{"total":125,"rows":[{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267,"area":null},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2504.05506","title":"ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering","created":"2025-04-07","cited_by_count":108,"area":null},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85,"area":null},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2110.11624","title":"SciCap: Generating Captions for Scientific Figures","created":"2021-10-22","cited_by_count":77,"area":null},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"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,"area":null},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66,"area":null},{"id":"2210.06628","title":"OpenCQA: Open-ended Question Answering with Charts","created":"2022-10-12","cited_by_count":61,"area":null},{"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,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"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,"area":null},{"id":"2407.15838","title":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","created":"2024-07-22","cited_by_count":38,"area":null},{"id":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35,"area":null},{"id":"2210.11248","title":"OCR-VQGAN: Taming Text-within-Image Generation","created":"2022-10-19","cited_by_count":31,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2304.06447","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","created":"2023-04-13","cited_by_count":28,"area":null},{"id":"2205.03966","title":"Chart Question Answering: State of the Art and Future Directions","created":"2022-05-08","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2304.02173","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","created":"2023-04-05","cited_by_count":24,"area":null},{"id":"2306.03491","title":"SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning","created":"2023-06-06","cited_by_count":24,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2205.13724","title":"V-Doc : Visual questions answers with Documents","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2207.07243","title":"LineCap: Line Charts for Data Visualization Captioning Models","created":"2022-07-15","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2305.18641","title":"Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs","created":"2023-05-29","cited_by_count":15,"area":null},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2110.00711","title":"Asking questions on handwritten document collections","created":"2021-10-02","cited_by_count":14,"area":null},{"id":"2302.12324","title":"Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization","created":"2023-02-23","cited_by_count":14,"area":null},{"id":"2506.08666","title":"LLaVA-c: Continual Improved Visual Instruction Tuning","created":"2025-06-10","cited_by_count":14,"area":null},{"id":"2108.06897","title":"AutoChart: A Dataset for Chart-to-Text Generation Task","created":"2021-08-16","cited_by_count":13,"area":null},{"id":"2309.08379","title":"PatFig: Generating Short and Long Captions for Patent Figures","created":"2023-09-15","cited_by_count":12,"area":null},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2110.01839","title":"Truth-Conditional Captioning of Time Series Data","created":"2021-10-05","cited_by_count":11,"area":null},{"id":"2111.14792","title":"Classification-Regression for Chart Comprehension","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2301.12293","title":"ACL-Fig: A Dataset for Scientific Figure Classification","created":"2023-01-28","cited_by_count":10,"area":null},{"id":"2503.18435","title":"On the Perception Bottleneck of VLMs for Chart Understanding","created":"2025-03-24","cited_by_count":10,"area":null},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2406.10228","title":"VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2506.04585","title":"MuSciClaims: Multimodal Scientific Claim Verification","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2507.19492","title":"ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation","created":"2025-05-31","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2601.04390","title":"SciFig: Towards Automating Editable Figure Generation for Scientific Papers","created":"2026-01-07","cited_by_count":8,"area":null},{"id":"2502.15803","title":"Megrez-Omni Technical Report","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2509.22437","title":"Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2409.19747","title":"Natural Language Generation for Visualizations: State of the Art, Challenges and Future Directions","created":"2024-09-29","cited_by_count":6,"area":null},{"id":"2501.02552","title":"Multi-LLM Collaborative Caption Generation in Scientific Documents","created":"2025-01-05","cited_by_count":6,"area":null},{"id":"2403.17784","title":"SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratings","created":"2024-03-26","cited_by_count":5,"area":null},{"id":"2412.17606","title":"SBS Figures: Pre-training Figure QA from Stage-by-Stage Synthesized Images","created":"2024-12-23","cited_by_count":5,"area":null},{"id":"2505.15046","title":"ChartCards: A Chart-Metadata Generation Framework for Multi-Task Chart Understanding","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2507.22890","title":"Evaluating LLMs for Visualization Generation and Understanding","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2402.08756","title":"Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2505.17473","title":"InfoDet: A Dataset for Infographic Element Detection","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2310.18983","title":"DCQA: Document-Level Chart Question Answering towards Complex Reasoning and Common-Sense Understanding","created":"2023-10-29","cited_by_count":3,"area":null},{"id":"2410.13883","title":"Transformers Utilization in Chart Understanding: A Review of Recent Advances & Future Trends","created":"2024-10-05","cited_by_count":3,"area":null},{"id":"2503.00086","title":"Generalization of CNNs on Relational Reasoning with Bar Charts","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2503.04065","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2504.11441","title":"TADACap: Time-series Adaptive Domain-Aware Captioning","created":"2025-04-15","cited_by_count":3,"area":null},{"id":"2504.17502","title":"RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2507.01627","title":"Chart Question Answering from Real-World Analytical Narratives","created":"2025-07-02","cited_by_count":3,"area":null},{"id":"2603.06958","title":"Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards","created":"2026-03-07","cited_by_count":3,"area":null},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2111.14103","title":"CHARTER: heatmap-based multi-type chart data extraction","created":"2021-11-28","cited_by_count":2,"area":null},{"id":"2112.03485","title":"VizExtract: Automatic Relation Extraction from Data Visualizations","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2509.13282","title":"ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement","created":"2025-09-16","cited_by_count":2,"area":null},{"id":"2601.02285","title":"pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.18238","title":"TechING: Towards Real World Technical Image Understanding via VLMs","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2603.12249","title":"SciMDR: Advancing Scientific Multimodal Document Reasoning","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2603.28902","title":"ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.22239","title":"Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.12154","title":"MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.29446","title":"CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2301.12032","title":"BinaryVQA: A Versatile Test Set to Evaluate the Out-of-Distribution Generalization of VQA Models","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2503.15176","title":"A Review on Large Language Models for Visual Analytics","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2505.10043","title":"Boosting Text-to-Chart Retrieval through Training with Synthesized Semantic Insights","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2505.17235","title":"CHAOS: Chart Analysis with Outlier Samples","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2602.10138","title":"Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2604.14941","title":"Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language Descriptions","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.26994","title":"ChartAct: A Benchmark for Dynamic Chart Understanding","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.27298","title":"Self-Ensembling Vision-Language Models for Chart Data Extraction","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2609.32041","title":"Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2211.08863","title":"ChartParser: Automatic Chart Parsing for Print-Impaired","created":"2022-11-16","cited_by_count":0,"area":null},{"id":"2211.14362","title":"Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2306.11699","title":"GenPlot: Increasing the Scale and Diversity of Chart Derendering Data","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2406.03087","title":"Lossless Image Compression Using Multi-level Dictionaries: Binary Images","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2406.17437","title":"Advancing Question Answering on Handwritten Documents: A State-of-the-Art Recognition-Based Model for HW-SQuAD","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2506.10996","title":"Evaluating LLMs for Visualization Tasks","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2510.06071","title":"Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks","created":"2025-10-07","cited_by_count":0,"area":null}],"next_cursor":"100"}