Speaker
Description
Precision studies of hadron structure increasingly require the integration of heterogeneous information from experiments, theoretical calculations, and numerical simulations. This talk will present recent developments in AI-assisted inference frameworks for hadron structure studies, including applications of machine learning, simulation-based inference, and generative modeling to global QCD analyses and hadron imaging. Particular emphasis will be placed on methodologies that enable the extraction of multidimensional structure information while maintaining rigorous uncertainty quantification. Connections to lattice QCD, generalized parton distributions, and future Electron-Ion Collider measurements will be discussed, together with prospects for agentic and AI-enabled scientific workflows in nuclear physics.