Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
Proceedings of the 2nd Efficient Systems for Foundation Models Workshop at the International Conference on Machine Learning (ICML) , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.