Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation

6 July 2022

Papers citing "Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation"

5 / 5 papers shown

Title
Learning to solve arithmetic problems with a virtual abacus Flavio Petruzzellis Ling-Hao Chen Alberto Testolin 19 1 0 17 Jan 2023
Logical Tasks for Measuring Extrapolation and Rule Comprehension Ippei Fujisawa Ryota Kanai ELM LRM 20 4 0 14 Nov 2022
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation Ofir Press Noah A. Smith M. Lewis 242 690 0 27 Aug 2021
PonderNet: Learning to Ponder Andrea Banino Jan Balaguer Charles Blundell PINN AIMat 92 80 0 12 Jul 2021
Neural Sequence-to-grid Module for Learning Symbolic Rules Segwang Kim Hyoungwook Nam Joonyoung Kim Kyomin Jung NAI 42 10 0 13 Jan 2021