{"total":63,"rows":[{"id":"2504.05299","title":"SmolVLM: Redefining small and efficient multimodal models","created":"2025-04-07","cited_by_count":237,"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":"2505.21497","title":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","created":"2025-05-27","cited_by_count":63,"area":null},{"id":"2503.11576","title":"SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion","created":"2025-03-14","cited_by_count":53,"area":"mllm"},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47,"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":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2510.15349","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-10-17","cited_by_count":17,"area":"mllm"},{"id":"2512.03413","title":"BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents","created":"2025-12-03","cited_by_count":16,"area":"rag"},{"id":"2605.12678","title":"No One Knows the State of the Art in Geospatial Foundation Models","created":"2026-05-12","cited_by_count":12,"area":null},{"id":"2604.08538","title":"ParseBench: A Document Parsing Benchmark for AI Agents","created":"2026-04-09","cited_by_count":11,"area":"agents"},{"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":"2507.05093","title":"The Hidden Threat in Plain Text: Attacking RAG Data Loaders","created":"2025-07-07","cited_by_count":8,"area":"rag"},{"id":"2507.19492","title":"ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation","created":"2025-05-31","cited_by_count":8,"area":null},{"id":"2603.22458","title":"MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2603.27064","title":"ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding","created":"2026-03-28","cited_by_count":8,"area":"mllm"},{"id":"2506.16035","title":"Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding","created":"2025-06-19","cited_by_count":6,"area":"rag"},{"id":"2602.12957","title":"HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding","created":"2026-02-13","cited_by_count":6,"area":"mllm"},{"id":"2508.03644","title":"Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?","created":"2025-08-05","cited_by_count":5,"area":"mllm"},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2604.11969","title":"Narrative-Driven Paper-to-Slide Generation via ArcDeck","created":"2026-04-13","cited_by_count":5,"area":null},{"id":"2606.02915","title":"Any2Poster: Any-Source Poster Generation Across Modalities and Domains","created":"2026-06-01","cited_by_count":5,"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":"2603.15118","title":"VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2506.03197","title":"Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2509.11253","title":"VideoAgent: Personalized Synthesis of Scientific Videos","created":"2025-09-14","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":"2606.26122","title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","created":"2026-05-27","cited_by_count":3,"area":"agents"},{"id":"2508.13256","title":"CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Support","created":"2025-08-18","cited_by_count":2,"area":"agents"},{"id":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2602.17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2508.15817","title":"Meet Your New Client: Writing Reports for AI -- Benchmarking Information Loss in Market Research Deliverables","created":"2025-08-17","cited_by_count":1,"area":"rag"},{"id":"2512.09577","title":"Auto-BenchmarkCard: Automated Synthesis of Benchmark Documentation","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2603.10765","title":"RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems","created":"2026-03-11","cited_by_count":1,"area":"rag"},{"id":"2604.04936","title":"Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems","created":"2026-01-08","cited_by_count":1,"area":"rag"},{"id":"2604.04948","title":"From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering","created":"2026-03-30","cited_by_count":1,"area":"rag"},{"id":"2605.12623","title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.02403","title":"AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.04231","title":"MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2608.12133","title":"GUIDE: Governed Unified Intelligence for Document-to-Artifact Generation in Enterprise Settings","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2504.19695","title":"SubGrapher: Visual Fingerprinting of Chemical Structures","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2506.09560","title":"Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2509.08907","title":"Automated Evidence Extraction and Scoring for Corporate Climate Policy Engagement: A Multilingual RAG Approach","created":"2025-09-10","cited_by_count":0,"area":"rag"},{"id":"2511.16417","title":"Pharos-ESG: A Framework for Multimodal Parsing, Contextual Narration, and Hierarchical Labeling of ESG Report","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2601.05125","title":"VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2602.06402","title":"MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing","created":"2026-02-06","cited_by_count":0,"area":"mllm"},{"id":"2603.16325","title":"A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems","created":"2026-03-17","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":"2605.19866","title":"Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding","created":"2026-05-19","cited_by_count":0,"area":"mllm"},{"id":"2606.05658","title":"Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval","created":"2026-06-04","cited_by_count":0,"area":"rag"},{"id":"2606.27316","title":"LLM-Based Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.28365","title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2609.11493","title":"From Document Silos to Process Intelligence: A Multi-Layer Knowledge Graph for CMC Process Development","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.20732","title":"Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure","created":"2026-09-17","cited_by_count":0,"area":"mechinterp"},{"id":"2609.24220","title":"Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion","created":"2026-09-21","cited_by_count":0,"area":"rag"},{"id":"2609.26381","title":"Layout-Guided Masking for GROBID: Lightweight Structural Gains in Large-Scale Scientific PDF Ingestion","created":"2026-09-22","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},{"id":"2609.31660","title":"Parser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.02254","title":"Overcoming Challenges of Interpretive Structural Modeling with Large Language Models","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.12617","title":"GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports","created":"2026-10-08","cited_by_count":0,"area":"rag"},{"id":"2610.15103","title":"RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}