SOURCE-LINKED INTELLIGENCE

Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage and query-time interaction costs make large-scale deployment expensive. Pooling document tokens before indexing offers a natural remedy, yet static pooling must decide which visual evidence to preserve before the query is known. We study an alternative: a heavily compressed hot-path index generates candidates, after which query-aware token budgeting operates on the original token sets of the shortlisted pages. We formulate this stage-two selection

Read original source ↗ Open in workspace

recordType

paper

region

Global