Recent advancements in artificial intelligence (AI)-based design strategies for metamaterials have revolutionized the creation of customizable architectures spanning nano- to macro-scale dimensions. However, their increasing complexity poses challenges in generating diverse metamaterials, hindering widespread adoption. Here, we introduce an innovative design strategy for three-dimensional graph metamaterials through simple arithmetic operations within the latent space. By leveraging carefully designed hidden representations of disentangled latent space and diffusion processes, our method unravels design space complexity, generating diverse graph metamaterials with comprehensive understanding. This versatile methodology facilitates the creation of graph metamaterials ranging from repetitive lattices to functionally graded materials. We believe that this methodology represents a foundational step in advancing our comprehension of the intricate latent design space, offering the potential to establish a unified model for various traditional generative models in the realm of graph metamaterials.

基于人工智能 (AI) 的超材料设计策略的最新进展彻底改变了从纳米到宏观尺寸的可定制架构的创建。然而，它们日益增加的复杂性给生成多样化的超材料带来了挑战，阻碍了广泛采用。在这里，我们通过潜在空间内的简单算术运算引入了三维图超材料的创新设计策略。通过利用精心设计的解开潜在空间和扩散过程的隐藏表示，我们的方法揭示了设计空间的复杂性，生成具有全面理解的多样化图形超材料。这种多功能的方法有助于创建从重复晶格到功能梯度材料的图形超材料。我们相信，这种方法代表了推进我们对复杂的潜在设计空间的理解的基础性一步，提供了为图超材料领域的各种传统生成模型建立统一模型的潜力。