{"total":95,"rows":[{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182,"area":"lr"},{"id":"2501.00321","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","created":"2024-12-31","cited_by_count":173,"area":"mllm"},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67,"area":"agents"},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62,"area":"mllm"},{"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":"2404.09797","title":"TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding","created":"2024-04-15","cited_by_count":38,"area":"lr"},{"id":"2406.11633","title":"DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models","created":"2024-06-17","cited_by_count":36,"area":"mllm"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"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":"2504.12330","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","created":"2025-04-13","cited_by_count":31,"area":"rag"},{"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":"2507.14675","title":"Docopilot: Improving Multimodal Models for Document-Level Understanding","created":"2025-07-19","cited_by_count":19,"area":"mllm"},{"id":"2509.09912","title":"When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review","created":"2025-09-12","cited_by_count":19,"area":"safety"},{"id":"2505.21333","title":"MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios","created":"2025-05-27","cited_by_count":18,"area":"mllm"},{"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":"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":"2506.20168","title":"Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models","created":"2025-06-25","cited_by_count":12,"area":"mllm"},{"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":"2505.16957","title":"Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2502.17540","title":"PosterSum: A Multimodal Benchmark for Scientific Poster Summarization","created":"2025-02-24","cited_by_count":10,"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":"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":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"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":"2501.15074","title":"PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures","created":"2025-01-25","cited_by_count":7,"area":"mllm"},{"id":"2510.07233","title":"LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding","created":"2025-10-08","cited_by_count":7,"area":"rag"},{"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":"2412.17092","title":"SAIL: Sample-Centric In-Context Learning for Document Information Extraction","created":"2024-12-22","cited_by_count":6,"area":null},{"id":"2502.17315","title":"HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization","created":"2025-02-24","cited_by_count":6,"area":"alignment"},{"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":"2407.12358","title":"ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data","created":"2024-07-17","cited_by_count":5,"area":"mllm"},{"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":"2602.05191","title":"Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMs","created":"2026-02-05","cited_by_count":5,"area":"inference"},{"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":"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":"2505.17625","title":"Enhancing Large Vision-Language Models with Layout Modality for Table Question Answering on Japanese Annual Securities Reports","created":"2025-05-23","cited_by_count":4,"area":"mllm"},{"id":"2511.15059","title":"Evaluating Multimodal Large Language Models on Vertically Written Japanese Text","created":"2025-11-19","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":"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":"2410.03061","title":"DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models","created":"2024-10-04","cited_by_count":3,"area":"distill"},{"id":"2411.11435","title":"GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts","created":"2024-11-18","cited_by_count":3,"area":"mllm"},{"id":"2508.17290","title":"MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment","created":"2025-08-24","cited_by_count":3,"area":"mllm"},{"id":"2509.11773","title":"AgenticIE: An Adaptive Agent for Information Extraction from Complex Regulatory Documents","created":"2025-09-15","cited_by_count":3,"area":"agents"},{"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":"2504.10659","title":"Relation-Rich Visual Document Generator for Visual Information Extraction","created":"2025-04-14","cited_by_count":2,"area":"mllm"},{"id":"2508.10745","title":"Agentic Design Review System","created":"2025-08-14","cited_by_count":2,"area":"agents"},{"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":"2511.18192","title":"ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization","created":"2025-11-22","cited_by_count":2,"area":"agents"},{"id":"2607.04625","title":"Hierarchical Evidence-Driven Reasoning for Long Document Understanding","created":"2026-07-06","cited_by_count":2,"area":"rag"},{"id":"2607.09068","title":"OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents","created":"2026-07-10","cited_by_count":2,"area":null},{"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":"2505.18603","title":"Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"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":"2512.09666","title":"Neurosymbolic Information Extraction from Transactional Documents","created":"2025-12-10","cited_by_count":0,"area":"distill"},{"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":"2601.12260","title":"Docs2Synth: A Synthetic Data Trained Retriever Framework for Scanned Visually Rich Documents Understanding","created":"2026-01-18","cited_by_count":0,"area":"mllm"},{"id":"2601.19613","title":"Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs","created":"2026-01-27","cited_by_count":0,"area":"mllm"},{"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":"2602.22013","title":"RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual Degradations","created":"2026-02-25","cited_by_count":0,"area":"mllm"},{"id":"2602.22828","title":"TCM-DiffRAG: Personalized Syndrome Differentiation Reasoning Method for Traditional Chinese Medicine based on Knowledge Graph and Chain of Thought","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"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":"2605.31354","title":"Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual Agents","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"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":"2606.31145","title":"SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference","created":"2026-06-30","cited_by_count":0,"area":"inference"},{"id":"2607.00465","title":"StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"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":"2608.24763","title":"MoTE: Mixture of Task Experts for Multi-Task Video Understanding","created":"2026-08-25","cited_by_count":0,"area":"moe"},{"id":"2608.28784","title":"ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement","created":"2026-08-28","cited_by_count":0,"area":"mllm"},{"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}