{"total":125,"rows":[{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"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":"2302.11713","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","created":"2023-02-23","cited_by_count":207,"area":null},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180,"area":null},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171,"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":"2407.04172","title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","created":"2024-07-04","cited_by_count":79,"area":null},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"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":"2210.06628","title":"OpenCQA: Open-ended Question Answering with Charts","created":"2022-10-12","cited_by_count":61,"area":null},{"id":"2406.08418","title":"OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text","created":"2024-06-12","cited_by_count":59,"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":"2407.00981","title":"VisEval: A Benchmark for Data Visualization in the Era of Large Language Models","created":"2024-07-01","cited_by_count":45,"area":null},{"id":"2412.09604","title":"SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding","created":"2024-12-12","cited_by_count":42,"area":null},{"id":"2404.09987","title":"OneChart: Purify the Chart Structural Extraction via One Auxiliary Token","created":"2024-04-15","cited_by_count":39,"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":"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":"2311.07453","title":"ChartCheck: Explainable Fact-Checking over Real-World Chart Images","created":"2023-11-13","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":"2401.13478","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","created":"2024-01-24","cited_by_count":23,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","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":"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,"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":"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":"2108.06897","title":"AutoChart: A Dataset for Chart-to-Text Generation Task","created":"2021-08-16","cited_by_count":13,"area":null},{"id":"2403.00209","title":"ChartReformer: Natural Language-Driven Chart Image Editing","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2111.14792","title":"Classification-Regression for Chart Comprehension","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2312.10610","title":"Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization","created":"2023-12-17","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":"2507.21167","title":"ChartM$^3$: Benchmarking Chart Editing with Multimodal Instructions","created":"2025-07-25","cited_by_count":9,"area":null},{"id":"2308.01979","title":"RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic","created":"2023-08-03","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":"2506.15594","title":"WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts","created":"2025-06-18","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":"2509.22437","title":"Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2409.18475","title":"Data Analysis in the Era of Generative AI","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2307.02065","title":"Line Graphics Digitization: A Step Towards Full Automation","created":"2023-07-05","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":"2602.09809","title":"SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing","created":"2026-02-10","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":"2406.10085","title":"Enhancing Question Answering on Charts Through Effective Pre-training Tasks","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2410.21414","title":"CT2C-QA: Multimodal Question Answering over Chinese Text, Table and Chart","created":"2024-10-28","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":"2503.00086","title":"Generalization of CNNs on Relational Reasoning with Bar Charts","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2510.26781","title":"ChartAB: A Benchmark for Chart Grounding & Dense Alignment","created":"2025-10-30","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":"2410.09761","title":"ChartKG: A Knowledge-Graph-Based Representation for Chart Images","created":"2024-10-13","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":"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":"2606.01348","title":"ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2607.11192","title":"GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2607.26848","title":"ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures","created":"2026-07-29","cited_by_count":2,"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":"2506.16571","title":"Capturing Visualization Design Rationale","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2508.13184","title":"BERT-VQA: Visual Question Answering on Plots","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2510.01030","title":"Uncovering the Computational Ingredients of Human-Like Representations in LLMs","created":"2025-10-01","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":"2602.15915","title":"MaS-VQA: A Mask-and-Select Framework for Knowledge-Based Visual Question Answering","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2604.12306","title":"GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2605.00800","title":"Generating Statistical Charts with Validation-Driven LLM Workflows","created":"2026-05-01","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":"2606.27731","title":"Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.25911","title":"AnnoBench: A Benchmark for Visualization Annotation Generation","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","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":"2306.11699","title":"GenPlot: Increasing the Scale and Diversity of Chart Derendering Data","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2312.11146","title":"OsmLocator: locating overlapping scatter marks with a non-training generative perspective","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2509.18177","title":"A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts","created":"2025-09-17","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},{"id":"2512.12424","title":"ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.19173","title":"CycleChart: A Unified Consistency-Based Learning Framework for Bidirectional Chart Understanding and Generation","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2601.10462","title":"ChartComplete: A Taxonomy-based Inclusive Chart Dataset","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.12983","title":"ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.20084","title":"Do Large Language Models Understand Data Visualization Principles?","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.06677","title":"Chart Deep Research in LVLMs via Parallel Relative Policy Optimization","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.21344","title":"Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts","created":"2026-04-23","cited_by_count":0,"area":null}],"next_cursor":"100"}