Story perspectives

THOR AI Revolutionizes Material Discovery, 400x Faster Insights

3/17/2026

Summary

Story summary

Researchers at The University of New Mexico and Los Alamos National Laboratory developed THOR AI.
THOR combines tensor network algorithms with machine learning to solve configurational integrals and PDEs.
The framework has been tested on various materials and is over 400 times faster than prior methods.
Duc Truong, lead author at The University of New Mexico and Los Alamos National Laboratory, states THOR enables faster discoveries and deeper insights.

1 of 1

Story summary

Researchers at The University of New Mexico and Los Alamos National Laboratory developed THOR AI.
THOR combines tensor network algorithms with machine learning to solve configurational integrals and PDEs.
The framework has been tested on various materials and is over 400 times faster than prior methods.
Duc Truong, lead author at The University of New Mexico and Los Alamos National Laboratory, states THOR enables faster discoveries and deeper insights.