1.  [](/)
2.  [Research](/research)
3.  Google's MUVERA: The One-Vector Trick Behind Fast Multi-Vector Search

[Back to Research](/research)

Google Research[arXiv:2405.19504](https://mxp.co/e/muvera)

# Google's MUVERA: The One-Vector Trick Behind Fast Multi-Vector Search

MUVERA collapses a multi-vector (ColBERT-style) representation into a single Fixed Dimensional Encoding whose dot product provably approximates the multi-vector score: so late-interaction quality can ride an ordinary single-vector ANN index.

## Where this fits in Mixpeek

Mixpeek's multi-vector search (MVS) keeps one embedding per token or region for late-interaction quality, which is expensive to serve at scale. MUVERA is the technique that lets that quality run on a standard ANN index: encode each document's token set into one FDE for a cheap first-tier recall pass, then rerank the top candidates with exact Chamfer/MaxSim over the original vectors. It's the theory behind Mixpeek's two-tier retrieve-then-rerank path: cheap recall over everything, exact scoring over the shortlist.

## About this research

Multi-vector models like ColBERT keep one embedding per token, which wins on accuracy but breaks fast indexes: Chamfer scoring forces custom pipelines like PLAID. MUVERA's Fixed Dimensional Encodings randomly partition the embedding space, aggregate each region's tokens (queries sum, documents average), and concatenate the blocks into one vector whose dot product provably approximates the multi-vector score, the first single-vector proxy with theoretical guarantees. On BEIR: about 10% higher recall at 90% lower latency than PLAID, 2 to 5x fewer candidates, 32x memory compression via product quantization. Paper: arxiv.org/abs/2405.19504

muveramulti-vectorlate-interactionannretrievalvector-search

## Frequently asked questions

What is a Fixed Dimensional Encoding (FDE)?+

Why can't ColBERT-style retrieval use standard vector indexes?+

## Go deeper

*   [Diagram: How a multi-vector set becomes one fixed vector →](/diagrams/muvera-fde-pipeline)
*   [Diagram: Query/document asymmetry in FDEs →](/diagrams/muvera-query-doc-asymmetry)
*   [Diagram: Two-tier retrieval (cheap FDE recall, exact rerank) →](/diagrams/muvera-two-tier-retrieval)
*   [Guide: What Is MUVERA? The FDE construction in full →](/guides/muvera-fixed-dimensional-encodings-multi-vector-retrieval)
*   [Guide: Late-Interaction Retrieval (ColBERT, ColPali, MUVERA) →](/guides/late-interaction-retrieval)

Put the research to work

Mixpeek turns video, images, audio, and documents in your object storage into searchable, timestamped results through one API: the retrieval stack these papers describe.

[Search your own data](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=research_detail&utm_campaign=mvs_onramp)

## Related research

[

![Late Interaction: How ColBERT and ColPali Search Documents as Images](https://cdn.mixpeek.com/videos/thumbs/82-late-interaction.jpg)

Stanford & Illuin (ColPali)

Late Interaction: How ColBERT and ColPali Search Documents as Images



](/research/colbert-colpali)[

![Cluster with Auctions: The FAISS Team Teaches Vector Indexes to Learn From Queries](https://cdn.mixpeek.com/videos/thumbs/70-cwa.jpg)

Meta AI (FAISS)

Cluster with Auctions: The FAISS Team Teaches Vector Indexes to Learn From Queries



](/research/cluster-with-auctions)[

![Learned Indexes Explained: When a Model Replaces the B-Tree](https://cdn.mixpeek.com/videos/thumbs/46-learned-indexes.jpg)

Google

Learned Indexes Explained: When a Model Replaces the B-Tree



](/research/learned-indexes)