{"total":182,"rows":[{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354,"area":"rag"},{"id":"2304.01116","title":"ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model","created":"2023-04-03","cited_by_count":287,"area":"rag"},{"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":"2210.02928","title":"MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text","created":"2022-10-06","cited_by_count":220,"area":"rag"},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210,"area":"rag"},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158,"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":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2203.07722","title":"ReACC: A Retrieval-Augmented Code Completion Framework","created":"2022-03-15","cited_by_count":119,"area":"rag"},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107,"area":"rag"},{"id":"2202.11233","title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","created":"2022-02-22","cited_by_count":106,"area":"rag"},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77,"area":"rag"},{"id":"2207.13038","title":"Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models","created":"2022-07-26","cited_by_count":64,"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":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"id":"2501.05874","title":"VideoRAG: Retrieval-Augmented Generation over Video Corpus","created":"2025-01-10","cited_by_count":57,"area":"rag"},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51,"area":"rag"},{"id":"2410.08182","title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models","created":"2024-10-10","cited_by_count":42,"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":"2207.13162","title":"Retrieval-Augmented Transformer for Image Captioning","created":"2022-07-26","cited_by_count":38,"area":"rag"},{"id":"2310.10445","title":"MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities","created":"2023-10-16","cited_by_count":38,"area":"rag"},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2311.13602","title":"Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation","created":"2023-11-22","cited_by_count":35,"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":"2311.15879","title":"EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension","created":"2023-11-27","cited_by_count":32,"area":"rag"},{"id":"2303.00534","title":"RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training","created":"2023-03-01","cited_by_count":31,"area":"rag"},{"id":"2410.21943","title":"Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications","created":"2024-10-29","cited_by_count":31,"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":"2302.08268","title":"Retrieval-augmented Image Captioning","created":"2023-02-16","cited_by_count":29,"area":"rag"},{"id":"2309.08051","title":"Retrieval-Augmented Text-to-Audio Generation","created":"2023-09-14","cited_by_count":24,"area":"rag"},{"id":"2510.01149","title":"ModernVBERT: Towards Smaller Visual Document Retrievers","created":"2025-10-01","cited_by_count":21,"area":"rag"},{"id":"2304.05173","title":"Improving Image Recognition by Retrieving from Web-Scale Image-Text Data","created":"2023-04-11","cited_by_count":20,"area":"rag"},{"id":"2305.19518","title":"Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels","created":"2023-05-31","cited_by_count":20,"area":"rag"},{"id":"2502.00848","title":"RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning","created":"2025-02-02","cited_by_count":20,"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":"2305.19821","title":"LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting","created":"2023-05-31","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":"2406.11148","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","created":"2024-06-17","cited_by_count":15,"area":"rag"},{"id":"2501.01120","title":"Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning","created":"2025-01-02","cited_by_count":15,"area":"rag"},{"id":"2402.02972","title":"Retrieval-Augmented Score Distillation for Text-to-3D Generation","created":"2024-02-05","cited_by_count":14,"area":"rag"},{"id":"2412.16500","title":"Speech Retrieval-Augmented Generation without Automatic Speech Recognition","created":"2024-12-21","cited_by_count":14,"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":"2505.23990","title":"Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding","created":"2025-05-29","cited_by_count":13,"area":"rag"},{"id":"2411.19921","title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","created":"2024-11-29","cited_by_count":12,"area":"rag"},{"id":"2409.12140","title":"MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion","created":"2024-09-18","cited_by_count":11,"area":"rag"},{"id":"2410.04749","title":"LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic Pathologies","created":"2024-10-07","cited_by_count":11,"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":"2508.02605","title":"ReMoMask: Retrieval-Augmented Masked Motion Generation","created":"2025-08-04","cited_by_count":11,"area":"rag"},{"id":"2406.19150","title":"RAVEN: Multitask Retrieval Augmented Vision-Language Learning","created":"2024-06-27","cited_by_count":10,"area":"rag"},{"id":"2408.12352","title":"GarmentAligner: Text-to-Garment Generation via Retrieval-augmented Multi-level Corrections","created":"2024-08-22","cited_by_count":10,"area":"rag"},{"id":"2505.07879","title":"OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval","created":"2025-05-10","cited_by_count":10,"area":"rag"},{"id":"2510.26160","title":"CRAG-MM: Multi-modal Multi-turn Comprehensive RAG