Google Releases RSLM: Training-Free Vector Quantization for ANN Search

_reachsumit · x · 2026-09-01

Google introduces RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1-4 bits per dimension for Approximate Nearest Neighbor (ANN) search. By encoding residual vectors and correcting L2 norms, RSLM reduces memory costs while matching the recall of trained quantizers across multiple benchmarks.

Original post →

More from Research

Research channel →