University of Wisconsin–Madison

Group News

Exploring Line Bundle Standard Models with Transformers

Our new paper appeared on the arXiv yesterday: https://arxiv.org/abs/2607.00078 where we developed an AI explorer to perform deep searches for string vacua with realistic particle physics spectra. The code and tools necessary to reproduce our findings are available at Github: https://github.com/alexmininno/LB-Explorer

AICY has gone live

AICY – an AI enabled Calabi-Yau repository has now gone live: https://aicy.physics.wisc.edu This is an effort to leverage AI to tackle the string theory landscape at scale.

Primordial non-Gaussianity — Fast simulations and persistent summary statistics

Check out our new paper: https://arxiv.org/abs/2512.09852 where we introduced the PNG-pmwd Suite —  a collection of 22,410 halo catalogs developed to support data-driven analyses of large-scale structure formation and the impact of primordial non-Gaussianity (PNG). Topological data analysis together with machine learning can unlock new ways to squeeze out early Universe signals beyond traditional n-point …