MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

arXiv:2609.15126 · cs.CL, cs.AI · Submitted 2026-09-14 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: Github: https://github.com/jojo23333/Mixutre-Of-Memory-Embedding

Code: https://github.com/jojo23333/Mixutre-Of-Memory-Embedding

License: http://creativecommons.org/licenses/by/4.0/

The gist: Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more recently, conditional memory: token-indexed embedding tables that augment the

Terminology

Abstract

Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more recently, conditional memory: token-indexed embedding tables that augment the backbone with cheap parametric lookups. Existing memory-embedding methods retrieve via a deterministic function of the surface form, which collapses different contextual senses of the same token (e.g., python the language vs. the animal) into a single fixed entry. We introduce Mixture of Memory Embeddings (MoME), a context-aware memory mechanism that replaces each token's single memory row with a mixture of M slots and uses a learned gate over the hidden state to choose which slots to read at each position. In controlled pretraining experiments across nanochat, Llama-3/MobileLLM, and Qwen3 backbones, MoME improves over Value Embedding, Bigram, and STEM baselines in iso-parameter and iso-training-FLOP settings, shows a more promising memory-size scaling trend at sub-billion scale, and remains efficient in training and inference. Qualitative routing analyses on polysemous tokens further suggest that the learned mixture exhibits a degree of semantic interpretability, dispatching the same surface token to distinct memory slots under different senses.

Sources

Related papers