# WARP: An Efficient Engine for Multi-Vector Retrieval

arXiv: https://arxiv.org/abs/2501.17788 · HTML: https://mlsanity.com/paper/2501.17788/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jan 2025.

## Built on by (most cited first, 17 of 17)

- [DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning](https://mlsanity.com/paper/2509.23883/) (2025)
- [Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework](https://mlsanity.com/paper/2602.19549/) (2026)
- [Simple Projection Variants Improve ColBERT Performance](https://mlsanity.com/paper/2510.12327/) (2025)
- [Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval](https://mlsanity.com/paper/2607.04605/) (2026)
- [LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026](https://mlsanity.com/paper/2511.00444/) (2025)
- [Topo-RAG: Topology-aware retrieval for hybrid text-table documents](https://mlsanity.com/paper/2601.10215/) (2026)
- [LEMUR: Learned Multi-Vector Retrieval](https://mlsanity.com/paper/2601.21853/) (2026)
- [Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing](https://mlsanity.com/paper/2604.28142/) (2026)
- [No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval](https://mlsanity.com/paper/2605.30120/) (2026)
- [TileMaxSim: IO-Aware GPU MaxSim Scoring with Dimension Tiling and Fused Product Quantization](https://mlsanity.com/paper/2606.26439/) (2026)
- [DamageScope: Vision-Language Retrieval at Scale for Disaster Damage Assessment from Satellite Imagery](https://mlsanity.com/paper/2608.21529/) (2026)
- [EigenLI: Spectral Approximations to Late Interaction](https://mlsanity.com/paper/2609.07561/) (2026)
- [MINT: Multi-Vector Search Index Tuning](https://mlsanity.com/paper/2504.20018/) (2025)
- [ColBERTSaR: Sparsified ColBERT Index via Product Quantization](https://mlsanity.com/paper/2606.05568/) (2026)
- [CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval](https://mlsanity.com/paper/2606.28365/) (2026)
- [BELXTR: Biomedical Entity Linking via Contextualized Token Retrieval](https://mlsanity.com/paper/2609.25859/) (2026)
- [Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence](https://mlsanity.com/paper/2610.13277/) (2026)

## Abstract (arXiv)

Multi-vector retrieval methods such as ColBERT and its recent variant, the ConteXtualized Token Retriever (XTR), offer high accuracy but face efficiency challenges at scale. To address this, we present WARP, a retrieval engine that substantially improves the efficiency of retrievers trained with the XTR objective through three key innovations: (1) WARPSELECT for dynamic similarity imputation; (2) implicit decompression, avoiding costly vector reconstruction during retrieval; and (3) a two-stage reduction process for efficient score aggregation. Combined with highly-optimized C++ kernels, our system reduces end-to-end latency compared to XTR's reference implementation by 41x, and achieves a 3x speedup over the ColBERTv2/PLAID engine, while preserving retrieval quality.