.9Improved
add contrastive sampling to GRPO (ablation)Anomaly-R1-7B · MVTecADdetection accuracy: 87.7 -> 88.8Improved
add contrastive sampling to GRPO (ablation)Anomaly-R1-7B · VisAdetection accuracy: 73.7 -> 74.9Improved
add anomaly-related domain knowledge to the prompt (ablation)Anomaly-R1-7B · MVTecADdetection accuracy: 88.8 -> 91.0Improved
add anomaly-related domain knowledge to the prompt (ablation)Anomaly-R1-7B · VisAdetection accuracy: 74.9 -> 79.0Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy