Saved in:
Bibliographic Details
Main Authors: Kumar, Ramnath, Jain, Prateek, Hsieh, Cho-Jui
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.06389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911374413660160
author Kumar, Ramnath
Jain, Prateek
Hsieh, Cho-Jui
author_facet Kumar, Ramnath
Jain, Prateek
Hsieh, Cho-Jui
contents Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce FastLane, a novel retrieval framework that dynamically routes queries to their most informative representations, eliminating redundant token comparisons. FastLane employs a learnable routing mechanism optimized alongside the embedding model, leveraging self-attention and differentiable selection to maximize efficiency. Our approach reduces computational complexity by up to 30x while maintaining competitive retrieval performance. By bridging late-interaction models with ANNS, FastLane enables scalable, low-latency retrieval, making it feasible for large-scale applications such as search engines, recommendation systems, and question-answering platforms. This work opens pathways for multi-lingual, multi-modal, and long-context retrieval, pushing the frontier of efficient and adaptive information retrieval.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06389
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FastLane: Efficient Routed Systems for Late-Interaction Retrieval
Kumar, Ramnath
Jain, Prateek
Hsieh, Cho-Jui
Information Retrieval
Late-interaction retrieval models like ColBERT achieve superior accuracy by enabling token-level interactions, but their computational cost hinders scalability and integration with Approximate Nearest Neighbor Search (ANNS). We introduce FastLane, a novel retrieval framework that dynamically routes queries to their most informative representations, eliminating redundant token comparisons. FastLane employs a learnable routing mechanism optimized alongside the embedding model, leveraging self-attention and differentiable selection to maximize efficiency. Our approach reduces computational complexity by up to 30x while maintaining competitive retrieval performance. By bridging late-interaction models with ANNS, FastLane enables scalable, low-latency retrieval, making it feasible for large-scale applications such as search engines, recommendation systems, and question-answering platforms. This work opens pathways for multi-lingual, multi-modal, and long-context retrieval, pushing the frontier of efficient and adaptive information retrieval.
title FastLane: Efficient Routed Systems for Late-Interaction Retrieval
topic Information Retrieval
url https://arxiv.org/abs/2601.06389