{"total":106,"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":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407,"area":null},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"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":"2203.02378","title":"DiT: Self-supervised Pre-training for Document Image Transformer","created":"2022-03-04","cited_by_count":152,"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":"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":"2108.04539","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":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2211.05776","title":"High-Quality Entity Segmentation","created":"2022-11-10","cited_by_count":93,"area":null},{"id":"2204.10939","title":"Unified Pretraining Framework for Document Understanding","created":"2022-04-22","cited_by_count":85,"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":"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":"2202.02312","title":"A Dataset for Interactive Vision-Language Navigation with Unknown Command Feasibility","created":"2022-02-04","cited_by_count":61,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","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":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45,"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":"2202.12985","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","created":"2022-02-25","cited_by_count":35,"area":null},{"id":"2303.18248","title":"Towards Flexible Multi-modal Document Models","created":"2023-03-31","cited_by_count":31,"area":null},{"id":"2111.13359","title":"Neural Collaborative Graph Machines for Table Structure Recognition","created":"2021-11-26","cited_by_count":30,"area":null},{"id":"2201.10252","title":"DocEnTr: An End-to-End Document Image Enhancement Transformer","created":"2022-01-25","cited_by_count":28,"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":"2304.02173","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","created":"2023-04-05","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":"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":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2204.01184","title":"Exploiting Temporal Relations on Radar Perception for Autonomous Driving","created":"2022-04-03","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":"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":"2303.06471","title":"Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review","created":"2023-03-11","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":"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":"2206.14719","title":"Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision","created":"2022-06-29","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":"2410.16038","title":"Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios","created":"2024-10-21","cited_by_count":17,"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":"2403.16516","title":"Visually Guided Generative Text-Layout Pre-training for Document Intelligence","created":"2024-03-25","cited_by_count":12,"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":"2209.08569","title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","created":"2022-09-18","cited_by_count":9,"area":null},{"id":"2211.14958","title":"MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2308.01979","title":"RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2404.19024","title":"Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism","created":"2024-04-29","cited_by_count":8,"area":null},{"id":"2305.00795","title":"SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2206.07240","title":"Test-Time Adaptation for Visual Document Understanding","created":"2022-06-15","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":"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":"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":"2310.18343","title":"PHD: Pixel-Based Language Modeling of Historical Documents","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2512.20174","title":"Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark","created":"2025-12-23","cited_by_count":5,"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":"2306.08937","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2312.03568","title":"DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","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":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2303.03127","title":"ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents","created":"2023-03-06","cited_by_count":3,"area":null},{"id":"2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","created":"2023-09-21","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":"2406.01651","title":"FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interaction","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2406.06594","title":"Stock Movement Prediction with Multimodal Stable Fusion via Gated Cross-Attention Mechanism","created":"2024-06-06","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":"2305.13850","title":"Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2307.11845","title":"Multimodal Document Analytics for Banking Process Automation","created":"2023-07-21","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":"2312.03946","title":"A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement","created":"2023-12-06","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":"2401.05167","title":"Watermark Text Pattern Spotting in Document Images","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2406.06236","title":"UnSupDLA: Towards Unsupervised Document Layout Analysis","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2505.10780","title":"SECRET: Semi-supervised Clinical Trial Document Similarity Search","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2508.09175","title":"A Context-aware Attention and Graph Neural Network-based Multimodal Framework for Misogyny Detection","created":"2025-08-07","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":"2211.17232","title":"ObjCAViT: Improving Monocular Depth Estimation Using Natural Language Models And Image-Object Cross-Attention","created":"2022-11-30","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":"2404.05210","title":"Bidirectional Long-Range Parser for Sequential Data Understanding","created":"2024-04-08","cited_by_count":1,"area":null},{"id":"2410.01441","title":"Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2505.23812","title":"Emotion-aware Dual Cross-Attentive Neural Network with Label Fusion for Stance Detection in Misinformative Social Media Content","created":"2025-05-27","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":"2512.20236","title":"IndicDLP: A Foundational Dataset for Multi-Lingual and Multi-Domain Document Layout Parsing","created":"2025-12-23","cited_by_count":1,"area":null},{"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":"2209.06584","title":"One-Shot Doc Snippet Detection: Powering Search in Document Beyond Text","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2305.14218","title":"DUBLIN -- Document Understanding By Language-Image Network","created":"2023-05-23","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":"2404.00488","title":"Noise-Aware Training of Layout-Aware Language Models","created":"2024-03-30","cited_by_count":0,"area":null}],"next_cursor":"100"}