{"total":72,"rows":[{"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":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90,"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":"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":"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":"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":"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":"2108.06543","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","created":"2021-08-14","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":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"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":"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":"2110.09915","title":"Entity Relation Extraction as Dependency Parsing in Visually Rich Documents","created":"2021-10-19","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":"2106.10786","title":"ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction","created":"2021-06-21","cited_by_count":22,"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":"2306.03287","title":"ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2106.12940","title":"MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction","created":"2021-06-24","cited_by_count":18,"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":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18,"area":null},{"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":"2104.08405","title":"LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2104.08041","title":"Cost-effective End-to-end Information Extraction for Semi-structured Document Images","created":"2021-04-16","cited_by_count":14,"area":null},{"id":"2506.20168","title":"Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models","created":"2025-06-25","cited_by_count":12,"area":"mllm"},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","cited_by_count":11,"area":null},{"id":"2505.17330","title":"FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding","created":"2025-05-22","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":"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":"2106.10681","title":"Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences","created":"2021-06-20","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":"2106.00978","title":"A Span Extraction Approach for Information Extraction on Visually-Rich Documents","created":"2021-06-02","cited_by_count":6,"area":null},{"id":"2207.04713","title":"GMN: Generative Multi-modal Network for Practical Document Information Extraction","created":"2022-07-11","cited_by_count":6,"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":"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":"2208.04011","title":"Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features","created":"2022-08-08","cited_by_count":5,"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":"2405.12842","title":"SmartFlow: Robotic Process Automation using LLMs","created":"2024-05-21","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":"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":"2602.07038","title":"UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2304.14044","title":"Large Scale Genealogical Information Extraction From Handwritten Quebec Parish Records","created":"2023-04-27","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":"2103.05908","title":"DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction","created":"2021-03-10","cited_by_count":3,"area":null},{"id":"2109.13967","title":"One-shot Key Information Extraction from Document with Deep Partial Graph Matching","created":"2021-09-26","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":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2309.05503","title":"Long-Range Transformer Architectures for Document Understanding","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2310.14802","title":"DocTrack: A Visually-Rich Document Dataset Really Aligned with Human Eye Movement for Machine Reading","created":"2023-10-23","cited_by_count":2,"area":null},{"id":"2410.01160","title":"GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2506.13363","title":"Efficient Medical VIE via Reinforcement Learning","created":"2025-06-16","cited_by_count":2,"area":"deeprl"},{"id":"2206.06890","title":"RDU: A Region-based Approach to Form-style Document Understanding","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2210.03453","title":"Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections","created":"2022-10-07","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":"2306.14374","title":"Transcending Traditional Boundaries: Leveraging Inter-Annotator Agreement (IAA) for Enhancing Data Management Operations (DMOps)","created":"2023-06-26","cited_by_count":1,"area":null},{"id":"2311.05778","title":"DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2409.00909","title":"ViRED: Prediction of Visual Relations in Engineering Drawings","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2209.12561","title":"Improving Document Image Understanding with Reinforcement Finetuning","created":"2022-09-26","cited_by_count":0,"area":null},{"id":"2305.13817","title":"Detecting automatically the layout of clinical documents to enhance the performances of downstream natural language processing","created":"2023-05-23","cited_by_count":0,"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":"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":"2409.15004","title":"ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2412.02886","title":"Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty","created":"2024-12-03","cited_by_count":0,"area":"mllm"},{"id":"2412.10155","title":"WordVIS: A Color Worth A Thousand Words","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2506.05061","title":"A Survey on Vietnamese Document Analysis and Recognition: Challenges and Future Directions","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2604.01452","title":"A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2607.22723","title":"Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models","created":"2026-07-22","cited_by_count":0,"area":"mllm"},{"id":"2609.35796","title":"Developing an OCR model for Extracting Information from Invoices with Korean Language","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.04437","title":"CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness","created":"2026-10-03","cited_by_count":0,"area":"agents"}],"next_cursor":null}