Uni-Macro-FRPN: Full-Resolution and Cross-Scale Learning for Polymers

This paper introduces Uni-Macro-FRPN, a Full-Resolution Polymer Network designed to address the trade-off between detailed monomer chemistry and computational efficiency in polymer modeling. The approach retains both atom-level structural details and explicit polymer graph connectivity, enabling accurate property predictions for long-chain polymers containing tens of thousands of atoms. This work contributes to the materials science domain by providing a scalable ML framework for polymer property prediction and material discovery applications.