{"total":53,"rows":[{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171,"area":"mllm"},{"id":"2407.12276","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","created":"2024-07-17","cited_by_count":50,"area":"mllm"},{"id":"2310.19070","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","created":"2023-10-29","cited_by_count":39,"area":"mllm"},{"id":"2407.21794","title":"Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey","created":"2024-07-31","cited_by_count":36,"area":"mllm"},{"id":"2503.10080","title":"Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection","created":"2025-03-13","cited_by_count":31,"area":"mllm"},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2311.02612","title":"GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection","created":"2023-11-05","cited_by_count":23,"area":"mllm"},{"id":"2503.14853","title":"Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection","created":"2025-03-19","cited_by_count":21,"area":"mllm"},{"id":"2409.20146","title":"VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection","created":"2024-09-30","cited_by_count":13,"area":"mllm"},{"id":"2505.09265","title":"MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning","created":"2025-05-14","cited_by_count":13,"area":"mllm"},{"id":"2506.06836","title":"Harnessing Vision-Language Models for Time Series Anomaly Detection","created":"2025-06-07","cited_by_count":11,"area":"mllm"},{"id":"2508.13560","title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","created":"2025-08-19","cited_by_count":10,"area":"mllm"},{"id":"2409.00556","title":"FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model","created":"2024-08-31","cited_by_count":7,"area":"mllm"},{"id":"2501.03786","title":"KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration","created":"2025-01-07","cited_by_count":7,"area":"mllm"},{"id":"2510.09867","title":"Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation","created":"2025-10-10","cited_by_count":7,"area":"mllm"},{"id":"2505.02626","title":"Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models","created":"2025-05-05","cited_by_count":6,"area":"mllm"},{"id":"2602.00522","title":"MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval","created":"2026-01-31","cited_by_count":6,"area":"mllm"},{"id":"2504.02799","title":"Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence","created":"2025-04-03","cited_by_count":5,"area":"mllm"},{"id":"2603.13779","title":"AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison","created":"2026-03-14","cited_by_count":5,"area":"mllm"},{"id":"2604.02327","title":"Steerable Visual Representations","created":"2026-04-02","cited_by_count":4,"area":"mllm"},{"id":"2508.05898","title":"ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates","created":"2025-08-07","cited_by_count":3,"area":"mllm"},{"id":"2511.08173","title":"VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion","created":"2025-11-11","cited_by_count":3,"area":"mllm"},{"id":"2604.07802","title":"Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models","created":"2026-04-09","cited_by_count":3,"area":"mllm"},{"id":"2406.18197","title":"Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme","created":"2024-06-26","cited_by_count":2,"area":"mllm"},{"id":"2510.16036","title":"IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection","created":"2025-10-16","cited_by_count":2,"area":"mllm"},{"id":"2602.17419","title":"EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"mllm"},{"id":"2605.20682","title":"IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2403.09493","title":"Anomaly Detection by Adapting a pre-trained Vision Language Model","created":"2024-03-14","cited_by_count":1,"area":"mllm"},{"id":"2404.00675","title":"LLM meets Vision-Language Models for Zero-Shot One-Class Classification","created":"2024-03-31","cited_by_count":1,"area":"mllm"},{"id":"2506.10730","title":"IQE-CLIP: Instance-aware Query Embedding for Zero-/Few-shot Anomaly Detection in Medical Domain","created":"2025-06-12","cited_by_count":1,"area":"mllm"},{"id":"2508.03447","title":"CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection","created":"2025-08-05","cited_by_count":1,"area":"mllm"},{"id":"2603.01305","title":"AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models","created":"2026-03-01","cited_by_count":1,"area":"mllm"},{"id":"2603.06313","title":"WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection","created":"2026-03-06","cited_by_count":1,"area":"mllm"},{"id":"2604.27629","title":"WaferSAGE: Large Language Model-Powered Wafer Defect Analysis via Synthetic Data Generation and Rubric-Guided Reinforcement Learning","created":"2026-04-30","cited_by_count":1,"area":"mllm"},{"id":"2605.30140","title":"AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2607.02930","title":"CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection","created":"2026-07-03","cited_by_count":1,"area":"mllm"},{"id":"2607.18850","title":"OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation","created":"2026-07-21","cited_by_count":1,"area":"mllm"},{"id":"2412.00890","title":"Exploring Large Vision-Language Models for Robust and Efficient Industrial Anomaly Detection","created":"2024-12-01","cited_by_count":0,"area":"mllm"},{"id":"2502.09057","title":"Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model","created":"2025-02-13","cited_by_count":0,"area":"mllm"},{"id":"2508.07819","title":"ACD-CLIP: Decoupling Representation and Dynamic Fusion for Zero-Shot Anomaly Detection","created":"2025-08-11","cited_by_count":0,"area":"mllm"},{"id":"2508.16157","title":"Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly Detection","created":"2025-08-22","cited_by_count":0,"area":"mllm"},{"id":"2512.09446","title":"Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentation","created":"2025-12-10","cited_by_count":0,"area":"mllm"},{"id":"2601.09147","title":"SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection","created":"2026-01-14","cited_by_count":0,"area":"mllm"},{"id":"2601.15453","title":"DevPrompt: Deviation-Based Prompt Learning for One-Normal ShotImage Anomaly Detection","created":"2026-01-21","cited_by_count":0,"area":"mllm"},{"id":"2603.21824","title":"SteelDefectX: A Multi-Form Vision-Language Dataset and Benchmark for Steel Surface Defect Analysis","created":"2026-03-23","cited_by_count":0,"area":"mllm"},{"id":"2605.27452","title":"Fine-Tuning Vision-Language Models for Understanding Current Damage and Scoring Priority with Quality Guard Agent","created":"2026-05-24","cited_by_count":0,"area":"mllm"},{"id":"2606.11266","title":"Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language Models","created":"2026-06-09","cited_by_count":0,"area":"mllm"},{"id":"2606.28401","title":"Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2607.01049","title":"GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.03817","title":"Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection","created":"2026-07-04","cited_by_count":0,"area":"mllm"},{"id":"2609.06360","title":"NOVA: Normal-Side Modeling for Training-Free Zero-Shot Video Anomaly Detection","created":"2026-09-06","cited_by_count":0,"area":"mllm"},{"id":"2609.07229","title":"Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2609.39033","title":"TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization","created":"2026-09-30","cited_by_count":0,"area":"mllm"}],"next_cursor":null}