14 citations · 32 across the 7 of their papers we have counts for
4 papers · 1 filter
Int2Int: a framework for mathematics with transformers
François Charton
This paper documents Int2Int, an open source code base for using transformers on problems of mathematical research, with a focus on number theory and other problems involving integ…
Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory
Tianji Cai, Garrett W. Merz, François Charton +4
We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to th…
Learning the greatest common divisor: explaining transformer predictions
François Charton
The predictions of small transformers, trained to calculate the greatest common divisor (GCD) of two positive integers, can be fully characterized by looking at model inputs and ou…
Linear algebra with transformers
François Charton
Transformers can learn to perform numerical computations from examples only. I study nine problems of linear algebra, from basic matrix operations to eigenvalue decomposition and i…