{"total":34,"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":"2502.18017","title":"ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents","created":"2025-02-25","cited_by_count":66,"area":"rag"},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59,"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":"2510.01149","title":"ModernVBERT: Towards Smaller Visual Document Retrievers","created":"2025-10-01","cited_by_count":21,"area":"rag"},{"id":"2508.07493","title":"VisR-Bench: An Empirical Study on Visual Retrieval-Augmented Generation for Multilingual Long Document Understanding","created":"2025-08-10","cited_by_count":14,"area":"rag"},{"id":"2505.05666","title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","created":"2025-05-08","cited_by_count":11,"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":"2510.27261","title":"RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding","created":"2025-10-31","cited_by_count":8,"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":"2504.07643","title":"CollEX -- A Multimodal Agentic RAG System Enabling Interactive Exploration of Scientific Collections","created":"2025-04-10","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":"2601.17644","title":"Do Multimodal RAG Systems Leak Data? A Comprehensive Evaluation of Membership Inference and Image Caption Retrieval Attacks","created":"2026-01-25","cited_by_count":3,"area":"rag"},{"id":"2604.16313","title":"MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering","created":"2026-02-01","cited_by_count":3,"area":"rag"},{"id":"2504.03524","title":"RANa: Retrieval-Augmented Navigation","created":"2025-04-04","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":"2505.21956","title":"Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented Generation","created":"2025-05-28","cited_by_count":1,"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":"2506.10030","title":"Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment","created":"2025-06-10","cited_by_count":1,"area":"rag"},{"id":"2509.02123","title":"CMRAG: Co-modality-based visual document retrieval and question answering","created":"2025-09-02","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":"2508.16577","title":"MV-RAG: Retrieval Augmented Multiview Diffusion","created":"2025-08-22","cited_by_count":0,"area":"rag"},{"id":"2603.04238","title":"Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG","created":"2026-03-04","cited_by_count":0,"area":"rag"},{"id":"2604.05268","title":"Region-R1: Reinforcing Query-Side Region Cropping for Multi-Modal Re-Ranking","created":"2026-04-07","cited_by_count":0,"area":"rag"},{"id":"2605.10253","title":"Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation","created":"2026-05-11","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":"2606.04240","title":"Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)","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":"2607.24663","title":"A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility","created":"2026-07-27","cited_by_count":0,"area":"rag"},{"id":"2607.24760","title":"CHaystack: Benchmarking Chinese Document Retrieval and VQA","created":"2026-05-30","cited_by_count":0,"area":"rag"},{"id":"2608.01211","title":"VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval","created":"2026-08-02","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":"2609.23769","title":"PRISM-RAG: Multimodal Hypergraph Retrieval-Augmented Generation for Tobacco Product and Legislative Policy Reasoning","created":"2026-09-20","cited_by_count":0,"area":"rag"}],"next_cursor":null}