{"total":58,"rows":[{"id":"2301.10140","title":"The Semantic Scholar Open Data Platform","created":"2023-01-24","cited_by_count":118,"area":null},{"id":"2304.06447","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","created":"2023-04-13","cited_by_count":28,"area":null},{"id":"2106.00676","title":"VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups","created":"2021-06-01","cited_by_count":27,"area":null},{"id":"2210.05391","title":"PP-StructureV2: A Stronger Document Analysis System","created":"2022-10-11","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":"2210.04261","title":"Noise-Robust De-Duplication at Scale","created":"2022-10-09","cited_by_count":17,"area":null},{"id":"2404.01462","title":"OpenChemIE: An Information Extraction Toolkit For Chemistry Literature","created":"2024-04-01","cited_by_count":17,"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":"2504.00414","title":"Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents","created":"2025-04-01","cited_by_count":12,"area":"mllm"},{"id":"2304.02737","title":"Efficient OCR for Building a Diverse Digital History","created":"2023-04-05","cited_by_count":10,"area":null},{"id":"2405.19255","title":"Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology using Large Language Models -- A Case in Optimizing Intermodal Freight Transportation","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2406.13719","title":"GUI Action Narrator: Where and When Did That Action Take Place?","created":"2024-06-19","cited_by_count":9,"area":"mllm"},{"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":"2410.13305","title":"Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2505.20429","title":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2205.02543","title":"OCR Synthetic Benchmark Dataset for Indic Languages","created":"2022-05-05","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":"2509.16506","title":"CommonForms: A Large, Diverse Dataset for Form Field Detection","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2201.01654","title":"TableParser: Automatic Table Parsing with Weak Supervision from Spreadsheets","created":"2022-01-05","cited_by_count":2,"area":null},{"id":"2305.14672","title":"Quantifying Character Similarity with Vision Transformers","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2310.03777","title":"PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction","created":"2023-10-05","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":"2406.06236","title":"UnSupDLA: Towards Unsupervised Document Layout Analysis","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2406.17591","title":"DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2408.09800","title":"Latent Diffusion for Guided Document Table Generation","created":"2024-08-19","cited_by_count":2,"area":"diffusion"},{"id":"2505.03214","title":"DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2505.03777","title":"MolMole: Molecule Mining from Scientific Literature","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2506.16006","title":"DIGMAPPER: A Modular System for Automated Geologic Map Digitization","created":"2025-06-19","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":"2110.08580","title":"Intelligent Video Editing: Incorporating Modern Talking Face Generation Algorithms in a Video Editor","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2204.00052","title":"Digitizing Historical Balance Sheet Data: A Practitioner's Guide","created":"2022-03-31","cited_by_count":1,"area":null},{"id":"2304.00086","title":"Machine Learning for Economics Research: When What and How?","created":"2023-03-31","cited_by_count":1,"area":null},{"id":"2304.03464","title":"Linking Representations with Multimodal Contrastive Learning","created":"2023-04-07","cited_by_count":1,"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":"2409.05125","title":"PdfTable: A Unified Toolkit for Deep Learning-Based Table Extraction","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2410.02955","title":"AiBAT: Artificial Intelligence/Instructions for Build, Assembly, and Test","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2501.00004","title":"NewsHomepages: Homepage Layouts Capture Information Prioritization Decisions","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2502.14778","title":"Harnessing PDF Data for Improving Japanese Large Multimodal Models","created":"2025-02-20","cited_by_count":1,"area":"mllm"},{"id":"2508.04208","title":"DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models","created":"2025-08-06","cited_by_count":1,"area":"diffusion"},{"id":"2510.08385","title":"Detecting Legend Items on Historical Maps Using GPT-4o with In-Context Learning","created":"2025-10-09","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":"2602.08749","title":"Shifting the Breaking Point of Flow Matching for Multi-Instance Editing","created":"2026-02-09","cited_by_count":1,"area":"diffusion"},{"id":"2605.12623","title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2201.08295","title":"DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis","created":"2022-01-20","cited_by_count":0,"area":null},{"id":"2309.13184","title":"Document Understanding for Healthcare Referrals","created":"2023-09-22","cited_by_count":0,"area":null},{"id":"2505.24676","title":"Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning","created":"2025-05-30","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":"2602.22828","title":"TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2603.13245","title":"Automating Document Intelligence in Statutory City Planning","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2604.14222","title":"Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents","created":"2026-04-14","cited_by_count":0,"area":"rag"},{"id":"2604.19770","title":"Hybrid Multi-Phase Page Matching and Multi-Layer Diff Detection for Japanese Building Permit Document Review","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2608.07994","title":"VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.16763","title":"LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.29268","title":"Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models","created":"2026-08-29","cited_by_count":0,"area":"mllm"},{"id":"2609.08330","title":"EMBLEM: Enhancing Multi-script Table Detection through Masking","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.35588","title":"Source-preserving alignment for robust evidence localization in scientific PDFS","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}