{"total":97,"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":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"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":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"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":"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":"2304.10759","title":"GeoLayoutLM: Geometric Pre-training for Visual Information Extraction","created":"2023-04-21","cited_by_count":40,"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":"2211.15421","title":"VRDU: A Benchmark for Visually-rich Document Understanding","created":"2022-11-15","cited_by_count":35,"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":"2310.11016","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction","created":"2023-10-17","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":"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":"2303.13095","title":"Modeling Entities as Semantic Points for Visual Information Extraction in the Wild","created":"2023-03-23","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":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18,"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":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16,"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":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13,"area":null},{"id":"2210.02849","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2306.12106","title":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","created":"2023-06-21","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":"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":"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":"2208.08201","title":"Understanding Long Documents with Different Position-Aware Attentions","created":"2022-08-17","cited_by_count":7,"area":null},{"id":"2404.12720","title":"PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering","created":"2024-04-19","cited_by_count":7,"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":"2408.06345","title":"Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2412.17092","title":"SAIL: Sample-Centric In-Context Learning for Document Information Extraction","created":"2024-12-22","cited_by_count":6,"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":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2405.17336","title":"XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2408.11981","title":"Large Language Models for Page Stream Segmentation","created":"2024-08-21","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":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"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":"2306.08937","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2410.01609","title":"SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction","created":"2024-10-02","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":"2603.15118","title":"VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2211.05284","title":"FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information","created":"2022-11-10","cited_by_count":3,"area":null},{"id":"2310.16356","title":"A Multi-Modal Multilingual Benchmark for Document Image Classification","created":"2023-10-25","cited_by_count":3,"area":null},{"id":"2404.13067","title":"Towards Efficient Resume Understanding: A Multi-Granularity Multi-Modal Pre-Training Approach","created":"2024-04-13","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":"2409.11887","title":"DocMamba: Efficient Document Pre-training with State Space Model","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2207.13979","title":"Knowing Where and What: Unified Word Block Pretraining for Document Understanding","created":"2022-07-28","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":"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":"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},{"id":"2311.00693","title":"On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval","created":"2023-11-01","cited_by_count":2,"area":null},{"id":"2401.03472","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","created":"2024-01-07","cited_by_count":2,"area":null},{"id":"2402.13475","title":"Multi-scale Spatio-temporal Transformer-based Imbalanced Longitudinal Learning for Glaucoma Forecasting from Irregular Time Series Images","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2406.08757","title":"SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2412.09341","title":"Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2211.14777","title":"Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models","created":"2022-11-27","cited_by_count":1,"area":null},{"id":"2302.08948","title":"Entry Separation using a Mixed Visual and Textual Language Model: Application to 19th century French Trade Directories","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2305.04460","title":"Language Independent Neuro-Symbolic Semantic Parsing for Form Understanding","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2305.17219","title":"GVdoc: Graph-based Visual Document Classification","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2306.00750","title":"End-to-End Document Classification and Key Information Extraction using Assignment Optimization","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2310.14785","title":"Vision-Enhanced Semantic Entity Recognition in Document Images via Visually-Asymmetric Consistency Learning","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2408.01038","title":"UNER: A Unified Prediction Head for Named Entity Recognition in Visually-rich Documents","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2502.19202","title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2503.05488","title":"KIEval: Evaluation Metric for Document Key Information Extraction","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2503.12267","title":"An Efficient Deep Learning-Based Approach to Automating Invoice Document Validation","created":"2025-03-15","cited_by_count":1,"area":null},{"id":"2503.19658","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2507.08865","title":"Spatial ModernBERT: Spatial-Aware Transformer for Table and Key-Value Extraction in Financial Documents at Scale","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2601.07620","title":"PARL: Position-Aware Relation Learning Network for Document Layout Analysis","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2603.09392","title":"ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2305.14590","title":"RE$^2$: Region-Aware Relation Extraction from Visually Rich Documents","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2308.15517","title":"Document AI: A Comparative Study of Transformer-Based, Graph-Based Models, and Convolutional Neural Networks For Document Layout Analysis","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2310.16527","title":"Enhancing Document Information Analysis with Multi-Task Pre-training: A Robust Approach for Information Extraction in Visually-Rich Documents","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2312.03367","title":"Lazy-k: Decoding for Constrained Token Classification","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2401.09220","title":"UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents","created":"2024-01-17","cited_by_count":0,"area":null},{"id":"2403.15765","title":"Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2404.00488","title":"Noise-Aware Training of Layout-Aware Language Models","created":"2024-03-30","cited_by_count":0,"area":null},{"id":"2503.16664","title":"TextBite: A Historical Czech Document Dataset for Logical Page Segmentation","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2503.16854","title":"Generative Compositor for Few-Shot Visual Information Extraction","created":"2025-03-21","cited_by_count":0,"area":null},{"id":"2507.08606","title":"DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.23273","title":"SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2511.05547","title":"Automated Invoice Data Extraction: Using LLM and OCR","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2511.19919","title":"HybriDLA: Hybrid Generation for Document Layout Analysis","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.07179","title":"Enhancing knowledge tracing robustness for new question cold start in Intelligent Tutoring Systems","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.18115","title":"Layout-Aware Text Editing for Efficient Transformation of Academic PDFs to Markdown","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2512.23714","title":"PharmaShip: An Entity-Centric, Reading-Order-Supervised Benchmark for Chinese Pharmaceutical Shipping Documents","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2601.05470","title":"ROAP: A Reading-Order and Attention-Prior Pipeline for Optimizing Layout Transformers in Key Information Extraction","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2601.11425","title":"PubMed-OCR: PMC Open Access OCR Annotations","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.21824","title":"DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.26462","title":"A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2607.21780","title":"Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.00036","title":"XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.20868","title":"Identify, Locate, Link: End-to-End Key-Value Extraction from Document Images","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}