{"total":52,"rows":[{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245,"area":"rag"},{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"id":"2411.13093","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","created":"2024-11-20","cited_by_count":138,"area":"rag"},{"id":"2411.04952","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","created":"2024-11-07","cited_by_count":111,"area":"rag"},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36,"area":"rag"},{"id":"2502.12342","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","created":"2025-02-17","cited_by_count":35,"area":"rag"},{"id":"2504.12330","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","created":"2025-04-13","cited_by_count":31,"area":"rag"},{"id":"2412.14457","title":"VISA: Retrieval Augmented Generation with Visual Source Attribution","created":"2024-12-19","cited_by_count":28,"area":"rag"},{"id":"2501.06713","title":"MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation","created":"2025-01-12","cited_by_count":28,"area":"rag"},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26,"area":"rag"},{"id":"2510.01149","title":"ModernVBERT: Towards Smaller Visual Document Retrievers","created":"2025-10-01","cited_by_count":21,"area":"rag"},{"id":"2503.09149","title":"Memory-enhanced Retrieval Augmentation for Long Video Understanding","created":"2025-03-12","cited_by_count":17,"area":"rag"},{"id":"2502.16636","title":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","created":"2025-02-23","cited_by_count":16,"area":"rag"},{"id":"2505.17471","title":"FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain","created":"2025-05-23","cited_by_count":16,"area":"rag"},{"id":"2502.04176","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","created":"2025-02-06","cited_by_count":15,"area":"rag"},{"id":"2602.03992","title":"Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval","created":"2026-02-03","cited_by_count":10,"area":"rag"},{"id":"2411.16365","title":"Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines","created":"2024-11-25","cited_by_count":9,"area":"rag"},{"id":"2505.22584","title":"DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers","created":"2025-05-28","cited_by_count":9,"area":"rag"},{"id":"2506.11063","title":"Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation","created":"2025-05-30","cited_by_count":9,"area":"rag"},{"id":"2509.00366","title":"KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generation","created":"2025-08-30","cited_by_count":9,"area":"rag"},{"id":"2504.02132","title":"One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image","created":"2025-04-02","cited_by_count":8,"area":"rag"},{"id":"2512.20626","title":"MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation","created":"2025-11-26","cited_by_count":7,"area":"rag"},{"id":"2501.13340","title":"Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models","created":"2025-01-23","cited_by_count":5,"area":"rag"},{"id":"2508.12081","title":"VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models","created":"2025-08-16","cited_by_count":4,"area":"rag"},{"id":"2511.00903","title":"ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval","created":"2025-11-02","cited_by_count":4,"area":"rag"},{"id":"2507.22938","title":"A Graph-based Approach for Multi-Modal Question Answering from Flowcharts in Telecom Documents","created":"2025-07-25","cited_by_count":3,"area":"rag"},{"id":"2603.00511","title":"Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning","created":"2026-02-28","cited_by_count":3,"area":"rag"},{"id":"2608.10775","title":"SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation","created":"2026-08-11","cited_by_count":3,"area":"rag"},{"id":"2506.12494","title":"FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation","created":"2025-06-14","cited_by_count":2,"area":"rag"},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2604.09552","title":"MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval","created":"2026-01-31","cited_by_count":2,"area":"rag"},{"id":"2606.28344","title":"PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation","created":"2026-06-01","cited_by_count":2,"area":"rag"},{"id":"2506.09109","title":"CAIRe: Cultural Attribution of Images by Retrieval-Augmented Evaluation","created":"2025-06-10","cited_by_count":1,"area":"rag"},{"id":"2603.07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","created":"2026-03-08","cited_by_count":1,"area":"rag"},{"id":"2606.13141","title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","created":"2026-06-11","cited_by_count":1,"area":"rag"},{"id":"2607.05438","title":"Modality Relevance is not Modality Utility: Post-hoc Selective Modality Escalation for Cost-Aware Multimodal RAG","created":"2026-07-03","cited_by_count":1,"area":"rag"},{"id":"2608.08612","title":"REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering","created":"2026-08-09","cited_by_count":1,"area":"rag"},{"id":"2508.17394","title":"LVLM-Aware Multimodal Retrieval for RAG-Based Medical Diagnosis with General-Purpose Models","created":"2025-08-24","cited_by_count":0,"area":"rag"},{"id":"2512.16802","title":"Exploration of Augmentation Strategies in Multi-modal Retrieval-Augmented Generation for the Biomedical Domain: A Case Study Evaluating Question Answering in Glycobiology","created":"2025-12-18","cited_by_count":0,"area":"rag"},{"id":"2602.11156","title":"HybridRAG: A Practical LLM-based ChatBot Framework based on Pre-Generated Q&A over Raw Unstructured Documents","created":"2025-11-30","cited_by_count":0,"area":"rag"},{"id":"2602.22462","title":"MammoWise: Multi-Model Local RAG Pipeline for Mammography Report Generation","created":"2026-02-25","cited_by_count":0,"area":"rag"},{"id":"2604.15663","title":"CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval","created":"2026-04-17","cited_by_count":0,"area":"rag"},{"id":"2605.22829","title":"LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding","created":"2026-04-18","cited_by_count":0,"area":"rag"},{"id":"2606.03354","title":"ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation","created":"2026-06-02","cited_by_count":0,"area":"rag"},{"id":"2606.17430","title":"CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation","created":"2026-06-16","cited_by_count":0,"area":"rag"},{"id":"2606.19960","title":"Stellar: Scalable Multimodal Document Retrieval for Natural Language Queries","created":"2026-06-18","cited_by_count":0,"area":"rag"},{"id":"2607.22643","title":"Reason Before You Retrieve: Agentic Planning for Multi-modal RAG","created":"2026-06-24","cited_by_count":0,"area":"rag"},{"id":"2607.24554","title":"DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding","created":"2026-07-27","cited_by_count":0,"area":"rag"},{"id":"2608.16536","title":"DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption","created":"2026-08-17","cited_by_count":0,"area":"rag"},{"id":"2609.15660","title":"CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual Defense","created":"2026-09-14","cited_by_count":0,"area":"rag"}],"next_cursor":null}