Benchmark","created":"2025-10-30","cited_by_count":10,"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":"2406.02265","title":"Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning","created":"2024-06-04","cited_by_count":9,"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":"2412.16086","title":"Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG","created":"2024-12-20","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":"2407.02233","title":"Synthetic Multimodal Question Generation","created":"2024-07-02","cited_by_count":8,"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":"2505.01657","title":"RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation","created":"2025-05-03","cited_by_count":8,"area":"rag"},{"id":"2506.03437","title":"Quake: Adaptive Indexing for Vector Search","created":"2025-06-03","cited_by_count":8,"area":"rag"},{"id":"2405.13127","title":"Towards Retrieval-Augmented Architectures for Image Captioning","created":"2024-05-21","cited_by_count":7,"area":"rag"},{"id":"2505.06020","title":"ArtRAG: Retrieval-Augmented Generation with Structured Context for Visual Art Understanding","created":"2025-05-09","cited_by_count":7,"area":"rag"},{"id":"2506.21934","title":"CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design","created":"2025-06-27","cited_by_count":7,"area":"rag"},{"id":"2407.02994","title":"MedPix 2.0: A Comprehensive Multimodal Biomedical Data set for Advanced AI Applications with Retrieval Augmented Generation and Knowledge Graphs","created":"2024-07-03","cited_by_count":6,"area":"rag"},{"id":"2504.05573","title":"MicroNN: An On-device Disk-resident Updatable Vector Database","created":"2025-04-08","cited_by_count":6,"area":"rag"},{"id":"2504.08761","title":"UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation","created":"2025-03-31","cited_by_count":6,"area":"rag"},{"id":"2601.21162","title":"A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning","created":"2026-01-29","cited_by_count":6,"area":"rag"},{"id":"2409.02343","title":"NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval","created":"2024-09-04","cited_by_count":5,"area":"rag"},{"id":"2410.11824","title":"KITTEN: A Knowledge-Intensive Evaluation of Image Generation on Visual Entities","created":"2024-10-15","cited_by_count":5,"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":"2502.18536","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","created":"2025-02-25","cited_by_count":5,"area":"rag"},{"id":"2504.06672","title":"RAGME: Retrieval Augmented Video Generation for Enhanced Motion Realism","created":"2025-04-09","cited_by_count":5,"area":"rag"},{"id":"2505.13957","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"rag"},{"id":"2505.19189","title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","created":"2025-05-25","cited_by_count":5,"area":"rag"},{"id":"2507.09174","title":"RAMA: Retrieval-Augmented Multi-Agent Framework for Misinformation Detection in Multimodal Fact-Checking","created":"2025-07-12","cited_by_count":5,"area":"rag"},{"id":"2508.11246","title":"RAG for Geoscience: What We Expect, Gaps and Opportunities","created":"2025-08-15","cited_by_count":5,"area":"rag"},{"id":"2511.16654","title":"Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems","created":"2025-11-20","cited_by_count":5,"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":"2601.10168","title":"RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation","created":"2026-01-15","cited_by_count":5,"area":"rag"},{"id":"2403.14421","title":"DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning","created":"2024-03-21","cited_by_count":4,"area":"rag"},{"id":"2501.14101","title":"StreamingRAG: Real-time Contextual Retrieval and Generation Framework","created":"2025-01-23","cited_by_count":4,"area":"rag"},{"id":"2504.07415","title":"RA-RRG: Multimodal Retrieval-Augmented Radiology Report Generation with Key Phrase Extraction","created":"2025-04-10","cited_by_count":4,"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":"2505.23275","title":"Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception","created":"2025-05-29","cited_by_count":4,"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":"2405.17706","title":"Video Enriched Retrieval Augmented Generation Using Aligned Video Captions","created":"2024-05-27","cited_by_count":3,"area":"rag"},{"id":"2408.11793","title":"Leveraging Chemistry Foundation Models to Facilitate Structure Focused Retrieval Augmented Generation in Multi-Agent Workflows for Catalyst and Materials Design","created":"2024-08-21","cited_by_count":3,"area":"rag"},{"id":"2411.11323","title":"SayComply: Grounding Field Robotic Tasks in Operational Compliance through Retrieval-Based Language Models","created":"2024-11-18","cited_by_count":3,"area":"rag"},{"id":"2412.16701","title":"AlzheimerRAG: Multimodal Retrieval Augmented Generation for Clinical Use Cases using PubMed articles","created":"2024-12-21","cited_by_count":3,"area":"rag"},{"id":"2505.17162","title":"DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes","created":"2025-05-22","cited_by_count":3,"area":"rag"},{"id":"2508.09105","title":"SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling","created":"2025-08-12","cited_by_count":3,"area":"rag"},{"id":"2509.14267","title":"Graph-Enhanced Retrieval-Augmented Question Answering for E-Commerce Customer Support","created":"2025-09-15","cited_by_count":3,"area":"rag"},{"id":"2511.21002","title":"Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning","created":"2025-11-26","cited_by_count":3,"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":"2602.13239","title":"CrisiSense-RAG: Crisis Sensing Multimodal Retrieval-Augmented Generation for Rapid Disaster Impact Assessment","created":"2026-01-30","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":"2603.15822","title":"Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation","created":"2026-03-16","cited_by_count":3,"area":"rag"},{"id":"2604.27934","title":"MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection","created":"2026-04-30","cited_by_count":3,"area":"rag"}],"next_cursor":"100"}