Cubit replaces Transformer's attention with a closed-form Kernel Ridge Regression token mixer and reports larger gains as training sequence length increases.
On the robustness of kernel ridge regression using the cauchy loss function
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Cubit: Token Mixer with Kernel Ridge Regression
Cubit replaces Transformer's attention with a closed-form Kernel Ridge Regression token mixer and reports larger gains as training sequence length increases.