Autonomous materials discovery with desired properties is one of the ultimate goals for materials science, and the current studies have been focusing mostly on high-throughput screening based on density functional theory calculations and forward modeling of physical properties using machine learning. Applying the deep learning techniques, we have developed a generative model, which can predict distinct stable crystal structures by optimizing the formation energy in the latent space. It is demonstrated that the optimization of physical properties can be integrated into the generative model as on-top screening or backward propagator, both with their own advantages. Applying the generative models on the binary Bi-Se system reveals that distinct crystal structures can be obtained covering the whole composition range, and the phases on the convex hull can be reproduced after the generated structures are fully relaxed to the equilibrium. The method can be extended to multicomponent systems for multi-objective optimization, which paves the way to achieve the inverse design of materials with optimal properties.

Magnetic materials have a plethora of applications from information technologies to energy harvesting. However, their functionalities are often limited by the magnetic ordering temperature. In this work, we performed random forest on the magnetic ground state and the Curie temperature (T_C) to classify ferromagnetic and antiferromagnetic compounds and to predict the T_C of the ferromagnets. The resulting accuracy is about 87% for classification and 91% for regression. When the trained model is applied to magnetic intermetallic materials in Materials Project, the accuracy is comparable. Our work paves the way to accelerate the discovery of new magnetic compounds for technological applications. GRAPHICAL ABSTRACT

Artificial intelligence (AI) technology has made remarkable progress in polymer materials, which has changed polymer science significantly. However, this community still relies heavily on the traditional research paradigm instead of the data-driven paradigm. This review advocates for a fundamental paradigm shift in polymer research from traditional experience-driven methods to data-driven approaches enabled by AI. While AI has made transformative advances in polymer design, property prediction, and process optimization, the field remains anchored in conventional methodologies. AI’s computational advantages against persistent barriers are also evaluated, such as data scarcity, inadequate material descriptors, and algorithmic complexity. Potential solutions, including collaborative data platforms, domain-adapted descriptor frameworks, and active learning strategies, are also discussed. Furthermore, we demonstrate how high-quality data and explainable AI methodologies overcome computational limitations while ensuring result credibility in other areas, which can benefit polymer research. Ultimately, this work provides a roadmap for accelerating the sustainable convergence of data-driven AI innovation with polymer science.