mlsanityData to 7 Oct 2026

Multimodal RAG

410 papers1 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: multimodal, visual, retrieval, generation, retrieval-augmented

Key facts. Multimodal RAG: 410 papers on arXiv since 2022 (data through 7 Oct 2026). 68 of its 410 mapped papers (17%) cite “VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents” (2024, arXiv 2410.10594). 61 of its 410 mapped papers (15%) cite “MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text” (2022, arXiv 2210.02928). 9 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

9 new papers, 17 Sep – 7 Oct; 1 this week.

  1. This week · 1
  2. EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding
  3. Earlier · 8
  4. CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation
  5. Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models
  6. Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation
  7. TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
  8. Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving
  9. Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
  10. PRISM-RAG: Multimodal Hypergraph Retrieval-Augmented Generation for Tobacco Product and Legislative Policy Reasoning also fits: Legal and financial RAG
  11. Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation

Foundations

Most cited by papers here

  1. VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents2024cited by 68 here
  2. MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text2022cited by 61 here
  3. Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories2023cited by 40 here
  4. M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding2024cited by 30 here
  5. Re-Imagen: Retrieval-Augmented Text-to-Image Generator2022cited by 28 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 64 here
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 231 here
  3. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 61 here
  4. 2022Retrieval-Augmented Multimodal Language Modelingcited by 23 here
  5. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 22 here
  6. 2023In-Context Retrieval-Augmented Language Modelscited by 30 here
  7. 2023Active Retrieval Augmented Generationcited by 19 here
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 53 here
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 62 here
  10. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 23 here
  11. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 18 here
13 more it builds on, not in this chain
  1. 2022Re-Imagen: Retrieval-Augmented Text-to-Image Generatorcited by 28 here
  2. 2022Retrieval Augmented Visual Question Answering with Outside Knowledgecited by 25 here
  3. 2022REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memorycited by 28 here
  4. 2023Encyclopedic VQA: Visual questions about detailed properties of fine-grained categoriescited by 40 here
  5. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 19 here
  6. 2024Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMscited by 25 here
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 37 here
  8. 2024MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Modelscited by 20 here
  9. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documentscited by 68 here
  10. 2024Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applicationscited by 19 here
  11. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understandingcited by 30 here
  12. 2024Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehensioncited by 21 here
  13. 2025ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agentscited by 20 here

The 24 most cited of 540.

Browse

30 of 410, ranked 6–35

  1. 6REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory202228
  2. 7Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs202425
  3. 8Retrieval Augmented Visual Question Answering with Outside Knowledge202225
  4. 9Retrieval-Augmented Multimodal Language Modeling202223
  5. 10Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension202421
  6. 11ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents202520
  7. 12MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models202420
  8. 13Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications202419
  9. 14VideoRAG: Retrieval-Augmented Generation over Video Corpus202518
  10. 15VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos202518
All 30
  1. 16Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent202417
  2. 17VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents202515
  3. 18VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation202414
  4. 19Is Semantic Chunking Worth the Computational Cost?202413
  5. 20Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation202512
  6. 21Retrieval Augmented Classification for Long-Tail Visual Recognition202212
  7. 22VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning202511
  8. 23MLLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training202410
  9. 24Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning202310
  10. 25Retrieval-augmented Image Captioning202310
  11. 26Retrieval-Augmented Transformer for Image Captioning202210
  12. 27MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System20259
  13. 28ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model20239
  14. 29A Survey of Multimodal Retrieval-Augmented Generation20258
  15. 30Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering20238
  16. 31RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance20257
  17. 32MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation20257
  18. 33Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries20257
  19. 34Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook20257
  20. 35OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval20257