{"total":41,"rows":[{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77,"area":"rag"},{"id":"2505.22019","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","created":"2025-05-28","cited_by_count":68,"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":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","cited_by_count":32,"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":"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":"2510.03663","title":"UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG","created":"2025-10-04","cited_by_count":21,"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":"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":"2510.27261","title":"RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding","created":"2025-10-31","cited_by_count":8,"area":"rag"},{"id":"2511.20227","title":"HKRAG: Holistic Knowledge Retrieval-Augmented Generation Over Visually-Rich Documents","created":"2025-11-25","cited_by_count":5,"area":"rag"},{"id":"2602.12735","title":"VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph","created":"2026-02-13","cited_by_count":5,"area":"rag"},{"id":"2602.24134","title":"AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation","created":"2026-02-27","cited_by_count":5,"area":"rag"},{"id":"2603.21654","title":"Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks","created":"2026-03-23","cited_by_count":4,"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":"2608.02583","title":"UEmbed: Unified Sparse and Dense Multimodal Embeddings","created":"2026-08-03","cited_by_count":2,"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":"2603.07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","created":"2026-03-08","cited_by_count":1,"area":"rag"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2606.07235","title":"FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A","created":"2026-06-05","cited_by_count":1,"area":"rag"},{"id":"2510.04145","title":"Automating construction safety inspections using a multi-modal vision-language RAG framework","created":"2025-10-05","cited_by_count":0,"area":"rag"},{"id":"2510.17354","title":"Towards Mixed-Modal Retrieval for Universal Retrieval-Augmented Generation","created":"2025-10-20","cited_by_count":0,"area":"rag"},{"id":"2511.21121","title":"Beyond Patch Aggregation: 3-Pass Pyramid Indexing for Vision-Enhanced Document Retrieval","created":"2025-11-26","cited_by_count":0,"area":"rag"},{"id":"2512.12458","title":"Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval","created":"2025-12-13","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":"2601.14123","title":"A Systematic Analysis of Chunking Strategies for Reliable Question Answering","created":"2026-01-20","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":"2606.19960","title":"Stellar: Scalable Multimodal Document Retrieval for Natural Language Queries","created":"2026-06-18","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":"2608.01211","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":"2608.15698","title":"ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval","created":"2026-08-16","cited_by_count":0,"area":"rag"},{"id":"2608.16628","title":"Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement","created":"2026-08-17","cited_by_count":0,"area":"rag"},{"id":"2608.23176","title":"Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2608.29953","title":"SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking","created":"2026-08-30","cited_by_count":0,"area":"rag"},{"id":"2609.11646","title":"Your Retriever Already Knows: Distribution-Shape QPP for RAG Retrieval Sufficiency","created":"2026-09-10","cited_by_count":0,"area":"rag"},{"id":"2609.15800","title":"Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation","created":"2026-09-14","cited_by_count":0,"area":"rag"},{"id":"2609.19634","title":"Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation","created":"2026-09-17","cited_by_count":0,"area":"rag"},{"id":"2609.37349","title":"TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG","created":"2026-09-29","cited_by_count":0,"area":"rag"}],"next_cursor":null}