{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2011.08785","title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","created":"2020-11-17","cited_by_count":594},{"id":"2108.07610","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","created":"2021-08-17","cited_by_count":514},{"id":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"1911.02357","title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","created":"2019-11-06","cited_by_count":386},{"id":"2107.12571","title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","created":"2021-07-27","cited_by_count":321},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2403.12580","title":"Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection","created":"2024-03-19","cited_by_count":139},{"id":"2206.04325","title":"CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization","created":"2022-06-09","cited_by_count":135},{"id":"2403.05897","title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","created":"2024-03-09","cited_by_count":116},{"id":"2104.06064","title":"Mixed supervision for surface-defect detection: from weakly to fully supervised learning","created":"2021-04-13","cited_by_count":101},{"id":"2405.14325","title":"Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection","created":"2024-05-23","cited_by_count":93},{"id":"2104.13897","title":"Inpainting Transformer for Anomaly Detection","created":"2021-04-28","cited_by_count":91},{"id":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84},{"id":"2207.10298","title":"Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey","created":"2022-07-21","cited_by_count":68},{"id":"2210.04570","title":"The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization","created":"2022-10-10","cited_by_count":57},{"id":"2502.07601","title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models","created":"2025-02-11","cited_by_count":54},{"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},{"id":"2407.12276","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","created":"2024-07-17","cited_by_count":50},{"id":"2410.09453","title":"MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection","created":"2024-10-12","cited_by_count":47},{"id":"2310.07716","title":"PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection","created":"2023-10-11","cited_by_count":46},{"id":"2310.19070","title":"Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection","created":"2023-10-29","cited_by_count":39},{"id":"2503.10080","title":"Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection","created":"2025-03-13","cited_by_count":31},{"id":"2504.11914","title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","created":"2025-04-16","cited_by_count":28},{"id":"2412.14592","title":"Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal Properties","created":"2024-12-19","cited_by_count":26},{"id":"1902.06197","title":"Online PCB Defect Detector On A New PCB Defect Dataset","created":"2019-02-17","cited_by_count":25},{"id":"2501.05767","title":"Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models","created":"2025-01-10","cited_by_count":22},{"id":"2211.13968","title":"MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection","created":"2022-11-25","cited_by_count":19},{"id":"2505.22039","title":"OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning","created":"2025-05-28","cited_by_count":18},{"id":"2501.15795","title":"Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?","created":"2025-01-27","cited_by_count":17},{"id":"2507.21619","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","created":"2025-07-29","cited_by_count":12},{"id":"2503.20252","title":"LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions","created":"2025-03-26","cited_by_count":9},{"id":"2504.19524","title":"LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoning","created":"2025-04-28","cited_by_count":9},{"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},{"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}],"next_cursor":null}