Tag: retrieval
All the articles with the tag "retrieval".
-
Low-Dimensional Representations: Projection, MRL, and Sparse Representations
In large-scale retrieval systems, embedding cost comes from model inference, vector storage, memory bandwidth, and KNN search. This post compares projection, MRL, and CSR-style sparse representations.
-
Think Before You Embed
Production search systems rewrite queries with LLMs before embedding them. Two ICLR 2026 papers ask what happens when elaboration and embedding share a model and a gradient.