{"total":134,"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":"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":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"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":"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":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152,"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":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"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":"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":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98,"area":"mllm"},{"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":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85,"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":"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":"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":"2203.12273","title":"DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition","created":"2022-03-23","cited_by_count":62,"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":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","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":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39,"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":"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":"2202.00217","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","created":"2022-02-01","cited_by_count":34,"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":"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":"2401.03411","title":"GRAM: Global Reasoning for Multi-Page VQA","created":"2024-01-07","cited_by_count":23,"area":"lr"},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2304.14953","title":"CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data","created":"2023-04-28","cited_by_count":21,"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":"2212.09621","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","created":"2022-12-19","cited_by_count":20,"area":null},{"id":"2305.02549","title":"FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction","created":"2023-05-04","cited_by_count":20,"area":null},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19,"area":null},{"id":"2206.13155","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","created":"2022-06-27","cited_by_count":18,"area":"mllm"},{"id":"2309.01131","title":"Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration","created":"2023-09-03","cited_by_count":18,"area":null},{"id":"2208.11168","title":"Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks","created":"2022-08-23","cited_by_count":17,"area":null},{"id":"2305.18721","title":"LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding","created":"2023-05-30","cited_by_count":17,"area":null},{"id":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16,"area":null},{"id":"2206.04045","title":"STable: Table Generation Framework for Encoder-Decoder Models","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2205.12029","title":"VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification","created":"2022-05-24","cited_by_count":14,"area":null},{"id":"2402.14073","title":"Improving Language Understanding from Screenshots","created":"2024-02-21","cited_by_count":14,"area":null},{"id":"2305.04609","title":"SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation","created":"2023-05-08","cited_by_count":13,"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":"2409.19672","title":"Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding","created":"2024-09-29","cited_by_count":12,"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":"2209.08569","title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","created":"2022-09-18","cited_by_count":9,"area":null},{"id":"2211.14958","title":"MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2304.07957","title":"A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images","created":"2023-04-17","cited_by_count":9,"area":null},{"id":"2402.09841","title":"LAPDoc: Layout-Aware Prompting for Documents","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2403.19454","title":"JDocQA: Japanese Document Question Answering Dataset for Generative Language Models","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2505.13535","title":"Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments","created":"2025-05-18","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":"2310.16131","title":"GenKIE: Robust Generative Multimodal Document Key Information Extraction","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2404.04003","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","created":"2024-04-05","cited_by_count":8,"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":"2311.08623","title":"DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models","created":"2023-11-15","cited_by_count":7,"area":"inference"},{"id":"2207.06744","title":"TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents","created":"2022-07-14","cited_by_count":6,"area":null},{"id":"2306.02623","title":"Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2401.02823","title":"DocGraphLM: Documental Graph Language Model for Information Extraction","created":"2024-01-05","cited_by_count":6,"area":null},{"id":"2403.04080","title":"Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis","created":"2024-03-06","cited_by_count":6,"area":null},{"id":"2404.17888","title":"A Hybrid Approach for Document Layout Analysis in Document images","created":"2024-04-27","cited_by_count":6,"area":null},{"id":"2502.18179","title":"Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2305.01938","title":"Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphs","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2305.02577","title":"Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation","created":"2023-05-04","cited_by_count":5,"area":null},{"id":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","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":"2505.07496","title":"DocVXQA: Context-Aware Visual Explanations for Document Question Answering","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2507.12441","title":"Describe Anything Model for Visual Question Answering on Text-rich Images","created":"2025-07-16","cited_by_count":5,"area":"mllm"},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2301.11312","title":"LoRaLay: A Multilingual and Multimodal Dataset for Long Range and Layout-Aware Summarization","created":"2023-01-26","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":"2306.08937","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2407.03830","title":"DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2410.10471","title":"ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training","created":"2024-10-14","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":"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":"2202.06080","title":"Recognition-free Question Answering on Handwritten Document Collections","created":"2022-02-12","cited_by_count":3,"area":null},{"id":"2309.05429","title":"Improving Information Extraction on Business Documents with Specific Pre-Training Tasks","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2405.00260","title":"CREPE: Coordinate-Aware End-to-End Document Parser","created":"2024-05-01","cited_by_count":3,"area":null},{"id":"2405.03104","title":"GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2409.11887","title":"DocMamba: Efficient Document Pre-training with State Space Model","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2506.12116","title":"Unsupervised Document and Template Clustering using Multimodal Embeddings","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2510.26615","title":"SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2111.04045","title":"Information Extraction from Visually Rich Documents with Font Style Embeddings","created":"2021-11-07","cited_by_count":2,"area":null},{"id":"2205.08094","title":"MATrIX -- Modality-Aware Transformer for Information eXtraction","created":"2022-05-17","cited_by_count":2,"area":null},{"id":"2305.10448","title":"Sequence-to-Sequence Pre-training with Unified Modality Masking for Visual Document Understanding","created":"2023-05-16","cited_by_count":2,"area":null},{"id":"2305.13850","title":"Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2309.05503","title":"Long-Range Transformer Architectures for Document Understanding","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2310.02372","title":"ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks","created":"2023-10-03","cited_by_count":2,"area":null}],"next_cursor":"100"}