{"total":148,"rows":[{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"id":"2509.22186","title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","created":"2025-09-26","cited_by_count":116,"area":"mllm"},{"id":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101,"area":"mllm"},{"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":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"id":"2410.12628","title":"DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception","created":"2024-10-16","cited_by_count":82,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2503.11576","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","created":"2025-03-14","cited_by_count":53,"area":"mllm"},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47,"area":"mllm"},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46,"area":"rag"},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2406.11633","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","created":"2024-06-17","cited_by_count":36,"area":"mllm"},{"id":"2411.06176","title":"M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework","created":"2024-11-09","cited_by_count":36,"area":null},{"id":"2305.03393","title":"Optimized Table Tokenization for Table Structure Recognition","created":"2023-05-05","cited_by_count":34,"area":null},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27,"area":null},{"id":"2503.17213","title":"PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Construction","created":"2025-03-21","cited_by_count":26,"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":"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":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2410.05970","title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","created":"2024-10-08","cited_by_count":14,"area":"mllm"},{"id":"2303.05325","title":"BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis Dataset","created":"2023-03-09","cited_by_count":13,"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":"2502.08417","title":"Handwritten Text Recognition: A Survey","created":"2025-02-12","cited_by_count":12,"area":null},{"id":"2405.11757","title":"DLAFormer: An End-to-End Transformer For Document Layout Analysis","created":"2024-05-20","cited_by_count":11,"area":null},{"id":"2604.08538","title":"ParseBench: A Document Parsing Benchmark for AI Agents","created":"2026-04-09","cited_by_count":11,"area":"agents"},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2502.04223","title":"\\'Eclair -- Extracting Content and Layout with Integrated Reading Order for Documents","created":"2025-02-06","cited_by_count":9,"area":null},{"id":"2602.12247","title":"ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction","created":"2026-02-12","cited_by_count":9,"area":null},{"id":"2310.17674","title":"Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis","created":"2023-10-25","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":"2312.10188","title":"WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2604.09590","title":"DeepReviewer 2.0: A Traceable Agentic System for Auditable Scientific Peer Review","created":"2026-03-03","cited_by_count":7,"area":"agents"},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2305.14962","title":"ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-24","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":"2604.12352","title":"MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2305.06553","title":"WeLayout: WeChat Layout Analysis System for the ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents","created":"2023-05-11","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":"2509.19345","title":"SCORE: A Semantic Evaluation Framework for Generative Document Parsing","created":"2025-09-16","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":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5,"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":"2407.03830","title":"DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2408.14764","title":"SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding","created":"2024-08-27","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":"2507.20145","title":"Multi-Agent Interactive Question Generation Framework for Long Document Understanding","created":"2025-07-27","cited_by_count":4,"area":"agents"},{"id":"2509.16506","title":"CommonForms: A Large, Diverse Dataset for Form Field Detection","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2511.04910","title":"SDS KoPub VDR: A Benchmark Dataset for Visual Document Retrieval in Korean Public Documents","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2511.13478","title":"Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling","created":"2025-11-17","cited_by_count":4,"area":"mllm"},{"id":"2605.07492","title":"How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2503.15893","title":"UniHDSA: A Unified Relation Prediction Approach for Hierarchical Document Structure Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2504.09249","title":"NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding","created":"2025-04-12","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":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2605.29606","title":"HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering","created":"2026-05-28","cited_by_count":3,"area":"rag"},{"id":"2207.11230","title":"You Actually Look Twice At it (YALTAi): using an object detection approach instead of region segmentation within the Kraken engine","created":"2022-07-19","cited_by_count":2,"area":null},{"id":"2304.11810","title":"PARAGRAPH2GRAPH: A GNN-based framework for layout paragraph analysis","created":"2023-04-24","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":"2310.18073","title":"A Scalable Framework for Table of Contents Extraction from Complex ESG Annual Reports","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2311.18481","title":"ESG Accountability Made Easy: DocQA at Your Service","created":"2023-11-30","cited_by_count":2,"area":null},{"id":"2402.11401","title":"GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation","created":"2024-02-17","cited_by_count":2,"area":"distill"},{"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":"2405.19765","title":"Towards Unified Multi-granularity Text Detection with Interactive Attention","created":"2024-05-30","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":"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":"2503.18742","title":"SFDLA: Source-Free Document Layout Analysis","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2506.14079","title":"FormGym: Doing Paperwork with Agents","created":"2025-06-17","cited_by_count":2,"area":"agents"},{"id":"2507.05805","title":"DREAM: Document Reconstruction via End-to-end Autoregressive Model","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.26213","title":"OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2512.10888","title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2512.17221","title":"DAVE: A VLM Vision Encoder for Document Understanding and Web Agents","created":"2025-12-19","cited_by_count":2,"area":"mllm"},{"id":"2603.11044","title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.25761","title":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2605.24973","title":"MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2309.17033","title":"Unveiling Document Structures with YOLOv5 Layout Detection","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2401.09232","title":"Dynamic Relation Transformer for Contextual Text Block Detection","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2406.08226","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","created":"2024-06-12","cited_by_count":1,"area":"distill"},{"id":"2409.10016","title":"AceParse: A Comprehensive Dataset with Diverse Structured Texts for Academic Literature Parsing","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2411.10068","title":"Diachronic Document Dataset for Semantic Layout Analysis","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2503.22526","title":"AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorization","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2506.18069","title":"Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2509.13236","title":"Layout-Aware OCR for Black Digital Archives with Unsupervised Evaluation","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.20478","title":"NVIDIA Nemotron Parse 1.1","created":"2025-11-25","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":"2601.07620","title":"PARL: Position-Aware Relation Learning Network for Document Layout Analysis","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2601.14722","title":"Typhoon OCR: Open Vision-Language Model For Thai Document Extraction","created":"2026-01-21","cited_by_count":1,"area":"mllm"},{"id":"2603.12718","title":"The COTe score: A decomposable framework for evaluating Document Layout Analysis models","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2603.17265","title":"LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2608.22842","title":"FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks","created":"2026-08-24","cited_by_count":1,"area":"lr"},{"id":"2609.07072","title":"Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection","created":"2026-09-07","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":"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":"2408.04661","title":"MaterioMiner -- An ontology-based text mining dataset for extraction of process-structure-property entities","created":"2024-08-05","cited_by_count":0,"area":null}],"next_cursor":"100"}