Artificial intelligence has analyzed data scattered across hundreds of research papers to discover new lead-free dielectric materials that maintain stable performance even at high temperatures. The study presents a new approach that could transform materials discovery from a trial-and-error process into a data-driven one.

- Developed a new multilayer interlayer dielectric — an "oxygen tunnel" — that resolves the long-standing trade-off between healing oxygen vacancies and preventing electrode oxidation in oxide vertical channel transistors, achieving world-class current density and stability

- Expected to accelerate the commercialization of next-generation compute-in-memory systems, enabling AI semiconductors process massive amounts of data faster while consuming less power

Hannah Meyer, Saket Navlakha, and colleagues have shown that a process very similar to the “generalization” that occurs in machine-learning models helps the body’s immune system learn to identify self-peptides. Their findings demonstrate how AI could aid in studies of health and disease while pointing to improved immunotherapies with a lower risk of autoimmune complications.