{"total":153,"rows":[{"id":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152,"area":null},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"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":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"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":"2104.08836","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","created":"2021-04-18","cited_by_count":103,"area":null},{"id":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101,"area":"mllm"},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100,"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":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90,"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":"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":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"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":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46,"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":"2409.03643","title":"Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matching","created":"2024-09-05","cited_by_count":41,"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":"2406.11633","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","created":"2024-06-17","cited_by_count":36,"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":"2203.09056","title":"Robust Table Detection and Structure Recognition from Heterogeneous Document Images","created":"2022-03-17","cited_by_count":30,"area":null},{"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":"2110.09915","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","created":"2021-10-19","cited_by_count":23,"area":null},{"id":"2303.13839","title":"HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures","created":"2023-03-24","cited_by_count":23,"area":null},{"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":"2303.10787","title":"Diffusion-based Document Layout Generation","created":"2023-03-19","cited_by_count":21,"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":"2410.21311","title":"MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding","created":"2024-10-25","cited_by_count":19,"area":"mllm"},{"id":"2208.10970","title":"Doc-GCN: Heterogeneous Graph Convolutional Networks for Document Layout Analysis","created":"2022-08-22","cited_by_count":17,"area":null},{"id":"2505.17104","title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2104.08405","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2401.11874","title":"Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis","created":"2024-01-22","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":"2502.14949","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","created":"2025-02-20","cited_by_count":15,"area":null},{"id":"2407.19787","title":"SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters","created":"2024-07-29","cited_by_count":14,"area":null},{"id":"2410.05970","title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","created":"2024-10-08","cited_by_count":14,"area":"mllm"},{"id":"2303.05325","title":"BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset","created":"2023-03-09","cited_by_count":13,"area":null},{"id":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","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":"2502.08417","title":"Handwritten Text Recognition: A Survey","created":"2025-02-12","cited_by_count":12,"area":null},{"id":"2205.02411","title":"Relational Representation Learning in Visually-Rich Documents","created":"2022-05-05","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":"2402.09841","title":"LAPDoc: Layout-Aware Prompting for Documents","created":"2024-02-15","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":"2109.01078","title":"Skim-Attention: Learning to Focus via Document Layout","created":"2021-09-02","cited_by_count":7,"area":null},{"id":"2305.02769","title":"Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2306.13526","title":"Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images","created":"2023-06-23","cited_by_count":7,"area":null},{"id":"2310.09118","title":"DSG: An End-to-End Document Structure Generator","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2312.10188","title":"WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data","created":"2023-12-15","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":"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":"2208.11203","title":"Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documents","created":"2022-08-23","cited_by_count":6,"area":null},{"id":"2305.14962","title":"ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2111.06016","title":"Synthetic Document Generator for Annotation-free Layout Recognition","created":"2021-11-11","cited_by_count":5,"area":null},{"id":"2505.14381","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"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":"2602.15958","title":"DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2101.10281","title":"PAWLS: PDF Annotation With Labels and Structure","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2306.01058","title":"Are Layout-Infused Language Models Robust to Layout Distribution Shifts? A Case Study with Scientific Documents","created":"2023-06-01","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":"2408.14764","title":"SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2410.15484","title":"\"What is the value of {templates}?\" Rethinking Document Information Extraction Datasets for LLMs","created":"2024-10-20","cited_by_count":4,"area":"lr"},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2302.01451","title":"CTE: A Dataset for Contextualized Table Extraction","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2306.05749","title":"DocAligner: Annotating Real-world Photographic Document Images by Simply Taking Pictures","created":"2023-06-09","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":"2510.26615","title":"SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2604.08115","title":"Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2606.26122","title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2106.15320","title":"ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and Dissertations","created":"2021-06-23","cited_by_count":2,"area":null},{"id":"2108.02095","title":"Human-In-The-Loop Document Layout Analysis","created":"2021-08-04","cited_by_count":2,"area":null},{"id":"2108.09436","title":"Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts","created":"2021-08-21","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":"2307.09047","title":"Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)","created":"2023-07-18","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":"2309.09742","title":"Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels","created":"2023-09-18","cited_by_count":2,"area":null},{"id":"2310.18073","title":"A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2311.18481","title":"ESG Accountability Made Easy: DocQA at Your Service","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2402.09811","title":"TEXTRON: Weakly Supervised Multilingual Text Detection through Data Programming","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2403.18183","title":"Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2404.09530","title":"RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2405.19765","title":"Towards Unified Multi-granularity Text Detection with Interactive Attention","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2506.14079","title":"FormGym: Doing Paperwork with Agents","created":"2025-06-17","cited_by_count":2,"area":"agents"},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.26213","title":"OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2512.17221","title":"DAVE: A VLM Vision Encoder for Document Understanding and Web Agents","created":"2025-12-19","cited_by_count":2,"area":"mllm"},{"id":"2602.01559","title":"Combined Flicker-banding and Moire Removal for Screen-Captured Images","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.25761","title":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2105.14931","title":"Document Domain Randomization for Deep Learning Document Layout Extraction","created":"2021-05-20","cited_by_count":1,"area":null},{"id":"2108.08111","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","created":"2021-08-18","cited_by_count":1,"area":null},{"id":"2304.13240","title":"Structure Diagram Recognition in Financial Announcements","created":"2023-04-26","cited_by_count":1,"area":null}],"next_cursor":"100"}