Preprint
Aug 2026
PolymerGPT: Multi-property Optimization with a Decoder-Based GPT Model for Generative Polymer Design
This paper proposes PolymerGPT, a decoder-based GPT model that incorporates up to 37 commonly used polymer properties into the generative process via learned conditioning prefixes, and supports a scaffold condition that specifies a desired scaffold for predicted structures.
C. Pyle, A. Gadari, C. A. Figg et al.
· 0 citations