HKT is a multi-scale attention architecture that bounds computation at 1.31x standard attention, proves kernel and decomposition properties, and reports accuracy gains on ListOps, sequential CIFAR-10, and character-level IMDB.
Title resolution pending
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
-
Hierarchical Kernel Transformer: Multi-Scale Attention with an Information-Theoretic Approximation Analysis
HKT is a multi-scale attention architecture that bounds computation at 1.31x standard attention, proves kernel and decomposition properties, and reports accuracy gains on ListOps, sequential CIFAR-10, and character-level IMDB.