Open access
Jan 2026
Multiobjective Fluorescent Molecule Design with a Data-Physics Dual-Driven Generative Framework
LUMOS combines neural networks with a fast time-dependent density functional theory calculation workflow to build a suite of complementary predictors spanning different trade-offs in speed, accuracy, and generalizability, enabling reliable property prediction across diverse scenarios.
Yan-Heng Li, Zhi-Chen Pu, Li-Jiang Yang et al.
· JACS Au · 0 citations