{"total":90,"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":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476,"area":"mllm"},{"id":"2211.14461","title":"CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion","created":"2022-11-26","cited_by_count":223,"area":null},{"id":"2403.04473","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","created":"2024-03-07","cited_by_count":174,"area":"mllm"},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140,"area":null},{"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":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106,"area":"mllm"},{"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":"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":"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":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","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":"2303.00289","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training","created":"2023-03-01","cited_by_count":39,"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":"2406.19101","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","created":"2024-06-27","cited_by_count":35,"area":"mllm"},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"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":"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":"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":"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":"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":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"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":"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":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13,"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":"2205.02411","title":"Relational Representation Learning in Visually-Rich Documents","created":"2022-05-05","cited_by_count":11,"area":null},{"id":"2412.10159","title":"Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance","created":"2024-12-13","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":"2402.09841","title":"LAPDoc: Layout-Aware Prompting for Documents","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2503.18434","title":"A Simple yet Effective Layout Token in Large Language Models for Document Understanding","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","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":"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":"2305.11392","title":"Fast-StrucTexT: An Efficient Hourglass Transformer with Modality-guided Dynamic Token Merge for Document Understanding","created":"2023-05-19","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":"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":"2305.02577","title":"Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation","created":"2023-05-04","cited_by_count":5,"area":null},{"id":"2407.12358","title":"ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data","created":"2024-07-17","cited_by_count":5,"area":"mllm"},{"id":"2307.12571","title":"MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary","created":"2023-07-24","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":"2207.06717","title":"Layout-Aware Information Extraction for Document-Grounded Dialogue: Dataset, Method and Demonstration","created":"2022-07-14","cited_by_count":3,"area":null},{"id":"2402.02379","title":"Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2402.05282","title":"TreeForm: End-to-end Annotation and Evaluation for Form Document Parsing","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2507.23295","title":"LED Benchmark: Diagnosing Structural Layout Errors for Document Layout Analysis","created":"2025-07-31","cited_by_count":3,"area":null},{"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":"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":"2211.06168","title":"Unimodal and Multimodal Representation Training for Relation Extraction","created":"2022-11-11","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":"2306.03377","title":"TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision","created":"2023-06-06","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":"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":"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":"2410.01160","title":"GraphRevisedIE: Multimodal Information Extraction with Graph-Revised Network","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2506.21055","title":"Class-Agnostic Region-of-Interest Matching in Document Images","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2510.02133","title":"FlexDoc: Parameterized Sampling for Diverse Multilingual Synthetic Documents for Training Document Understanding Models","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2511.18192","title":"ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization","created":"2025-11-22","cited_by_count":2,"area":"agents"},{"id":"2211.04934","title":"DoSA : A System to Accelerate Annotations on Business Documents with Human-in-the-Loop","created":"2022-11-09","cited_by_count":1,"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":"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":"2404.10848","title":"A LayoutLMv3-Based Model for Enhanced Relation Extraction in Visually-Rich Documents","created":"2024-04-16","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":"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":"2607.04636","title":"Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2609.32041","title":"Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2202.09144","title":"Modelling the semantics of text in complex document layouts using graph transformer networks","created":"2022-02-18","cited_by_count":0,"area":null},{"id":"2310.11650","title":"VKIE: The Application of Key Information Extraction on Video Text","created":"2023-10-18","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":"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":"2411.01139","title":"HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction","created":"2024-11-02","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":"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":"2512.23714","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":"2601.11248","title":"Language-Agnostic Visual Embeddings for Cross-Script Handwriting Retrieval","created":"2026-01-16","cited_by_count":0,"area":null},{"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":"2608.18685","title":"DocClaw: A Unified Agentic System for Intelligent Document Processing","created":"2026-08-19","cited_by_count":0,"area":"agents"},{"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}