{"list":"other","total":51,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2504.07981","title":"ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use","created":"2025-04-04","cited_by_count":254},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"2506.03569","title":"MiMo-VL Technical Report","created":"2025-06-04","cited_by_count":115},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2305.16289","title":"Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation","created":"2023-05-25","cited_by_count":100},{"id":"2302.03298","title":"Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion","created":"2023-02-07","cited_by_count":81},{"id":"2306.04607","title":"GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation","created":"2023-06-07","cited_by_count":56},{"id":"2305.15316","title":"Training on Thin Air: Improve Image Classification with Generated Data","created":"2023-05-24","cited_by_count":50},{"id":"2503.19990","title":"LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?","created":"2025-03-25","cited_by_count":49},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46},{"id":"2409.05840","title":"MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct","created":"2024-09-09","cited_by_count":42},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41},{"id":"2405.14974","title":"LOVA3: Learning to Visual Question Answering, Asking and Assessment","created":"2024-05-23","cited_by_count":21},{"id":"2412.07012","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","created":"2024-12-09","cited_by_count":21},{"id":"2503.04229","title":"Synthetic Data is an Elegant GIFT for Continual Vision-Language Models","created":"2025-03-06","cited_by_count":21},{"id":"2508.06492","title":"Effective Training Data Synthesis for Improving MLLM Chart Understanding","created":"2025-08-08","cited_by_count":20},{"id":"2212.11237","title":"Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators","created":"2022-12-21","cited_by_count":17},{"id":"2408.04594","title":"Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models","created":"2024-08-08","cited_by_count":17},{"id":"2210.06886","title":"ImaginaryNet: Learning Object Detectors without Real Images and Annotations","created":"2022-10-13","cited_by_count":16},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12},{"id":"2504.14523","title":"Learning from Reasoning Failures via Synthetic Data Generation","created":"2025-04-20","cited_by_count":2}],"next_cursor":null}