Speaker
Description
Extracting transverse-momentum-dependent parton distributions (TMDs) from experiment is an inverse problem. We present a generative adversarial network (GAN) framework that solves this inverse problem at the event level, without assuming a functional form for the TMD. The GAN generator produces the TMD as an image and is trained against reference events through a discriminator, using a fully differentiable physics pipeline such that TMD is learned end to end from events alone. In closure tests with the fragmentation function held fixed, the generator successfully recovers the ground-truth TMD image and reproduces the event distributions. Building on this validation, we are extending the framework to real experimental data, which opens a path toward AI-driven hadron imaging at the EIC.