{"total":33,"rows":[{"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":"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":"2502.08826","title":"Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation","created":"2025-02-12","cited_by_count":42,"area":"rag"},{"id":"2412.10704","title":"VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation","created":"2024-12-14","cited_by_count":41,"area":"rag"},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40,"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":"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":"2601.08620","title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","created":"2026-01-13","cited_by_count":26,"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":"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":"2508.08632","title":"AgriGPT: a Large Language Model Ecosystem for Agriculture","created":"2025-08-12","cited_by_count":11,"area":"rag"},{"id":"2510.15253","title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","created":"2025-10-17","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":"2510.07233","title":"LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding","created":"2025-10-08","cited_by_count":7,"area":"rag"},{"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":"2511.20227","title":"HKRAG: Holistic Knowledge Retrieval-Augmented Generation Over Visually-Rich Documents","created":"2025-11-25","cited_by_count":5,"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":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2511.06582","title":"TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations","created":"2025-11-10","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":"2604.23276","title":"Lightweight and Production-Ready PDF Visual Element Parsing","created":"2026-04-25","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":"2605.25379","title":"StateRAG: Typed State Contracts for Complex Retrieval-Augmented Generation","created":"2026-05-25","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":"2607.24760","title":"CHaystack: Benchmarking Chinese Document Retrieval and VQA","created":"2026-05-30","cited_by_count":0,"area":"rag"},{"id":"2608.07006","title":"Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?","created":"2026-08-07","cited_by_count":0,"area":"rag"},{"id":"2608.12335","title":"HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings","created":"2026-06-03","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":"2608.30163","title":"Doc-REFRAG: Rethinking Multimodal Document Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"rag"},{"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"}],"next_cursor":null}