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.
More from Research
- Opus-assisted open design: a $31k low-field head MRI sketched in hours — DreamFly_13 · 2026-10-18
- semiconductor.diy: open-source guides to make real chips in a garden shed — jwt0625 · 2026-10-18
- Work in progress: geometric structure of GPG projections as Markov chain coarsening — michaelchchoi · 2026-10-18
- Backprop-free pretraining gets 2.3x speedup as Noise method crushes Dust record on 8 GPUs — inductionheads · 2026-10-18
- q3dviewer: open-source Qt+OpenGL tool for painter-like point cloud editing — 4310sy · 2026-10-18
- Smarter Every Day's Destin to defend PhD dissertation on impact fusion — CatAstro_Piyush · 2026-10-18