Architecture researcher

Ofir Press

Introduced ALiBi attention biasing, enabling Transformers to extrapolate to longer sequences than trained on.

Works in the archive (2) · lead author on 1

“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

Noah A. Smith, Mike Lewis, John Yang, Carlos E. Jimenez, Karthik Narasimhan, Xingyao Wang, Graham Neubig

View co-author network (8 people)

Loading graph…