BWhat changed
Combined recurrent fading memory with a local attention window and innovation-selected stored tokens, expressing a family of hybrid state-space modules that can retrieve selected information beyond the recent context.
Scientific scope
Combined recurrent fading memory with a local attention window and innovation-selected stored tokens, expressing a family of hybrid state-space modules that can retrieve selected information beyond the recent context. The framework's structural reductions do not guarantee optimal Solomonoff inference, lossless retention of every token or unlimited useful recall at fixed resources. Selection/storage/retrieval have costs; studied scale and length generalization are finite.
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 framework's structural reductions do not guarantee optimal Solomonoff inference, lossless retention of every token or unlimited useful recall at fixed resources. Selection/storage/retrieval have costs; studied scale and length generalization are finite.
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.
- B’MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
- B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory
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