Target-property-guided material generation: towards on-demand inverse design of materials

In recent years, the application of machine learning in materials science has significantly accelerated the discovery of new materials. In particular, when combined with traditional methods such as first-principles calculations, machine learning models have proven effective in screening potential high-performance materials from existing databases. However, these approaches are largely constrained within known chemical spaces and struggle to enable the active design of entirely novel material structures. To overcome this limitation, generative models have emerged as a promising tool for inverse material design, offering new avenues to explore unknown structural and property spaces. Although existing generative models have achieved initial progress in crystal structure generation, achieving property-guided material generation remains a significant challenge. This review first introduces representative generative models recently applied to materials generation, including CDVAE, MatGAN, and MatterGen, and analyzes their fundamental capabilities and limitations in structural generation. We then focus on strategies for incorporating target properties into generative models to achieve property-directed structure generation. Specifically, we discuss four representative approaches: Con-CDVAE based on target property vectors, SCIGEN with integrated structural constraints and guidance mechanisms, a fine-tuned version of MatterGen leveraging adapter-based property control, and a CDVAE latent space optimization strategy guided by property objectives. Finally, we summarize the key challenges faced by property-guided generative models and provide an outlook on future research directions. This review aims to offer researchers a systematic reference and inspiration for advancing property-driven generative approaches in material design. This work aims to provide researchers with a systematic reference and insight into the advancement of property-driven generative methods for materials design.