ModelRefs / State Space Model (SSM) — AI Glossary
State Space Model (SSM) — AI Glossary
A sequence model based on linear recurrence rather than attention, offering linear-time inference at long context lengths.
Overview
SSMs (S4, Mamba, RWKV) model sequences via a hidden state updated each step, avoiding the quadratic cost of attention. At inference time the hidden state serves as a fixed-size memory, enabling O(n) generation. Mamba adds selective state expansion; Mamba-2 and Jamba blend SSM with attention layers.
Reference details
| Topic | architecture |
|---|---|
| Also known as | SSM, linear recurrence model |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to State Space Model (SSM) — AI Glossary.
Frequently asked questions
What is State Space Model (SSM)?
A sequence model based on linear recurrence rather than attention, offering linear-time inference at long context lengths.
Is State Space Model (SSM) the same as SSM?
Yes — SSM, linear recurrence model are common aliases for State Space Model (SSM).
What concepts are related to State Space Model (SSM)?
Closely related concepts include mamba, transformer, attention.