Weighted State Souping for Efficient Long-Context Retrieval
Apple Machine Learning
This paper was accepted at the Workshop on Personalized, Aligned, Long-term
Memory for AI Systems (PALM) at NeurIPS 2026. State space models (SSMs)
combine fast inference and fixed state size with competitive language-modeling
performance. Recently, state souping has been proposed as a procedure whereby
an SSM independently encodes chunks of tokens like documents, tool
definitions, or memory records. The resulting state encodings may be cached
and recombined to cheaply construct a context for do