{"total":49,"rows":[{"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":"2506.10741","title":"PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework","created":"2025-06-12","cited_by_count":40,"area":null},{"id":"2503.14908","title":"POSTA: A Go-to Framework for Customized Artistic Poster Generation","created":"2025-03-19","cited_by_count":36,"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":"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":"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":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"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":"2505.13535","title":"Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments","created":"2025-05-18","cited_by_count":9,"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":"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":"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":"2407.06904","title":"Hypergraph based Understanding for Document Semantic Entity Recognition","created":"2024-07-09","cited_by_count":4,"area":null},{"id":"2410.01609","title":"SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction","created":"2024-10-02","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":"2404.08860","title":"Enhancing Mobile \"How-to\" Queries with Automated Search Results Verification and Reranking","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2409.19573","title":"See then Tell: Enhancing Key Information Extraction with Vision Grounding","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2607.07179","title":"Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering","created":"2026-07-08","cited_by_count":3,"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":"2508.14395","title":"NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding","created":"2025-08-20","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":"2511.17881","title":"MGA-VQA: Secure and Interpretable Graph-Augmented Visual Question Answering with Memory-Guided Protection Against Unauthorized Knowledge Use","created":"2025-11-22","cited_by_count":1,"area":null},{"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":"2601.22455","title":"ScribbleSense: Generative Scribble-Based Texture Editing with Intent Prediction","created":"2026-01-30","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":"2605.18025","title":"TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?","created":"2026-05-18","cited_by_count":1,"area":null},{"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":"2409.05275","title":"RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2507.08606","title":"DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures","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":"2510.19585","title":"Detecting Latin in Historical Books with Large Language Models: A Multimodal Benchmark","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2512.03335","title":"Step-by-step Layered Design Generation","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2512.17151","title":"Text-Conditioned Background Generation for Editable Multi-Layer Documents","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.11425","title":"PubMed-OCR: PMC Open Access OCR Annotations","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.02014","title":"Rethinking Genomic Modeling Through Optical Character Recognition","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.09337","title":"Kyrtos: A methodology for automatic deep analysis of graphic charts with curves in technical documents","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2602.13345","title":"BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents","created":"2026-02-12","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":"2606.02162","title":"Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis","created":"2026-06-01","cited_by_count":0,"area":null},{"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":"2606.11238","title":"Artificial Intelligence in Ship Finance: Applications, Opportunities, and a Case Study in AI-Augmented Loan Origination","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.16203","title":"DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2609.17538","title":"From Pixels to Pairs: A Comprehensive Benchmark of LLM-Driven Key-Value Extraction in Noisy Document Settings","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.31341","title":"The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}