Skip to content
TL;DR
Keep per-token embeddings for both query and document and score via a sum of max-similarities. Much more expressive than a single-vector dual encoder while still fast enough to index.
BACKLOG · WORK IN PROGRESS

This paper is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.