SOURCE-LINKED INTELLIGENCE

EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory

arXiv · AI, language, vision and robotics · article · Oct 7, 2026 · UTC

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture has demonstrated the potential to decouple factual knowledge storage from general-purpose computation, offering a promising route to updating factual knowledge while keeping the Transformer backbone fixed. Realizing this potential is challenging because different expressions of a fact may activate different n-gram embeddings, while updating shared embeddings c

Read original source ↗ Open in workspace

recordType

paper

region

Global