BWhat changed
Stored a larger sparse model in flash and selected prompt-dependent expert subsets into DRAM, combining always-active shared weights, periodic expert reselection and task-dependent active capacity for on-device multimodal inference.
Scientific scope
Stored a larger sparse model in flash and selected prompt-dependent expert subsets into DRAM, combining always-active shared weights, periodic expert reselection and task-dependent active capacity for on-device multimodal inference. IFPruning is an earlier Apple research method, not invented by this product family. Account describes family collaboration with Google but does not resolve per-method/person roles. Acquired delta is flash/DRAM prompt-routing and elasticity integration, not a model-size or privacy guarantee. September policy update is not backdated to June.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. IFPruning is an earlier Apple research method, not invented by this product family. Account describes family collaboration with Google but does not resolve per-method/person roles. Acquired delta is flash/DRAM prompt-routing and elasticity integration, not a model-size or privacy guarantee. September policy update is not backdated to June.
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.
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