Generative Design of inorganic compounds using deep diffusion language models

Discovering novel synthesizable and stable materials is of fundamental importance to our society. However, chemical innovation is nontrivial. The material composition and structure must satisfy many stringent constraints such as charge neutrality, balanced electronegativity, synthesizability, geometric symmetry, and mechanical stability. Historically, new material discovery relies on expert heuristics and usually is based on the tinkering of existing materials. Several structure generation studies [1, 2] have used brute-force element substitution to generate new structures based on known prototypes. However, the limitation of this permutation-based approach is that it cannot generate new formula prototypes, it can only employ known formulas as templates, facilitating the generation of novel compositions solely through the substitution of elements. With the development of crystal structure prediction algorithms such as CSMPL [3], TCSP [4], and ParetoCSP [5], the generation of chemically stable compositions has emerged as an increasingly critical challenge. Stable compositions play a pivotal role in mitigating the computational demands associated with subsequent stages of analysis.