{"total":351,"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":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347,"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":"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":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173,"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":"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":"2303.08137","title":"LayoutDM: Discrete Diffusion Model for Controllable Layout Generation","created":"2023-03-14","cited_by_count":143,"area":"diffusion"},{"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":"2301.10140","title":"The Semantic Scholar Open Data Platform","created":"2023-01-24","cited_by_count":118,"area":null},{"id":"2106.03331","title":"SelfDoc: Self-Supervised Document Representation Learning","created":"2021-06-07","cited_by_count":117,"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":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97,"area":null},{"id":"2108.01249","title":"CanvasVAE: Learning to Generate Vector Graphic Documents","created":"2021-08-03","cited_by_count":95,"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":"2203.01017","title":"TableFormer: Table Structure Understanding with Transformers","created":"2022-03-02","cited_by_count":94,"area":null},{"id":"2104.02416","title":"Variational Transformer Networks for Layout Generation","created":"2021-04-06","cited_by_count":88,"area":null},{"id":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85,"area":null},{"id":"2108.00871","title":"Constrained Graphic Layout Generation via Latent Optimization","created":"2021-08-02","cited_by_count":83,"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":"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":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","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":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"area":null},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","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":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2305.02567","title":"LayoutDM: Transformer-based Diffusion Model for Layout Generation","created":"2023-05-04","cited_by_count":57,"area":"diffusion"},{"id":"2311.06495","title":"LayoutPrompter: Awaken the Design Ability of Large Language Models","created":"2023-11-11","cited_by_count":48,"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":"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":"2305.10825","title":"DiffUTE: Universal Text Editing Diffusion Model","created":"2023-05-18","cited_by_count":45,"area":"diffusion"},{"id":"2206.05224","title":"A Multi-Task Benchmark for Korean Legal Language Understanding and Judgement Prediction","created":"2022-06-10","cited_by_count":44,"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":"2208.08037","title":"LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction","created":"2022-08-17","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":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2303.05049","title":"Unifying Layout Generation with a Decoupled Diffusion Model","created":"2023-03-09","cited_by_count":41,"area":"diffusion"},{"id":"2303.11589","title":"LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models","created":"2023-03-21","cited_by_count":41,"area":"diffusion"},{"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":"2404.14368","title":"Graphic Design with Large Multimodal Model","created":"2024-04-22","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":"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":"2505.19114","title":"CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design","created":"2025-05-25","cited_by_count":36,"area":"diffusion"},{"id":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35,"area":null},{"id":"2305.03393","title":"Optimized Table Tokenization for Table Structure Recognition","created":"2023-05-05","cited_by_count":34,"area":null},{"id":"2209.00852","title":"Geometry Aligned Variational Transformer for Image-conditioned Layout Generation","created":"2022-09-02","cited_by_count":33,"area":null},{"id":"2411.18499","title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","created":"2024-11-27","cited_by_count":31,"area":"mllm"},{"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":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"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":"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":"2402.04754","title":"Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints","created":"2024-02-07","cited_by_count":26,"area":"diffusion"},{"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":"2110.14968","title":"DocScanner: Robust Document Image Rectification with Progressive Learning","created":"2021-10-28","cited_by_count":25,"area":null},{"id":"2203.16850","title":"Revisiting Document Image Dewarping by Grid Regularization","created":"2022-03-31","cited_by_count":25,"area":null},{"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":"2301.11529","title":"PLay: Parametrically Conditioned Layout Generation using Latent Diffusion","created":"2023-01-27","cited_by_count":24,"area":"diffusion"},{"id":"2303.14884","title":"A large-scale dataset for end-to-end table recognition in the wild","created":"2023-03-27","cited_by_count":24,"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":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","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":"2502.16161","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","created":"2025-02-22","cited_by_count":23,"area":"lr"},{"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":"2403.18187","title":"LayoutFlow: Flow Matching for Layout Generation","created":"2024-03-27","cited_by_count":21,"area":"diffusion"},{"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":"2203.08504","title":"A Survey of Historical Document Image Datasets","created":"2022-03-16","cited_by_count":20,"area":null},{"id":"2210.05391","title":"PP-StructureV2: A Stronger Document Analysis System","created":"2022-10-11","cited_by_count":20,"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":"2303.03755","title":"DLT: Conditioned layout generation with Joint Discrete-Continuous Diffusion Layout Transformer","created":"2023-03-07","cited_by_count":20,"area":"diffusion"},{"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":"2201.11438","title":"DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer","created":"2022-01-27","cited_by_count":19,"area":null},{"id":"2205.13724","title":"V-Doc : Visual questions answers with Documents","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2309.09506","title":"LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models","created":"2023-09-18","cited_by_count":19,"area":null},{"id":"2311.15941","title":"Tell2Design: A Dataset for Language-Guided Floor Plan Generation","created":"2023-11-27","cited_by_count":19,"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":"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":"2107.02638","title":"DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis","created":"2021-07-06","cited_by_count":17,"area":null},{"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":"2101.12741","title":"Post-OCR Paragraph Recognition by Graph Convolutional Networks","created":"2021-01-29","cited_by_count":16,"area":null},{"id":"2203.04814","title":"Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2505.24878","title":"Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents","created":"2025-05-30","cited_by_count":16,"area":"mllm"},{"id":"2105.06400","title":"TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables","created":"2021-05-12","cited_by_count":15,"area":null},{"id":"2212.09877","title":"LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer","created":"2022-12-19","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":"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":"2405.06706","title":"Exploring the Capabilities of Large Multimodal Models on Dense Text","created":"2024-05-09","cited_by_count":14,"area":"mllm"}],"next_cursor":"100"}