most citedMasked Multi-Domain Network: Multi-Type and Multi-Scenario Conversion Rate Prediction with a Single Model

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Intrinsic Interaction Geometry Controls the Low-Rank Complexity of Softmax Attention

Yuhe Sui, Jianing Zhang, Yingzhi Tang

How much matrix rank is required to preserve every bounded value output of normalized softmax attention? We study the unrestricted maximum-row-\(\ell_1\) approximation rank \(r_\va…