{"total":185,"rows":[{"id":"2307.10088","title":"Android in the Wild: A Large-Scale Dataset for Android Device Control","created":"2023-07-19","cited_by_count":319,"area":null},{"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":"2411.17465","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","created":"2024-11-26","cited_by_count":232,"area":null},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229,"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":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"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":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"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":"2503.15661","title":"UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction","created":"2025-03-19","cited_by_count":77,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2404.19205","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","created":"2024-04-30","cited_by_count":69,"area":null},{"id":"2306.00245","title":"From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces","created":"2023-05-31","cited_by_count":68,"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":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2312.03003","title":"Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation","created":"2023-12-04","cited_by_count":58,"area":null},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2305.13507","title":"Multimodal Automated Fact-Checking: A Survey","created":"2023-05-22","cited_by_count":53,"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":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2312.13108","title":"ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation","created":"2023-12-20","cited_by_count":45,"area":null},{"id":"2404.06369","title":"WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs","created":"2024-04-09","cited_by_count":44,"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":"2406.10227","title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos","created":"2024-06-14","cited_by_count":35,"area":null},{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"area":null},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"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":"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":"2306.00526","title":"Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering","created":"2023-06-01","cited_by_count":24,"area":null},{"id":"2402.04476","title":"Dual-View Visual Contextualization for Web Navigation","created":"2024-02-06","cited_by_count":24,"area":null},{"id":"2403.14252","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","created":"2024-03-21","cited_by_count":24,"area":null},{"id":"2311.00522","title":"Text Rendering Strategies for Pixel Language Models","created":"2023-11-01","cited_by_count":22,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"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":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2406.02547","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","created":"2024-06-04","cited_by_count":17,"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":"2411.11098","title":"MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild","created":"2024-11-17","cited_by_count":17,"area":null},{"id":"2508.16763","title":"WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation","created":"2025-08-22","cited_by_count":16,"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":"2308.12700","title":"A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions","created":"2023-08-24","cited_by_count":15,"area":null},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"id":"2409.05137","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","created":"2024-09-08","cited_by_count":15,"area":null},{"id":"2402.14073","title":"Improving Language Understanding from Screenshots","created":"2024-02-21","cited_by_count":14,"area":null},{"id":"2404.12500","title":"UIClip: A Data-driven Model for Assessing User Interface Design","created":"2024-04-18","cited_by_count":14,"area":null},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2403.00209","title":"ChartReformer: Natural Language-Driven Chart Image Editing","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2403.04822","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","created":"2024-03-07","cited_by_count":13,"area":null},{"id":"2310.07023","title":"Automatic Macro Mining from Interaction Traces at Scale","created":"2023-10-10","cited_by_count":12,"area":null},{"id":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2409.13148","title":"UniTabNet: Bridging Vision and Language Models for Enhanced Table Structure Recognition","created":"2024-09-20","cited_by_count":11,"area":null},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"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":"2405.18616","title":"Wavelet-Based Image Tokenizer for Vision Transformers","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2406.09606","title":"Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2407.09103","title":"DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2410.02179","title":"HATFormer: Historic Handwritten Arabic Text Recognition with Transformers","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2509.19768","title":"CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition","created":"2025-09-24","cited_by_count":9,"area":null},{"id":"2602.05998","title":"VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2404.19024","title":"Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2407.12594","title":"VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2409.14201","title":"LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinement","created":"2024-09-21","cited_by_count":8,"area":null},{"id":"2410.00201","title":"DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2501.15415","title":"OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery","created":"2025-01-26","cited_by_count":8,"area":null},{"id":"2601.03714","title":"Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR","created":"2026-01-07","cited_by_count":8,"area":null},{"id":"2309.14389","title":"Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2312.10175","title":"UniAR: A Unified model for predicting human Attention and Responses on visual content","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2408.15646","title":"{\\mu}gat: Improving Single-Page Document Parsing by Providing Multi-Page Context","created":"2024-08-28","cited_by_count":7,"area":null},{"id":"2510.26389","title":"Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2311.09808","title":"PixT3: Pixel-based Table-To-Text Generation","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2405.18240","title":"MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution","created":"2024-05-28","cited_by_count":6,"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":"2211.03256","title":"On Web-based Visual Corpus Construction for Visual Document Understanding","created":"2022-11-07","cited_by_count":5,"area":null},{"id":"2310.18343","title":"PHD: Pixel-Based Language Modeling of Historical Documents","created":"2023-10-22","cited_by_count":5,"area":null},{"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":"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":"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":"2505.07496","title":"DocVXQA: Context-Aware Visual Explanations for Document Question Answering","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2512.20174","title":"Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2304.14936","title":"Information Redundancy and Biases in Public Document Information Extraction Benchmarks","created":"2023-04-28","cited_by_count":4,"area":null},{"id":"2305.15080","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2406.06947","title":"CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only","created":"2024-06-11","cited_by_count":4,"area":null},{"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":"2505.15755","title":"Exploring The Visual Feature Space for Multimodal Neural Decoding","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2511.04910","title":"SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents","created":"2025-11-07","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":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2307.10471","title":"Classification of Visualization Types and Perspectives in Patents","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","created":"2023-09-21","cited_by_count":3,"area":null}],"next_cursor":"100"}