{"total":21,"rows":[{"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":"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":"2501.06713","title":"MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation","created":"2025-01-12","cited_by_count":28,"area":"rag"},{"id":"2504.20734","title":"UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities","created":"2025-04-29","cited_by_count":20,"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":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"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":"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":"2510.27261","title":"RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding","created":"2025-10-31","cited_by_count":8,"area":"rag"},{"id":"2504.04988","title":"Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model","created":"2025-04-07","cited_by_count":6,"area":"rag"},{"id":"2507.22917","title":"Reading Between the Timelines: RAG for Answering Diachronic Questions","created":"2025-07-21","cited_by_count":4,"area":"rag"},{"id":"2602.10271","title":"MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation","created":"2026-02-10","cited_by_count":4,"area":"rag"},{"id":"2507.03868","title":"From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEM","created":"2025-07-05","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":"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":"2412.11396","title":"Leveraging Retrieval-Augmented Tags for Large Vision-Language Understanding in Complex Scenes","created":"2024-12-16","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":"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":"2608.25935","title":"TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding","created":"2026-08-26","cited_by_count":0,"area":"rag"},{"id":"2609.14100","title":"RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes","created":"2026-09-12","cited_by_count":0,"area":"rag"}],"next_cursor":null}