notesum.ai

Published at October 21

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

cs.CV

cs.AI

Released Date: October 21, 2024

Authors: Hanseul Cho¹, Jaeyoung Cha¹, Srinadh Bhojanapalli², Chulhee Yun¹

Aff.: ¹Graduate School of AI, KAIST; ²Google Research

Arxiv: https://arxiv.org/abs/2410.15787v1