{"total":75,"rows":[{"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":"2407.01523","title":"MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations","created":"2024-07-01","cited_by_count":183,"area":null},{"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,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"area":null},{"id":"2407.04172","title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","created":"2024-07-04","cited_by_count":79,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"id":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"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":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null},{"id":"2503.14324","title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","created":"2025-03-18","cited_by_count":42,"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":"2502.19870","title":"MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge","created":"2025-02-27","cited_by_count":23,"area":null},{"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":"2504.07089","title":"OmniCaptioner: One Captioner to Rule Them All","created":"2025-04-09","cited_by_count":20,"area":null},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2409.13194","title":"ChemDFM-X: Towards Large Multimodal Model for Chemistry","created":"2024-09-20","cited_by_count":16,"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":"2406.12246","title":"TroL: Traversal of Layers for Large Language and Vision Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2508.18190","title":"ST-Raptor: LLM-Powered Semi-Structured Table Question Answering","created":"2025-08-25","cited_by_count":11,"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":"2503.18434","title":"A Simple yet Effective Layout Token in Large Language Models for Document Understanding","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2601.08834","title":"Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2501.03403","title":"BoundingDocs: a Unified Dataset for Document Question Answering with Spatial Annotations","created":"2025-01-06","cited_by_count":8,"area":null},{"id":"2501.15415","title":"OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery","created":"2025-01-26","cited_by_count":8,"area":null},{"id":"2507.09861","title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","created":"2025-07-14","cited_by_count":8,"area":null},{"id":"2412.17092","title":"SAIL: Sample-Centric In-Context Learning for Document Information Extraction","created":"2024-12-22","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":"2409.05405","title":"A Survey of Multimodal Composite Editing and Retrieval","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2412.14596","title":"LDP: Generalizing to Multilingual Visual Information Extraction by Language Decoupled Pretraining","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2503.16096","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2509.21205","title":"TABLET: A Large-Scale Dataset for Robust Visual Table Understanding","created":"2025-09-25","cited_by_count":5,"area":null},{"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":"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":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2605.12882","title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","created":"2026-05-13","cited_by_count":5,"area":null},{"id":"2411.17835","title":"Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction","created":"2024-11-19","cited_by_count":4,"area":null},{"id":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2511.13283","title":"TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2512.10004","title":"Exploring LLMs for Scientific Information Extraction Using The SciEx Framework","created":"2025-12-10","cited_by_count":4,"area":null},{"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":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2503.04065","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2504.18406","title":"HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2512.03514","title":"M3DR: Towards Universal Multilingual Multimodal Document Retrieval","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2506.21625","title":"Doc2SAR: A Synergistic Framework for High-Fidelity Extraction of Structure-Activity Relationships from Scientific Documents","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.12883","title":"HRSeg: High-Resolution Visual Perception and Enhancement for Reasoning Segmentation","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2606.01717","title":"Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2410.09729","title":"MIRAGE: Multimodal Identification and Recognition of Annotations in Indian General Prescriptions","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2505.17235","title":"CHAOS: Chart Analysis with Outlier Samples","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2511.04161","title":"Seeing Straight: Document Orientation Detection for Efficient OCR","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2602.07645","title":"From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.22819","title":"TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2609.03445","title":"OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2507.08458","title":"A document is worth a structured record: Principled inductive bias design for document recognition","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.23273","title":"SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2510.09822","title":"Task-Aware Resolution Optimization for Visual Large Language Models","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2512.18115","title":"Layout-Aware Text Editing for Efficient Transformation of Academic PDFs to Markdown","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.10104","title":"MathDoc: Benchmarking Structured Extraction and Active Refusal on Noisy Mathematics Exam Papers","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.22026","title":"RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.09414","title":"PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.26462","title":"A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2609.13268","title":"Capability-Routed Visual Retrieval and Evidence Threading for Long-Context Document Question Answering","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.17458","title":"Tables Decoded: DELTA for Structure, TARQA for Understanding","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.19158","title":"VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.20423","title":"WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}