{"total":171,"rows":[{"id":"2407.15795","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","created":"2024-07-22","cited_by_count":127,"area":null},{"id":"2412.04292","title":"SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model","created":"2024-12-05","cited_by_count":108,"area":"mllm"},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87,"area":null},{"id":"2406.12235","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","created":"2024-06-18","cited_by_count":64,"area":"mllm"},{"id":"2407.10299","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","created":"2024-07-14","cited_by_count":57,"area":"lr"},{"id":"2502.07601","title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models","created":"2025-02-11","cited_by_count":54,"area":"lr"},{"id":"2404.13671","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","created":"2024-04-21","cited_by_count":51,"area":null},{"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":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2503.02424","title":"Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection","created":"2025-03-04","cited_by_count":48,"area":null},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2311.02782","title":"Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead","created":"2023-11-05","cited_by_count":40,"area":null},{"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":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2503.21622","title":"The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detection","created":"2025-03-27","cited_by_count":30,"area":null},{"id":"2403.04306","title":"Effectiveness Assessment of Recent Large Vision-Language Models","created":"2024-03-07","cited_by_count":29,"area":"mllm"},{"id":"2411.16778","title":"GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis","created":"2024-11-25","cited_by_count":29,"area":null},{"id":"2412.03342","title":"UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection","created":"2024-12-04","cited_by_count":28,"area":null},{"id":"2504.11914","title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","created":"2025-04-16","cited_by_count":28,"area":"lr"},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26,"area":null},{"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":"2406.01078","title":"Unseen Visual Anomaly Generation","created":"2024-06-03","cited_by_count":23,"area":null},{"id":"2410.10289","title":"Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection","created":"2024-10-14","cited_by_count":22,"area":null},{"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":"2405.19882","title":"PixOOD: Pixel-Level Out-of-Distribution Detection","created":"2024-05-30","cited_by_count":20,"area":null},{"id":"2406.04687","title":"LogiCode: an LLM-Driven Framework for Logical Anomaly Detection","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2408.14307","title":"LLM-3D Print: Large Language Models To Monitor and Control 3D Printing","created":"2024-08-26","cited_by_count":18,"area":null},{"id":"2505.09264","title":"Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt","created":"2025-05-14","cited_by_count":18,"area":null},{"id":"2403.20236","title":"Long-Tailed Anomaly Detection with Learnable Class Names","created":"2024-03-29","cited_by_count":14,"area":null},{"id":"2505.06152","title":"MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks","created":"2025-05-09","cited_by_count":14,"area":"mllm"},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"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":"2410.10238","title":"ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2412.03409","title":"PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation","created":"2024-12-04","cited_by_count":13,"area":"lr"},{"id":"2407.10810","title":"FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queries","created":"2024-07-15","cited_by_count":12,"area":null},{"id":"2504.06740","title":"MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning","created":"2025-04-09","cited_by_count":12,"area":null},{"id":"2312.12273","title":"VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering","created":"2023-12-19","cited_by_count":11,"area":null},{"id":"2503.14162","title":"EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2308.15939","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","created":"2023-08-30","cited_by_count":10,"area":null},{"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":"2602.03018","title":"From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection","created":"2026-02-03","cited_by_count":9,"area":null},{"id":"2501.10067","title":"FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization","created":"2025-01-17","cited_by_count":8,"area":null},{"id":"2503.13184","title":"Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2506.17633","title":"Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection","created":"2025-06-21","cited_by_count":8,"area":null},{"id":"2508.06203","title":"AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection","created":"2025-08-08","cited_by_count":8,"area":"moe"},{"id":"2508.09185","title":"A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality","created":"2025-08-07","cited_by_count":8,"area":null},{"id":"2403.04151","title":"Dual-path Frequency Discriminators for Few-shot Anomaly Detection","created":"2024-03-07","cited_by_count":7,"area":null},{"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":"2502.01201","title":"One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2506.21398","title":"FastRef:Fast Prototype Refinement for Few-Shot Industrial Anomaly Detection","created":"2025-06-26","cited_by_count":7,"area":null},{"id":"2507.19949","title":"AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2509.15888","title":"Distribution-Aligned