{"total":160,"rows":[{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"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":"2311.16483","title":"ChartLlama: A Multimodal LLM for Chart Understanding and Generation","created":"2023-11-27","cited_by_count":163,"area":"mllm"},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160,"area":"mllm"},{"id":"2407.15711","title":"AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?","created":"2024-07-22","cited_by_count":158,"area":"agents"},{"id":"2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","created":"2025-01-09","cited_by_count":134,"area":"lr"},{"id":"2402.12185","title":"ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning","created":"2024-02-19","cited_by_count":128,"area":"lr"},{"id":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"area":"mllm"},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120,"area":"lr"},{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98,"area":"mllm"},{"id":"2505.19255","title":"VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use","created":"2025-05-25","cited_by_count":90,"area":"lr"},{"id":"2510.14528","title":"PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model","created":"2025-10-16","cited_by_count":89,"area":"mllm"},{"id":"2404.13046","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","created":"2024-04-19","cited_by_count":83,"area":"mllm"},{"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,"area":"mllm"},{"id":"2312.11562","title":"A Survey of Reasoning with Foundation Models","created":"2023-12-17","cited_by_count":70,"area":"lr"},{"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":"2403.09028","title":"ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning","created":"2024-03-14","cited_by_count":68,"area":"lr"},{"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":"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,"area":"mllm"},{"id":"2312.10160","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","created":"2023-12-15","cited_by_count":49,"area":"mllm"},{"id":"2409.03277","title":"ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding","created":"2024-09-05","cited_by_count":46,"area":"moe"},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41,"area":"mllm"},{"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":"2505.20289","title":"VisualToolAgent (VisTA): A Reinforcement Learning Framework for Visual Tool Selection","created":"2025-05-26","cited_by_count":34,"area":"lr"},{"id":"2505.11935","title":"ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing","created":"2025-05-17","cited_by_count":32,"area":"mllm"},{"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,"area":"mllm"},{"id":"2311.07453","title":"ChartCheck: Explainable Fact-Checking over Real-World Chart Images","created":"2023-11-13","cited_by_count":26,"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":"2606.03264","title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","created":"2026-06-02","cited_by_count":21,"area":null},{"id":"2403.12596","title":"Chart-based Reasoning: Transferring Capabilities from LLMs to VLMs","created":"2024-03-19","cited_by_count":20,"area":"lr"},{"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":"2508.06492","title":"Effective Training Data Synthesis for Improving MLLM Chart Understanding","created":"2025-08-08","cited_by_count":20,"area":"synth"},{"id":"2309.11268","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","created":"2023-09-20","cited_by_count":19,"area":null},{"id":"2403.11236","title":"ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization","created":"2024-03-17","cited_by_count":19,"area":"lr"},{"id":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"area":"lr"},{"id":"2502.01977","title":"AutoGUI: Scaling GUI Grounding with Automatic Functionality Annotations from LLMs","created":"2025-02-04","cited_by_count":19,"area":"mllm"},{"id":"2508.13587","title":"Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation","created":"2025-08-19","cited_by_count":19,"area":"lr"},{"id":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17,"area":"agents"},{"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":"2409.19242","title":"SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement","created":"2024-09-28","cited_by_count":15,"area":null},{"id":"2403.00209","title":"ChartReformer: Natural Language-Driven Chart Image Editing","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2407.14506","title":"On Pre-training of Multimodal Language Models Customized for Chart Understanding","created":"2024-07-19","cited_by_count":13,"area":"mllm"},{"id":"2310.02804","title":"DOMINO: A Dual-System for Multi-step Visual Language Reasoning","created":"2023-10-04","cited_by_count":12,"area":"lr"},{"id":"2508.04650","title":"EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts","created":"2025-08-06","cited_by_count":12,"area":"mllm"},{"id":"2404.12689","title":"Can LLMs Understand Computer Networks? Towards a Virtual System Administrator","created":"2024-04-19","cited_by_count":11,"area":null},{"id":"2405.21013","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","created":"2024-05-31","cited_by_count":11,"area":"mllm"},{"id":"2412.05983","title":"Chimera: Improving Generalist Model with Domain-Specific Experts","created":"2024-12-08","cited_by_count":11,"area":"mllm"},{"id":"2503.23131","title":"RefChartQA: Grounding Visual Answer on Chart Images through Instruction Tuning","created":"2025-03-29","cited_by_count":11,"area":"mllm"},{"id":"2604.25884","title":"QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding","created":"2026-04-28","cited_by_count":11,"area":"mllm"},{"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":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2404.01548","title":"mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning","created":"2024-04-02","cited_by_count":9,"area":"lr"},{"id":"2311.01918","title":"Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review","created":"2023-11-03","cited_by_count":8,"area":null},{"id":"2410.20494","title":"MatViX: