mlsanityData to 14 Oct 2026

WARP: An Efficient Engine for Multi-Vector Retrieval

arXiv 2501.17788 ↗First posted 29 Jan 2025cs.IRcited by 17

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 13.

17 papers.

Sort:

By area:

  1. 2025DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruningcited by 20
  2. 2026Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Frameworkcited by 10
  3. 2025Simple Projection Variants Improve ColBERT Performancecited by 2
  4. 2026Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrievalcited by 2
  5. 2025LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026cited by 1
  6. 2026Topo-RAG: Topology-aware retrieval for hybrid text-table documentscited by 1
  7. 2026LEMUR: Learned Multi-Vector Retrievalcited by 1
  8. 2026Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexingcited by 1
  9. 2026No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrievalcited by 1
  10. 2026TileMaxSim: IO-Aware GPU MaxSim Scoring with Dimension Tiling and Fused Product Quantizationcited by 1
  11. 2026DamageScope: Vision-Language Retrieval at Scale for Disaster Damage Assessment from Satellite Imagerycited by 1
  12. 2026EigenLI: Spectral Approximations to Late Interactioncited by 1
5 more
  1. 2025MINT: Multi-Vector Search Index Tuningcited by 0
  2. 2026ColBERTSaR: Sparsified ColBERT Index via Product Quantizationcited by 0
  3. 2026CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrievalcited by 0
  4. 2026BELXTR: Biomedical Entity Linking via Contextualized Token Retrievalcited by 0
  5. 2026Beyond the Final Embedding: Retrieving Memories from Token-Level Evidencecited by 0