Search Results for author: David Ciprut

Found 2 papers, 2 papers with code

Date Published Github Stars

Memory-efficient Transformers via Top-k Attention

1 code implementation • EMNLP (sustainlp) 2021 • Ankit Gupta, Guy Dar, Shaya Goodman, David Ciprut, Jonathan Berant

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length.

56
Paper
Code

Memory-efficient Transformers via Top-$k$ Attention

1 code implementation • 13 Jun 2021 • Ankit Gupta, Guy Dar, Shaya Goodman, David Ciprut, Jonathan Berant

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length.

56
Paper
Code
Cannot find the paper you are looking for? You can Submit a new open access paper.
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy