{"total":485,"rows":[{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267,"area":null},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245,"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":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195,"area":"mllm"},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"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":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168,"area":"mllm"},{"id":"2305.14761","title":"UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning","created":"2023-05-24","cited_by_count":160,"area":"mllm"},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143,"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":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2212.09662","title":"MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering","created":"2022-12-19","cited_by_count":133,"area":"lr"},{"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":"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":"2411.04952","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","created":"2024-11-07","cited_by_count":111,"area":"rag"},{"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":"2212.05935","title":"Hierarchical multimodal transformers for Multi-Page DocVQA","created":"2022-12-07","cited_by_count":105,"area":null},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98,"area":"mllm"},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"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":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"id":"2404.13046","title":"MoVA: Adapting Mixture of Vision Experts to Multimodal Context","created":"2024-04-19","cited_by_count":83,"area":"mllm"},{"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":"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":"2412.18424","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","created":"2024-12-24","cited_by_count":72,"area":"lr"},{"id":"2405.19327","title":"MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series","created":"2024-05-29","cited_by_count":67,"area":null},{"id":"2504.13865","title":"A Survey on (M)LLM-Based GUI Agents","created":"2025-03-27","cited_by_count":62,"area":"agents"},{"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":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"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":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47,"area":null},{"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":"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":"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":"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":"2309.10952","title":"LMDX: Language Model-based Document Information Extraction and Localization","created":"2023-09-19","cited_by_count":37,"area":null},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"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":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36,"area":"rag"},{"id":"2211.15421","title":"VRDU: A Benchmark for Visually-rich Document Understanding","created":"2022-11-15","cited_by_count":35,"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":"2407.04346","title":"MobileFlow: A Multimodal LLM For Mobile GUI Agent","created":"2024-07-05","cited_by_count":32,"area":"mllm"},{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30,"area":null},{"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":"2411.01106","title":"SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding","created":"2024-11-02","cited_by_count":25,"area":"mllm"},{"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":"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":"2506.02404","title":"GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation","created":"2025-06-03","cited_by_count":24,"area":"lr"},{"id":"2305.09750","title":"ICDAR 2023 Competition on Hierarchical Text Detection and Recognition","created":"2023-05-16","cited_by_count":23,"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":"2401.03411","title":"GRAM: Global Reasoning for Multi-Page VQA","created":"2024-01-07","cited_by_count":23,"area":"lr"},{"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":"2409.02914","title":"Can LVLMs Obtain a Driver's License? A Benchmark Towards Reliable AGI for Autonomous Driving","created":"2024-09-04","cited_by_count":22,"area":"mllm"},{"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":"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":"2303.13095","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":"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":"2304.12484","title":"DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents","created":"2023-04-24","cited_by_count":19,"area":null},{"id":"2206.13155","title":"Bi-VLDoc: Bidirectional Vision-Language Modeling for Visually-Rich Document Understanding","created":"2022-06-27","cited_by_count":18,"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":"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":"2403.11905","title":"Tur[k]ingBench: A Challenge Benchmark for Web Agents","created":"2024-03-18","cited_by_count":18,"area":"agents"},{"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":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2505.17104","title":"P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark","created":"2025-05-21","cited_by_count":17,"area":null},{"id":"2510.15349","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-10-17","cited_by_count":17,"area":"mllm"},{"id":"2601.06992","title":"FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering","created":"2026-01-11","cited_by_count":16,"area":null},{"id":"2312.17264","title":"ESGReveal: An LLM-based approach for extracting structured data from ESG reports","created":"2023-12-25","cited_by_count":15,"area":null},{"id":"2401.11874","title":"Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis","created":"2024-01-22","cited_by_count":15,"area":null},{"id":"2409.05137","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","created":"2024-09-08","cited_by_count":15,"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":"2402.14073","title":"Improving Language Understanding from Screenshots","created":"2024-02-21","cited_by_count":14,"area":null},{"id":"2407.19787","title":"SciPostLayout: A Dataset for Layout Analysis and Layout Generation of Scientific Posters","created":"2024-07-29","cited_by_count":14,"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":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14,"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":"2309.14962","title":"GridFormer: Towards Accurate Table Structure Recognition via Grid Prediction","created":"2023-09-26","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":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"area":"rag"},{"id":"2210.02849","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","created":"2022-10-06","cited_by_count":12,"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":"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":"2411.05254","title":"Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding","created":"2024-11-08","cited_by_count":12,"area":"mllm"},{"id":"2504.11101","title":"Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR","created":"2025-04-15","cited_by_count":12,"area":"mllm"},{"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":"2405.21013","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","created":"2024-05-31","cited_by_count":11,"area":"mllm"},{"id":"2410.23780","title":"Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Map","created":"2024-10-31","cited_by_count":11,"area":"driving"},{"id":"2505.05666","title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","created":"2025-05-08","cited_by_count":11,"area":"rag"}],"next_cursor":"100"}