Diffusion Generative Models for Designing Efficient Singlet Fission Dimers.

Diffusion generative models, a class of machine learning techniques, have shown remarkable promise in materials science and chemistry by enabling the precise generation of complex molecular structures. In this article, we propose a novel application of diffusion generative models for stabilizing reactive molecular structures identified through quantum mechanical screening. Specifically, we focus on the design challenge presented by singlet fission (SF), a phenomenon crucial for advancing solar cell efficiency beyond theoretical limits. While theoretical chemistry has been successful in predicting intermolecular arrangements with enhanced SF coupling, the practical implementation of these configurations faces challenges due to discrepancies between favorable and stabilized structures. To address this gap, we introduce a three-step strategy combining quantum mechanical screening for identifying optimal molecular arrangements and diffusion generative models for predicting stabilizing linkers. Through a case study of cibalackrot dimers, a promising SF material, we demonstrate the efficacy of our approach in enhancing SF efficiency by stabilizing the desired molecular arrangements.