AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation

arXiv · AI, language, vision and robotics · article · Oct 14, 2026 · UTC

The scaling relationship of compute and performance for language models (LMs) has been extensively studied; more recently, models are being designed to scale memory use, as well. In particular, adding embeddings for n-grams scales memory separately from compute use, because each pass only processes individual embedding rows, which are much smaller than the storage used for the whole embedding table. However, existing methods train embeddings from scratch, which needs expensive GPU memory for fast reading and writing. Meanwhile, the ordinary memory of the host system is cheap and underutilized

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-15T15:42:31.647Z. This is not the publication date.