Pith. sign in

International Conference on Machine Learning , year =

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

ACCEPT 1

representative citing papers

Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention

cs.LG · 2026-08-11 · accept · novelty 7.0

For Boolean Min-IP, a single normalized nonnegative kernel-attention head needs exponentially many features to solve all three-token sequences, even though rank one solves every sequence of length at most two and dense softmax uses m-dimensional scores.

citing papers explorer

Showing 1 of 1 citing paper.

  • Three Tokens Force Exponential Feature Rank in Nonnegative Kernel Attention cs.LG · 2026-08-11 · accept · none · ref 5

    For Boolean Min-IP, a single normalized nonnegative kernel-attention head needs exponentially many features to solve all three-token sequences, even though rank one solves every sequence of length at most two and dense softmax uses m-dimensional scores.