{"total":103,"rows":[{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"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":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79,"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":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2405.04408","title":"DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks","created":"2024-05-07","cited_by_count":27,"area":null},{"id":"2403.14252","title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","created":"2024-03-21","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":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","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":"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":"2403.14442","title":"RoDLA: Benchmarking the Robustness of Document Layout Analysis Models","created":"2024-03-21","cited_by_count":13,"area":null},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","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":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2402.09841","title":"LAPDoc: Layout-Aware Prompting for Documents","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2403.19454","title":"JDocQA: Japanese Document Question Answering Dataset for Generative Language Models","created":"2024-03-28","cited_by_count":9,"area":null},{"id":"2404.04003","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","created":"2024-04-05","cited_by_count":8,"area":null},{"id":"2407.12594","title":"VisFocus: Prompt-Guided Vision Encoders for OCR-Free Dense Document Understanding","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2601.03714","title":"Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR","created":"2026-01-07","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2309.14389","title":"Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2408.15646","title":"{\\mu}gat: Improving Single-Page Document Parsing by Providing Multi-Page Context","created":"2024-08-28","cited_by_count":7,"area":null},{"id":"2501.06659","title":"Visual Template Inference for Data Extraction from Documents","created":"2025-01-11","cited_by_count":7,"area":null},{"id":"2505.14699","title":"Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairs","created":"2025-05-12","cited_by_count":7,"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":"2502.18179","title":"Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs","created":"2025-02-25","cited_by_count":6,"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":"2309.14805","title":"Fine-tuning and aligning question answering models for complex information extraction tasks","created":"2023-09-26","cited_by_count":5,"area":null},{"id":"2311.09612","title":"Efficient End-to-End Visual Document Understanding with Rationale Distillation","created":"2023-11-16","cited_by_count":5,"area":null},{"id":"2406.08354","title":"DocSynthv2: A Practical Autoregressive Modeling for Document Generation","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2503.16096","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2510.10138","title":"Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task","created":"2025-10-11","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":"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":"2305.15080","title":"Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2406.08255","title":"M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation","created":"2024-06-12","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":"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":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"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":"2401.15050","title":"LongFin: A Multimodal Document Understanding Model for Long Financial Domain Documents","created":"2024-01-26","cited_by_count":3,"area":null},{"id":"2407.05750","title":"Large Language Models Understand Layout","created":"2024-07-08","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":"2506.12116","title":"Unsupervised Document and Template Clustering using Multimodal Embeddings","created":"2025-06-13","cited_by_count":3,"area":null},{"id":"2602.23061","title":"MoDora: Tree-Based Semi-Structured Document Analysis System","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2305.12311","title":"i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2403.18183","title":"Can AI Models Appreciate Document Aesthetics? An Exploration of Legibility and Layout Quality in Relation to Prediction Confidence","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2409.11282","title":"Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2506.01388","title":"VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding","created":"2025-06-02","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":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2603.28550","title":"MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structures","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2606.23344","title":"RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2310.00917","title":"Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2311.03650","title":"Image Generation and Learning Strategy for Deep Document Forgery Detection","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2402.14579","title":"Text Role Classification in Scientific Charts Using Multimodal Transformers","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2404.00439","title":"DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering","created":"2024-03-30","cited_by_count":1,"area":null},{"id":"2405.06636","title":"Federated Document Visual Question Answering: A Pilot Study","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2409.00447","title":"The MERIT Dataset: Modelling and Efficiently Rendering Interpretable Transcripts","created":"2024-08-31","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":"2504.00385","title":"Leveraging Contrast Information for Efficient Document Shadow Removal","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.10419","title":"Unchecked and Overlooked: Addressing the Checkbox Blind Spot in Large Language Models with CheckboxQA","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2511.17881","title":"MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use","created":"2025-11-22","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":"2602.07645","title":"From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2602.18178","title":"Evaluating Graphical Perception Capabilities of Vision Transformers","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2609.27784","title":"EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA","created":"2026-08-17","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":"2305.14218","title":"DUBLIN -- Document Understanding By Language-Image Network","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2405.18669","title":"Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2412.12902","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","created":"2024-12-17","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":"2505.18925","title":"Words as Geometric Features: Estimating Homography using Optical Character Recognition as Compressed Image Representation","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2506.23605","title":"AI-Generated Lecture Slides for Improving Slide Element Detection and Retrieval","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2507.18952","title":"Legal Document Summarization: Enhancing Judicial Efficiency through Automation Detection","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.04233","title":"DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.10311","title":"From Surface to Semantics: Semantic Structure Parsing for Table-Centric Document Analysis","created":"2025-08-14","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":"2511.19919","title":"HybriDLA: Hybrid Generation for Document Layout Analysis","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.02660","title":"Spatially-Grounded Document Retrieval via Patch-to-Region Relevance Propagation","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.02539","title":"How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.09337","title":"Kyrtos: A methodology for automatic deep analysis of graphic charts with curves in technical documents","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.21225","title":"Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.10077","title":"DocRevive: A Unified Pipeline for Document Text Restoration","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2606.17644","title":"Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasets","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.31446","title":"Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap","created":"2026-06-30","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":"2607.24745","title":"DocAnnot -- Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2608.10636","title":"DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.18679","title":"FRAGMENT: Factorized Graph Representations for Document Generation and Editing via Entity-Aware Transformations","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.26091","title":"PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":"100"}