{"list":"other","total":54,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2201.10703","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","created":"2022-01-26","cited_by_count":421},{"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":"2505.07062","title":"Seed1.5-VL Technical Report","created":"2025-05-11","cited_by_count":373},{"id":"2501.00656","title":"2 OLMo 2 Furious","created":"2024-12-31","cited_by_count":340},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"2206.03687","title":"A Unified Model for Multi-class Anomaly Detection","created":"2022-06-08","cited_by_count":268},{"id":"2201.01293","title":"A Transformer-Based Siamese Network for Change Detection","created":"2022-01-04","cited_by_count":244},{"id":"2506.07044","title":"Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning","created":"2025-06-08","cited_by_count":230},{"id":"2303.14535","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","created":"2023-03-25","cited_by_count":160},{"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":"2407.15795","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","created":"2024-07-22","cited_by_count":127},{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2404.05231","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","created":"2024-04-08","cited_by_count":98},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73},{"id":"2403.14233","title":"SoftPatch: Unsupervised Anomaly Detection with Noisy Data","created":"2024-03-21","cited_by_count":55},{"id":"2401.16753","title":"MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images","created":"2024-01-30","cited_by_count":52},{"id":"2304.01091","title":"Changes to Captions: An Attentive Network for Remote Sensing Change Captioning","created":"2023-04-03","cited_by_count":41},{"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},{"id":"2410.14987","title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","created":"2024-10-19","cited_by_count":27},{"id":"2412.04867","title":"MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects","created":"2024-12-06","cited_by_count":26},{"id":"2307.04956","title":"PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation","created":"2023-07-11","cited_by_count":21},{"id":"2403.11083","title":"Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning","created":"2024-03-17","cited_by_count":20},{"id":"2505.22039","title":"OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning","created":"2025-05-28","cited_by_count":18},{"id":"2408.04594","title":"Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models","created":"2024-08-08","cited_by_count":17},{"id":"2508.09178","title":"IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection","created":"2025-08-07","cited_by_count":17},{"id":"2407.05645","title":"OneDiff: A Generalist Model for Image Difference Captioning","created":"2024-07-08","cited_by_count":15},{"id":"2402.18998","title":"COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection","created":"2024-02-29","cited_by_count":13},{"id":"2411.19930","title":"On Domain-Adaptive Post-Training for Multimodal Large Language Models","created":"2024-11-29","cited_by_count":13},{"id":"2503.11093","title":"OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning","created":"2025-03-14","cited_by_count":12},{"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},{"id":"2507.21619","title":"EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO","created":"2025-07-29","cited_by_count":12},{"id":"2202.07006","title":"A Survey of Visual Sensory Anomaly Detection","created":"2022-02-14","cited_by_count":11},{"id":"2503.14162","title":"EIAD: Explainable Industrial Anomaly Detection Via Multi-Modal Large Language Models","created":"2025-03-18","cited_by_count":11},{"id":"2502.05761","title":"3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly","created":"2025-02-09","cited_by_count":10},{"id":"2510.00495","title":"Normal-Abnormal Guided Generalist Anomaly Detection","created":"2025-10-01","cited_by_count":10},{"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},{"id":"2403.14213","title":"Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference","created":"2024-03-21","cited_by_count":7},{"id":"2412.20870","title":"SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation","created":"2024-12-30","cited_by_count":7}],"next_cursor":null}