Multimodal Information Extraction from Visually Rich Articles","created":"2024-10-27","cited_by_count":8,"area":null},{"id":"2502.20503","title":"Protecting multimodal large language models against misleading visualizations","created":"2025-02-27","cited_by_count":8,"area":"mllm"},{"id":"2308.07743","title":"ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2405.00021","title":"SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials","created":"2024-02-22","cited_by_count":7,"area":"lr"},{"id":"2412.12567","title":"FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning","created":"2024-12-17","cited_by_count":7,"area":"lr"},{"id":"2503.12326","title":"Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots","created":"2025-03-16","cited_by_count":7,"area":"mllm"},{"id":"2505.23242","title":"ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering","created":"2025-05-29","cited_by_count":7,"area":"lr"},{"id":"2506.20743","title":"A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools","created":"2025-06-25","cited_by_count":7,"area":"agents"},{"id":"2405.07765","title":"TANQ: An open domain dataset of table answered questions","created":"2024-05-13","cited_by_count":6,"area":null},{"id":"2408.11735","title":"Clinical Insights: A Comprehensive Review of Language Models in Medicine","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2503.04095","title":"Chart-HQA: A Benchmark for Hypothetical Question Answering in Charts","created":"2025-03-06","cited_by_count":6,"area":"mllm"},{"id":"2505.18570","title":"VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis","created":"2025-05-24","cited_by_count":6,"area":null},{"id":"2508.21675","title":"Is this chart lying to me? Automating the detection of misleading visualizations","created":"2025-08-29","cited_by_count":6,"area":null},{"id":"2512.00305","title":"ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning","created":"2025-11-29","cited_by_count":6,"area":"lr"},{"id":"2311.09612","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2405.19094","title":"Faithful Chart Summarization with ChaTS-Pi","created":"2024-05-29","cited_by_count":5,"area":null},{"id":"2407.21038","title":"Advancing Chart Question Answering with Robust Chart Component Recognition","created":"2024-07-19","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":"2501.04675","title":"Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations","created":"2025-01-08","cited_by_count":5,"area":"mllm"},{"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":"2506.23061","title":"Empowering Small VLMs to Think with Dynamic Memorization and Exploration","created":"2025-06-29","cited_by_count":5,"area":"lr"},{"id":"2507.03262","title":"Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders","created":"2025-07-04","cited_by_count":5,"area":"mllm"},{"id":"2509.18425","title":"Losing the Plot: How VLM responses degrade on imperfect charts","created":"2025-09-22","cited_by_count":5,"area":"mllm"},{"id":"2602.16455","title":"Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing","created":"2026-02-18","cited_by_count":5,"area":"mllm"},{"id":"2403.00816","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","created":"2024-02-26","cited_by_count":4,"area":"lr"},{"id":"2407.14133","title":"I Know About \"Up\"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction","created":"2024-07-19","cited_by_count":4,"area":"lr"},{"id":"2412.20715","title":"ChartAdapter: Large Vision-Language Model for Chart Summarization","created":"2024-12-30","cited_by_count":4,"area":"mllm"},{"id":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2509.09286","title":"Visual Programmability: A Guide for Code-as-Thought in Chart Understanding","created":"2025-09-11","cited_by_count":4,"area":"lr"},{"id":"2512.14040","title":"ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2501.11233","title":"PlotEdit: Natural Language-Driven Accessible Chart Editing in PDFs via Multimodal LLM Agents","created":"2025-01-20","cited_by_count":3,"area":null},{"id":"2504.09764","title":"Socratic Chart: Cooperating Multiple Agents for Robust SVG Chart Understanding","created":"2025-04-14","cited_by_count":3,"area":"mllm"},{"id":"2505.17374","title":"Chart-to-Experience: Benchmarking Multimodal LLMs for Predicting Experiential Impact of Charts","created":"2025-05-23","cited_by_count":3,"area":"mllm"},{"id":"2505.19360","title":"ChartLens: Fine-grained Visual Attribution in Charts","created":"2025-05-25","cited_by_count":3,"area":"mllm"},{"id":"2507.14298","title":"In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart Understanding","created":"2025-07-18","cited_by_count":3,"area":"mllm"},{"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":"2603.24326","title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","created":"2026-03-25","cited_by_count":3,"area":"mllm"},{"id":"2408.04852","title":"MSG-Chart: Multimodal Scene Graph for ChartQA","created":"2024-08-09","cited_by_count":2,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2506.08700","title":"ClimateViz: A Benchmark for Statistical Reasoning and Fact Verification on Scientific Charts","created":"2025-06-10","cited_by_count":2,"area":"lr"},{"id":"2507.20046","title":"Infogen: Generating Complex Statistical Infographics from Documents","created":"2025-07-26","cited_by_count":2,"area":null},{"id":"2510.07098","title":"TALENT: Table VQA via Augmented Language-Enhanced Natural-text Transcription","created":"2025-10-08","cited_by_count":2,"area":"mllm"}],"next_cursor":"100"}