{"list":"other","total":65,"rows":[{"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":"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":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2407.12772","title":"LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models","created":"2024-07-17","cited_by_count":353},{"id":"1801.08163","title":"DVQA: Understanding Data Visualizations via Question Answering","created":"2018-01-24","cited_by_count":340},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310},{"id":"1901.01588","title":"PyOD: A Python Toolbox for Scalable Outlier Detection","created":"2019-01-06","cited_by_count":222},{"id":"2401.16822","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","created":"2024-01-30","cited_by_count":184},{"id":"2407.06581","title":"Vision language models are blind: Failing to translate detailed visual features into words","created":"2024-07-09","cited_by_count":147},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120},{"id":"2307.05356","title":"VisText: A Benchmark for Semantically Rich Chart Captioning","created":"2023-06-28","cited_by_count":112},{"id":"2504.05506","title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","created":"2025-04-07","cited_by_count":108},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85},{"id":"2401.02384","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","created":"2024-01-04","cited_by_count":79},{"id":"2010.09142","title":"Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model","created":"2020-10-18","cited_by_count":78},{"id":"2210.06628","title":"OpenCQA: Open-ended Question Answering with Charts","created":"2022-10-12","cited_by_count":61},{"id":"2502.14846","title":"Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation","created":"2025-02-20","cited_by_count":58},{"id":"1907.12861","title":"LEAF-QA: Locate, Encode & Attend for Figure Question Answering","created":"2019-07-30","cited_by_count":54},{"id":"2403.12027","title":"From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models","created":"2024-03-18","cited_by_count":53},{"id":"2503.11576","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","created":"2025-03-14","cited_by_count":53},{"id":"2404.16635","title":"TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning","created":"2024-04-25","cited_by_count":52},{"id":"2405.07001","title":"ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering","created":"2024-05-11","cited_by_count":50},{"id":"2312.10160","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","created":"2023-12-15","cited_by_count":49},{"id":"2110.04406","title":"Accessible Visualization via Natural Language Descriptions: A Four-Level Model of Semantic Content","created":"2021-10-08","cited_by_count":39},{"id":"2305.03393","title":"Optimized Table Tokenization for Table Structure Recognition","created":"2023-05-05","cited_by_count":34},{"id":"2505.02024","title":"From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent","created":"2025-05-04","cited_by_count":33},{"id":"2304.13620","title":"ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries","created":"2023-04-26","cited_by_count":32},{"id":"2407.17291","title":"How Good (Or Bad) Are LLMs at Detecting Misleading Visualizations?","created":"2024-07-24","cited_by_count":27},{"id":"2407.20174","title":"Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning","created":"2024-07-29","cited_by_count":27},{"id":"2311.07453","title":"ChartCheck: Explainable Fact-Checking over Real-World Chart Images","created":"2023-11-13","cited_by_count":26},{"id":"2410.14179","title":"MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems","created":"2024-10-18","cited_by_count":24},{"id":"1812.10636","title":"Chart-Text: A Fully Automated Chart Image Descriptor","created":"2018-12-27","cited_by_count":20},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20},{"id":"2503.16632","title":"Benchmarking Visual Language Models on Standardized Visualization Literacy Tests","created":"2025-03-20","cited_by_count":20},{"id":"1711.05962","title":"Beagle: Automated Extraction and Interpretation of Visualizations from the Web","created":"2017-11-16","cited_by_count":19},{"id":"2404.19097","title":"Exploring the Capability of LLMs in Performing Low-Level Visual Analytic Tasks on SVG Data Visualizations","created":"2024-04-29","cited_by_count":18},{"id":"2504.04974","title":"Towards Visual Text Grounding of Multimodal Large Language Model","created":"2025-04-07","cited_by_count":18},{"id":"2207.07243","title":"LineCap: Line Charts for Data Visualization Captioning Models","created":"2022-07-15","cited_by_count":17},{"id":"2407.11229","title":"Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness","created":"2024-07-15","cited_by_count":17},{"id":"2505.19028","title":"InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts","created":"2025-05-25","cited_by_count":17},{"id":"2502.14949","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","created":"2025-02-20","cited_by_count":15},{"id":"2507.01955","title":"How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks","created":"2025-07-02","cited_by_count":14},{"id":"2503.09837","title":"On the Limitations of Vision-Language Models in Understanding Image Transforms","created":"2025-03-12","cited_by_count":13},{"id":"2209.13718","title":"A Dataset of Alt Texts from HCI Publications: Analyses and Uses Towards Producing More Descriptive Alt Texts of Data Visualizations in Scientific Papers","created":"2022-09-27","cited_by_count":11},{"id":"2506.02022","title":"Do You See Me : A Multidimensional Benchmark for Evaluating Visual Perception in Multimodal LLMs","created":"2025-05-28","cited_by_count":11},{"id":"2408.06837","title":"How Aligned are Human Chart Takeaways and LLM Predictions? A Case Study on Bar Charts with Varying Layouts","created":"2024-08-13","cited_by_count":10},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10},{"id":"2407.10996","title":"Visualization Literacy of Multimodal Large Language Models: A Comparative Study","created":"2024-06-24","cited_by_count":9},{"id":"2412.12150","title":"Rethinking Comprehensive Benchmark for Chart Understanding: A Perspective from Scientific Literature","created":"2024-12-11","cited_by_count":9},{"id":"2508.09716","title":"The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models","created":"2025-08-13","cited_by_count":7},{"id":"2502.15563","title":"Bridging vision language model (VLM) evaluation gaps with a framework for scalable and cost-effective benchmark generation","created":"2025-02-21","cited_by_count":6},{"id":"2505.15046","title":"ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding","created":"2025-05-21","cited_by_count":5},{"id":"2405.13580","title":"AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks","created":"2024-05-22","cited_by_count":3},{"id":"2503.20089","title":"MatplotAlt: A Python Library for Adding Alt Text to Matplotlib Figures in Computational Notebooks","created":"2025-03-25","cited_by_count":3},{"id":"2505.17374","title":"Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of Charts","created":"2025-05-23","cited_by_count":3},{"id":"2507.10024","title":"Qualitative Study for LLM-assisted Design Study Process: Strategies, Challenges, and Roles","created":"2025-07-14","cited_by_count":3},{"id":"2507.11939","title":"POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering","created":"2025-07-16","cited_by_count":3},{"id":"2405.19111","title":"Alt4Blind: A User Interface to Simplify Charts Alt-Text Creation","created":"2024-05-29","cited_by_count":2},{"id":"2505.16647","title":"Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models","created":"2025-05-22","cited_by_count":2},{"id":"2508.12192","title":"Playing telephone with generative models: \"verification disability,\" \"compelled reliance,\" and accessibility in data visualization","created":"2025-08-17","cited_by_count":2}],"next_cursor":null}