A Formal Framework for Understanding Length Generalization in Transformers

Open Webpage

Xinting Huang, Andy Yang, Satwik Bhattamishra, Yash Sarrof, Andreas Krebs, Hattie Zhou, Preetum Nakkiran, Michael Hahn

Published: 01 Jan 2025, Last Modified: 18 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0