AWhat changed
Connected structured state-space models and attention variants through semiseparable matrix representations, using this duality to design Mamba-2 computation.
Scientific scope
Connected structured state-space models and attention variants through semiseparable matrix representations, using this duality to design Mamba-2 computation. The connection concerns specified model families and structured representations, not an equivalence of all Transformers and state-space models. Reported layer speedups are implementation-dependent.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The connection concerns specified model families and structured representations, not an equivalence of all Transformers and state-space models. Reported layer speedups are implementation-dependent.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- State-spaces team: Mamba-2 and SSD implementation
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction