Speaker
Description
Nuclear and high-energy physics facilities, such as CERN, Jefferson Lab, RHIC, and the forthcoming EIC, are producing exabytes of data. This unprecedented amount of data promises to provide a better understanding of QCD in the nonperturbative regime. However, extracting the required information is an extremely challenging task, as there is no available QCD analytic solution to interpret data. Solving this challenge requires nuclear physics to develop and adopt methods from data science, AI/ML, applied mathematics, and large-scale computing and adapt them to this goal. The A(i)DAPT working group is deploying machine learning physics event generators (MLEGs) based on AI generative models to faithfully mimic distributions of final state particle momenta, unfold the detector-induced distortions, and gain new insight into non perturbative QCD. In this contribution, results obtained by the A(i)DAPT WG will be reported.
