{"total":553,"rows":[{"id":"2204.08387","title":"LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking","created":"2022-04-18","cited_by_count":485,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256,"area":null},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245,"area":null},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224,"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":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"area":null},{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174,"area":"mllm"},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168,"area":"mllm"},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"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":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148,"area":null},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140,"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":"2212.09662","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","created":"2022-12-19","cited_by_count":133,"area":"lr"},{"id":"2502.18443","title":"olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models","created":"2025-02-25","cited_by_count":125,"area":"mllm"},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117,"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":"2202.13669","title":"LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding","created":"2022-02-28","cited_by_count":107,"area":null},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106,"area":"mllm"},{"id":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105,"area":null},{"id":"2108.04539","title":"BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents","created":"2021-08-10","cited_by_count":104,"area":null},{"id":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95,"area":"mllm"},{"id":"2105.11210","title":"StructuralLM: Structural Pre-training for Form Understanding","created":"2021-05-24","cited_by_count":91,"area":null},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88,"area":null},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85,"area":null},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82,"area":null},{"id":"2207.11871","title":"Towards Complex Document Understanding By Discrete Reasoning","created":"2022-07-25","cited_by_count":82,"area":null},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82,"area":null},{"id":"2205.11029","title":"META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI","created":"2022-05-23","cited_by_count":81,"area":null},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80,"area":null},{"id":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79,"area":null},{"id":"2403.19128","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","created":"2024-03-28","cited_by_count":74,"area":null},{"id":"2203.16618","title":"End-to-end Document Recognition and Understanding with Dessurt","created":"2022-03-30","cited_by_count":73,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2412.18424","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","created":"2024-12-24","cited_by_count":72,"area":"lr"},{"id":"2402.11941","title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","created":"2024-02-19","cited_by_count":70,"area":"mllm"},{"id":"2407.19056","title":"OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation","created":"2024-07-26","cited_by_count":70,"area":"agents"},{"id":"2104.01767","title":"WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach","created":"2021-04-05","cited_by_count":69,"area":null},{"id":"2203.06947","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","created":"2022-03-14","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":"2210.06155","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","created":"2022-10-12","cited_by_count":67,"area":null},{"id":"2102.06732","title":"Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64,"area":null},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"area":null},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58,"area":null},{"id":"2105.00377","title":"MathBERT: A Pre-Trained Model for Mathematical Formula Understanding","created":"2021-05-02","cited_by_count":58,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","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":"2302.11097","title":"A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram","created":"2023-02-22","cited_by_count":56,"area":"lr"},{"id":"2305.07498","title":"Visual Information Extraction in the Wild: Practical Dataset and End-to-end Solution","created":"2023-05-12","cited_by_count":54,"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":"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":"2402.05121","title":"Large Language Model for Table Processing: A Survey","created":"2024-02-04","cited_by_count":52,"area":null},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47,"area":"mllm"},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46,"area":null},{"id":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45,"area":null},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2501.08828","title":"MMDocIR: Benchmarking Multimodal Retrieval for Long Documents","created":"2025-01-15","cited_by_count":43,"area":null},{"id":"2201.09745","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","created":"2022-01-24","cited_by_count":42,"area":null},{"id":"2105.06220","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","created":"2021-05-13","cited_by_count":40,"area":null},{"id":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40,"area":null},{"id":"2308.15996","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","created":"2023-08-30","cited_by_count":40,"area":null},{"id":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39,"area":null},{"id":"2303.05063","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","created":"2023-03-09","cited_by_count":38,"area":null},{"id":"2309.10952","title":"LMDX: Language Model-based Document Information Extraction and Localization","created":"2023-09-19","cited_by_count":37,"area":null},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"id":"2405.11029","title":"Generative Artificial Intelligence: A Systematic Review and Applications","created":"2024-05-17","cited_by_count":37,"area":null},{"id":"2308.14221","title":"High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net","created":"2023-08-27","cited_by_count":36,"area":null},{"id":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35,"area":null},{"id":"2211.15421","title":"VRDU: A Benchmark for Visually-rich Document Understanding","created":"2022-11-15","cited_by_count":35,"area":null},{"id":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35,"area":"mllm"},{"id":"2202.00217","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","created":"2022-02-01","cited_by_count":34,"area":null},{"id":"2206.00311","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","created":"2022-06-01","cited_by_count":34,"area":null},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2111.13359","title":"Neural Collaborative Graph Machines for Table Structure Recognition","created":"2021-11-26","cited_by_count":30,"area":null},{"id":"2105.11672","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","created":"2021-05-25","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":"2412.08746","title":"DocVLM: Make Your VLM an Efficient Reader","created":"2024-12-11","cited_by_count":28,"area":"mllm"},{"id":"2106.00676","title":"VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups","created":"2021-06-01","cited_by_count":27,"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":"2203.09629","title":"HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2503.17213","title":"PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction","created":"2025-03-21","cited_by_count":26,"area":null},{"id":"2311.13194","title":"Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs","created":"2023-11-22","cited_by_count":25,"area":"mllm"},{"id":"2203.13530","title":"Multimodal Pre-training Based on Graph Attention Network for Document Understanding","created":"2022-03-25","cited_by_count":24,"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}],"next_cursor":"100"}