Content
(29.01.) Sampling String Vacua Using Generative Models
Magdalena Larfors (Uppsala Universitet)
29.01.2026 at 16:15
In this talk, we discus the application of generative models to the construction of ISD flux vacua of type IIB string theory. Specifically, we focus on Bayesian Flow Networks and Transformers, two techniques with complementary properties. We find that both models demonstrate good performance, in particular on interpolation and conditional sampling. Some extrapolation capabilities are observed, which could be leveraged in future studies to generate flux vacua in less well explored settings. Time permitting, I will discuss the use of Reinforcement Learning in the string landscape, both in conjunction with generative models, and on its own.
A348