{"list":"other","total":54,"rows":[{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2409.18839","title":"MinerU: An Open-Source Solution for Precise Document Content Extraction","created":"2024-09-27","cited_by_count":267},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183},{"id":"2409.01704","title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","created":"2024-09-03","cited_by_count":180},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150},{"id":"2206.01062","title":"DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis","created":"2022-06-02","cited_by_count":148},{"id":"2005.00589","title":"Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context","created":"2020-05-01","cited_by_count":147},{"id":"2507.05595","title":"PaddleOCR 3.0 Technical Report","created":"2025-07-08","cited_by_count":143},{"id":"2502.18443","title":"olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models","created":"2025-02-25","cited_by_count":125},{"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},{"id":"1903.01949","title":"TableBank: A Benchmark Dataset for Table Detection and Recognition","created":"2019-03-05","cited_by_count":102},{"id":"1908.04729","title":"Complicated Table Structure Recognition","created":"2019-08-13","cited_by_count":92},{"id":"2510.14528","title":"PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model","created":"2025-10-16","cited_by_count":89},{"id":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87},{"id":"2412.02210","title":"CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy","created":"2024-12-03","cited_by_count":81},{"id":"2108.11591","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","created":"2021-08-26","cited_by_count":80},{"id":"1609.04938","title":"Image-to-Markup Generation with Coarse-to-Fine Attention","created":"2016-09-16","cited_by_count":79},{"id":"2601.20552","title":"DeepSeek-OCR 2: Visual Causal Flow","created":"2026-01-28","cited_by_count":74},{"id":"2412.18424","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","created":"2024-12-24","cited_by_count":72},{"id":"2501.17887","title":"Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversion","created":"2025-01-27","cited_by_count":63},{"id":"2405.14295","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","created":"2024-05-23","cited_by_count":62},{"id":"2103.15348","title":"LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis","created":"2021-03-29","cited_by_count":58},{"id":"2601.21957","title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","created":"2026-01-29","cited_by_count":57},{"id":"2308.14978","title":"Vision Grid Transformer for Document Layout Analysis","created":"2023-08-29","cited_by_count":47},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47},{"id":"2305.08719","title":"M$^{6}$Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis","created":"2023-05-15","cited_by_count":46},{"id":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37},{"id":"2509.02359","title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture","created":"2025-09-02","cited_by_count":30},{"id":"2603.10910","title":"GLM-OCR Technical Report","created":"2026-03-11","cited_by_count":26},{"id":"2303.13839","title":"HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures","created":"2023-03-24","cited_by_count":23},{"id":"2511.15722","title":"Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods","created":"2025-11-14","cited_by_count":23},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22},{"id":"2510.03663","title":"UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG","created":"2025-10-04","cited_by_count":21},{"id":"2603.13398","title":"Qianfan-OCR: A Unified End-to-End Model for Document Intelligence","created":"2026-03-11","cited_by_count":21},{"id":"2509.19760","title":"Logics-Parsing Technical Report","created":"2025-09-24","cited_by_count":17},{"id":"2512.03413","title":"BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents","created":"2025-12-03","cited_by_count":16},{"id":"2409.05137","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","created":"2024-09-08","cited_by_count":15},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","cited_by_count":13},{"id":"2601.21639","title":"OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models","created":"2026-01-29","cited_by_count":12},{"id":"2604.08538","title":"ParseBench: A Document Parsing Benchmark for AI Agents","created":"2026-04-09","cited_by_count":11},{"id":"2508.13238","title":"DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model","created":"2025-08-18","cited_by_count":10},{"id":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10},{"id":"2511.18434","title":"DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation","created":"2025-11-23","cited_by_count":9},{"id":"2602.05014","title":"DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search","created":"2026-02-04","cited_by_count":7},{"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},{"id":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5},{"id":"2603.07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","created":"2026-03-08","cited_by_count":1}],"next_cursor":null}