{
  "annotation_id": "4e3e595c-acd5-4568-bdc0-3c6883ce8873",
  "date_created": "2026-02-17T05:53:08.562000Z",
  "date_modified": "2026-02-17T05:53:08.562000Z",
  "file_hash": "633cfb6626b3de03012fa5201a6fa3b815f309aee94c852e66acc8ad7e708f5d",
  "private": false,
  "record": {
    "abstract": "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.",
    "arxiv_id": "2601.06389",
    "authors": [
      "Ramnath Kumar",
      "Prateek Jain",
      "Cho-Jui Hsieh"
    ],
    "categories": [
      "cs.IR"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "FastLane: Efficient Routed Systems for Late-Interaction Retrieval",
    "url": "https://arxiv.org/abs/2601.06389",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "e739b80c-11cb-4444-9d27-7a7dc25ea323",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}