Architecture researcher

Łukasz Kaiser

ORCID lookup ↗DBLP lookup ↗Scholar lookup ↗Semantic Scholar ↗arXiv ↗

Worked on linearized / efficient attention variants that reduce the Transformer's quadratic cost for long sequences.

Works in the archive (1)

Linearized Attention (Reformer/Performer/Linear Transformers) · 2020

“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.

Co-authors in the archive

Nikita Kitaev, Krzysztof Choromanski, Adrian Weller, Angelos Katharopoulos, François Fleuret

View co-author network (6 people)

Loading graph…