mlsanityData to 7 Oct 2026

MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition

arXiv 2510.08976 ↗First posted 10 Oct 2025cs.CV cs.DC cs.IRcited by 0

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

also in 1 more
Abstract (arXiv)

To effectively leverage user-specific data, retrieval augmented generation (RAG) is employed in multimodal large language model (MLLM) applications. However, conventional retrieval approaches often suffer from limited retrieval accuracy. Recent advances in multi-vector retrieval (MVR) improve accuracy by decomposing queries and matching against segmented images. They still suffer from sub-optimal accuracy and efficiency, overlooking alignment between the query and varying image objects and redundant fine-grained image segments. In this work, we present an efficient scheduling framework for image retrieval - MIRAGE. First, we introduce a novel hierarchical paradigm, employing multiple intermediate granularities for varying image objects to enhance alignment. Second, we minimize redundancy in retrieval by leveraging cross-hierarchy similarity consistency and hierarchy sparsity to minimize unnecessary matching computation. Furthermore, we configure parameters for each dataset automatically for practicality across diverse scenarios. Our empirical study shows that, MIRAGE not only achieves substantial accuracy improvements but also reduces computation by up to 3.5 times over the existing MVR system.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 14 of its 22 references that are in the map. First posted on arXiv 10 Oct 2025.

Builds on

14 of 22 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  6. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  7. 2018nocaps: novel object captioning at scalecited by 444
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  9. 2022CREPE: Can Vision-Language Foundation Models Reason Compositionally?cited by 177
  10. 2013A Theoretical Analysis of NDCG Type Ranking Measurescited by 119
  11. 2022PLAID: An Efficient Engine for Late Interaction Retrievalcited by 95
  12. 2020A Decade Survey of Content Based Image Retrieval using Deep Learningcited by 72
2 more
  1. 2025POQD: Performance-Oriented Query Decomposer for Multi-vector retrievalcited by 5
  2. 2025Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-rankingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Vector Retrieval with Similarity and Diversity: How Hard Is It?
  2. 2026Visual RAG Toolkit: Scaling Multi-Vector Visual Retrieval with Training-Free Pooling and Multi-Stage Search
  3. 2025ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning
  4. 2025RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal Retrieval-Augmented Generation on the Edge
  5. 2025AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
  6. 2025Cross-modal RAG: Sub-dimensional Text-to-Image Retrieval-Augmented Generation
  7. 2026CoCo-IR: Contextual Composed Image Retrieval
  8. 2026A Sanity Check on Composed Image Retrieval