{"list":"other","total":57,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"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":"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":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2109.10282","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","created":"2021-09-21","cited_by_count":279},{"id":"2311.17600","title":"MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models","created":"2023-11-29","cited_by_count":274},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249},{"id":"2406.18521","title":"CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs","created":"2024-06-26","cited_by_count":234},{"id":"2311.10774","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","created":"2023-11-15","cited_by_count":150},{"id":"2402.12185","title":"ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning","created":"2024-02-19","cited_by_count":128},{"id":"2305.16504","title":"On the Tool Manipulation Capability of Open-source Large Language Models","created":"2023-05-25","cited_by_count":122},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120},{"id":"2305.18279","title":"Contextual Object Detection with Multimodal Large Language Models","created":"2023-05-29","cited_by_count":100},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75},{"id":"2402.15052","title":"ToMBench: Benchmarking Theory of Mind in Large Language Models","created":"2024-02-23","cited_by_count":72},{"id":"2308.03349","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","created":"2023-08-07","cited_by_count":68},{"id":"2401.08276","title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception","created":"2024-01-16","cited_by_count":65},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64},{"id":"2401.01523","title":"GOAT-Bench: Safety Insights to Large Multimodal Models through Meme-Based Social Abuse","created":"2024-01-03","cited_by_count":52},{"id":"2405.12523","title":"Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models","created":"2024-05-21","cited_by_count":46},{"id":"2404.09619","title":"UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark","created":"2024-04-15","cited_by_count":42},{"id":"2406.13246","title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","created":"2024-06-19","cited_by_count":33},{"id":"2403.07350","title":"VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark","created":"2024-03-12","cited_by_count":30},{"id":"2402.14835","title":"MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing","created":"2024-02-18","cited_by_count":25},{"id":"2406.13219","title":"MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency","created":"2024-06-19","cited_by_count":22},{"id":"2008.08899","title":"Document Visual Question Answering Challenge 2020","created":"2020-08-20","cited_by_count":20},{"id":"2403.19322","title":"Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models","created":"2024-03-28","cited_by_count":18},{"id":"2404.04204","title":"Social Skill Training with Large Language Models","created":"2024-04-05","cited_by_count":15},{"id":"2401.02575","title":"Large Language Models for Social Networks: Applications, Challenges, and Solutions","created":"2024-01-04","cited_by_count":11},{"id":"2502.08211","title":"Quality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data Curation","created":"2025-02-12","cited_by_count":5},{"id":"2402.18169","title":"MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery","created":"2024-02-28","cited_by_count":3},{"id":"2503.05529","title":"PoSSUM: A Protocol for Surveying Social-media Users with Multimodal LLMs","created":"2025-03-07","cited_by_count":3},{"id":"2504.10166","title":"Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis","created":"2025-04-14","cited_by_count":2}],"next_cursor":null}