{"total":82,"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":"2502.18443","title":"olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models","created":"2025-02-25","cited_by_count":125,"area":"mllm"},{"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":"2506.05218","title":"MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm","created":"2025-06-05","cited_by_count":87,"area":null},{"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,"area":"mllm"},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"2505.11404","title":"Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasoner","created":"2025-05-16","cited_by_count":40,"area":"lr"},{"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":"2604.04771","title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","created":"2026-04-06","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":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"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":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2508.21720","title":"PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation","created":"2025-08-29","cited_by_count":8,"area":null},{"id":"2603.23885","title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","created":"2026-03-25","cited_by_count":7,"area":"mllm"},{"id":"2512.10619","title":"DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2412.12505","title":"DocFusion: A Unified Framework for Document Parsing Tasks","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2505.14381","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2510.09302","title":"CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Understanding","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"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":"2510.22215","title":"Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy","created":"2025-10-25","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":"2512.01248","title":"TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition","created":"2025-12-01","cited_by_count":4,"area":"mllm"},{"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":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2412.11574","title":"PyPotteryLens: An Open-Source Deep Learning Framework for Automated Digitisation of Archaeological Pottery Documentation","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2502.14901","title":"Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2510.10828","title":"VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering","created":"2025-10-12","cited_by_count":3,"area":"rag"},{"id":"2512.03514","title":"M3DR: Towards Universal Multilingual Multimodal Document Retrieval","created":"2025-12-03","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":"2605.27978","title":"ABot-OCR Technical Report","created":"2026-05-27","cited_by_count":3,"area":"mllm"},{"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":"2506.13363","title":"Efficient Medical VIE via Reinforcement Learning","created":"2025-06-16","cited_by_count":2,"area":"deeprl"},{"id":"2507.03009","title":"PDFMathTranslate: Scientific Document Translation Preserving Layouts","created":"2025-07-02","cited_by_count":2,"area":null},{"id":"2508.18984","title":"Enhancing Document VQA Models via Retrieval-Augmented Generation","created":"2025-08-26","cited_by_count":2,"area":"mllm"},{"id":"2510.09558","title":"AutoPR: Let's Automate Your Academic Promotion!","created":"2025-10-10","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":"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":"2604.06160","title":"The Character Error Vector: Decomposable errors for page-level OCR evaluation","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.05773","title":"CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt","created":"2026-05-07","cited_by_count":2,"area":"mechinterp"},{"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":"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":"2505.02418","title":"SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration","created":"2025-05-05","cited_by_count":1,"area":"rag"},{"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":"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":"2601.07483","title":"FocalOrder: Focal Preference Optimization for Reading Order Detection","created":"2026-01-12","cited_by_count":1,"area":"alignment"},{"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":"2603.00707","title":"Towards Khmer Scene Document Layout Detection","created":"2026-02-28","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":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2605.17159","title":"MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop","created":"2026-05-16","cited_by_count":1,"area":"agents"},{"id":"2607.00596","title":"Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.02218","title":"PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.06146","title":"PaDoc: Layout-Grounded Parallel Decoding for Document Parsing","created":"2026-08-06","cited_by_count":1,"area":"inference"},{"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":"2502.03971","title":"RWKV-UI: UI Understanding with Enhanced Perception and Reasoning","created":"2025-02-06","cited_by_count":0,"area":"lr"},{"id":"2502.16541","title":"EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2506.20326","title":"From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2508.16295","title":"Edge-Native Digitization of Handwritten Marksheets: A Hybrid Heuristic-Deep Learning Framework","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.02864","title":"A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation","created":"2025-09-02","cited_by_count":0,"area":"synth"},{"id":"2509.17012","title":"DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2511.16216","title":"FlipVQA: Scaling Multi-modal Instruction Tuning via Textbook-to-Knowledge Synthesis","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2601.03496","title":"STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2604.02692","title":"Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.11042","title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.23276","title":"Lightweight and Production-Ready PDF Visual Element Parsing","created":"2026-04-25","cited_by_count":0,"area":"rag"},{"id":"2605.10845","title":"BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.15794","title":"ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.16861","title":"Prefix-Adaptive Block Diffusion for Efficient Document Recognition","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2605.19309","title":"How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence","created":"2026-05-19","cited_by_count":0,"area":"rag"},{"id":"2605.22829","title":"LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding","created":"2026-04-18","cited_by_count":0,"area":"rag"},{"id":"2606.06242","title":"Benchmarking Open-Source Layout Detection Models for Data Snapshot Extraction from Institutional Documents","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.18997","title":"Benchmarking Deep Learning Approaches for AEC Engineering Drawing Layout Detection and Information Extraction","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.04424","title":"Thinking with Anchors: Grounded and Efficient Document Reasoning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.18988","title":"DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.28698","title":"State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models","created":"2026-08-27","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":"2609.39600","title":"GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed","created":"2026-09-30","cited_by_count":0,"area":"inference"},{"id":"2609.39601","title":"GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}