188 citations · 215 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers
Yoshihiro Yamada
Transformers have driven remarkable breakthroughs in natural language processing and computer vision, yet their standard attention mechanism still imposes O(N^2) complexity, hinder…
cs.LG2021★ 7 cited
Joint Search of Data Augmentation Policies and Network Architectures
Taiga Kashima, Yoshihiro Yamada, Shunta Saito
The common pipeline of training deep neural networks consists of several building blocks such as data augmentation and network architecture selection. AutoML is a research field th…