Decoding for Efficient LLM Task Adaptation","created":"2025-09-19","cited_by_count":7,"area":"mechinterp"},{"id":"2312.06718","title":"Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey","created":"2023-12-11","cited_by_count":6,"area":null},{"id":"2407.11480","title":"AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2505.00742","title":"Zoomer: Adaptive Image Focus Optimization for Black-box MLLM","created":"2025-04-30","cited_by_count":6,"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":"2407.21351","title":"Small Object Few-shot Segmentation for Vision-based Industrial Inspection","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2408.11221","title":"On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2409.20353","title":"CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2410.00713","title":"RAD: A Dataset and Benchmark for Real-Life Anomaly Detection with Robotic Observations","created":"2024-10-01","cited_by_count":5,"area":null},{"id":"2502.19106","title":"A Survey on Foundation-Model-Based Industrial Defect Detection","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2503.07253","title":"AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2504.02775","title":"TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2504.03306","title":"Multi-Flow: Multi-View-Enriched Normalizing Flows for Industrial Anomaly Detection","created":"2025-04-04","cited_by_count":5,"area":null},{"id":"2510.01934","title":"Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2602.13807","title":"AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning","created":"2026-02-14","cited_by_count":5,"area":"agents"},{"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":"2408.13516","title":"Bidirectional Multimodal Prompt Learning with Scale-Aware Training for Few-Shot Multi-Class Anomaly Detection","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2409.17330","title":"VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection","created":"2024-09-25","cited_by_count":4,"area":"mllm"},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2510.26464","title":"Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2512.13671","title":"AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentation","created":"2025-12-15","cited_by_count":4,"area":"agents"},{"id":"2602.19206","title":"GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning","created":"2026-02-22","cited_by_count":4,"area":null},{"id":"2502.06911","title":"Foundation Models for Anomaly Detection: Vision and Challenges","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2504.19627","title":"VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning","created":"2025-04-28","cited_by_count":3,"area":"lr"},{"id":"2505.07040","title":"Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2505.13828","title":"Multimodal RAG-driven Anomaly Detection and Classification in Laser Powder Bed Fusion using Large Language Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2507.14899","title":"InsightX Agent: An LMM-based Agentic Framework with Integrated Tools for Reliable X-ray NDT Analysis","created":"2025-07-20","cited_by_count":3,"area":null},{"id":"2508.13975","title":"ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation","created":"2025-08-19","cited_by_count":3,"area":null},{"id":"2603.01713","title":"Dual Distillation for Few-Shot Anomaly Detection","created":"2026-03-02","cited_by_count":3,"area":null},{"id":"2407.02586","title":"Improving Visual Storytelling with Multimodal Large Language Models","created":"2024-07-02","cited_by_count":2,"area":"mllm"},{"id":"2504.03718","title":"Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2506.04713","title":"Enabling Validation for Robust Few-Shot Recognition","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2507.18481","title":"Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detection","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2508.03539","title":"Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2509.10282","title":"MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detection","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2510.10456","title":"On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection","created":"2025-10-12","cited_by_count":2,"area":null},{"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":"2511.00540","title":"Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2512.00691","title":"Silhouette-based Gait Foundation Model","created":"2025-11-30","cited_by_count":2,"area":null},{"id":"2601.01856","title":"GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.16381","title":"VTFusion: A Vision-Text Multimodal Fusion Network for Few-Shot Anomaly Detection","created":"2026-01-23","cited_by_count":2,"area":null},{"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":"2603.15237","title":"Multi-turn Physics-informed Vision-language Model for Physics-grounded Anomaly Detection","created":"2026-03-16","cited_by_count":2,"area":"lr"},{"id":"2604.03322","title":"VitaTouch: Property-Aware Vision-Tactile-Language Model for Robotic Quality Inspection in Manufacturing","created":"2026-04-02","cited_by_count":2,"area":null},{"id":"2605.20110","title":"SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction","created":"2026-05-19","cited_by_count":2,"area":null},{"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":"2605.23116","title":"CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection","created":"2026-05-22","cited_by_count":2,"area":"lr"},{"id":"2406.07572","title":"Domain-specific ReAct for physics-integrated iterative modeling: A case study of LLM agents for gas path analysis of gas turbines","created":"2024-06-01","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}