{"total":82,"rows":[{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357,"area":"mllm"},{"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":"2407.01523","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":"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":"2402.05935","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","created":"2024-02-08","cited_by_count":131,"area":"mllm"},{"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":"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":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"area":null},{"id":"2401.16160","title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs","created":"2024-01-29","cited_by_count":84,"area":"mllm"},{"id":"2111.08609","title":"Document AI: Benchmarks, Models and Applications","created":"2021-11-16","cited_by_count":62,"area":null},{"id":"2302.05658","title":"DocILE Benchmark for Document Information Localization and Extraction","created":"2023-02-11","cited_by_count":58,"area":null},{"id":"2505.20147","title":"FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities","created":"2025-05-26","cited_by_count":46,"area":"mllm"},{"id":"2404.06918","title":"HRVDA: High-Resolution Visual Document Assistant","created":"2024-04-10","cited_by_count":37,"area":"mllm"},{"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":"2311.18248","title":"mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model","created":"2023-11-30","cited_by_count":32,"area":"mllm"},{"id":"2405.15574","title":"Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models","created":"2024-05-24","cited_by_count":30,"area":"ssm"},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2412.09616","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","created":"2024-12-12","cited_by_count":28,"area":"mllm"},{"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":"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":"2407.14439","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","created":"2024-07-19","cited_by_count":22,"area":"mllm"},{"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":"2503.14140","title":"Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding","created":"2025-03-18","cited_by_count":20,"area":"mllm"},{"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":"2503.02304","title":"A Token-level Text Image Foundation Model for Document Understanding","created":"2025-03-04","cited_by_count":14,"area":"mllm"},{"id":"2411.05254","title":"Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding","created":"2024-11-08","cited_by_count":12,"area":"mllm"},{"id":"2206.11229","title":"Business Document Information Extraction: Towards Practical Benchmarks","created":"2022-06-20","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":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2411.17125","title":"DOGR: Towards Versatile Visual Document Grounding and Referring","created":"2024-11-26","cited_by_count":10,"area":"mllm"},{"id":"2502.01341","title":"AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding","created":"2025-02-03","cited_by_count":9,"area":"mllm"},{"id":"2502.16586","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","created":"2025-02-23","cited_by_count":9,"area":"mllm"},{"id":"2602.12247","title":"ExtractBench: A Benchmark and Evaluation Methodology for Complex Structured Extraction","created":"2026-02-12","cited_by_count":9,"area":null},{"id":"2310.16131","title":"GenKIE: Robust Generative Multimodal Document Key Information Extraction","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2404.04003","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","created":"2024-04-05","cited_by_count":8,"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":"2208.08201","title":"Understanding Long Documents with Different Position-Aware Attentions","created":"2022-08-17","cited_by_count":7,"area":null},{"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":"2502.18179","title":"Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2208.04011","title":"Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features","created":"2022-08-08","cited_by_count":5,"area":null},{"id":"2405.00505","title":"KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents","created":"2024-05-01","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":"2602.15958","title":"DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2304.14936","title":"Information Redundancy and Biases in Public Document Information Extraction Benchmarks","created":"2023-04-28","cited_by_count":4,"area":null},{"id":"2306.08937","title":"DocumentNet: Bridging the Data Gap in Document Pre-Training","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2307.10551","title":"PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2403.20101","title":"RealKIE: Five Novel Datasets for Enterprise Key Information Extraction","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2411.07722","title":"Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding","created":"2024-11-12","cited_by_count":4,"area":"mllm"},{"id":"2505.09498","title":"Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput","created":"2025-05-14","cited_by_count":4,"area":"mllm"},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2407.02842","title":"MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis","created":"2024-07-03","cited_by_count":3,"area":"mllm"},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2401.05167","title":"Watermark Text Pattern Spotting in Document Images","created":"2024-01-10","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":"2409.11282","title":"Leveraging Distillation Techniques for Document Understanding: A Case Study with FLAN-T5","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2506.01388","title":"VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2607.09068","title":"OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2301.12394","title":"DocILE 2023 Teaser: Document Information Localization and Extraction","created":"2023-01-29","cited_by_count":1,"area":null},{"id":"2403.07553","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2406.08226","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","created":"2024-06-12","cited_by_count":1,"area":"distill"},{"id":"2408.16986","title":"AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding","created":"2024-08-30","cited_by_count":1,"area":"mllm"},{"id":"2502.20295","title":"Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription","created":"2025-02-27","cited_by_count":1,"area":"mllm"},{"id":"2503.19658","title":"BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2607.04636","title":"Enhancing Large Multimodal Models in Key Information Extraction via Scene-Aware Document Synthesis","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2607.29677","title":"ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction","created":"2026-07-31","cited_by_count":1,"area":"agents"},{"id":"2609.32041","title":"Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2212.10047","title":"An Augmentation Strategy for Visually Rich Documents","created":"2022-12-20","cited_by_count":0,"area":null},{"id":"2304.10994","title":"Information Extraction from Documents: Question Answering vs Token Classification in real-world setups","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2310.16527","title":"Enhancing Document Information Analysis with Multi-Task Pre-training: A Robust Approach for Information Extraction in Visually-Rich Documents","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2405.06701","title":"Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents","created":"2024-05-08","cited_by_count":0,"area":null},{"id":"2409.05275","title":"RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2412.12902","title":"DoPTA: Improving Document Layout Analysis using Patch-Text Alignment","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2504.02971","title":"QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding","created":"2025-04-03","cited_by_count":0,"area":"mllm"},{"id":"2510.15727","title":"Invoice Information Extraction: Methods and Performance Evaluation","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2602.19188","title":"PositionOCR: Augmenting Positional Awareness in Multi-Modal Models via Hybrid Specialist Integration","created":"2026-02-22","cited_by_count":0,"area":"mllm"},{"id":"2607.05614","title":"BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2609.23679","title":"Mind the Gaps: A Curated Benchmark for Form Field Detection","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}