News > Generative AI aids scientists in solving complex physics problems

Generative AI aids scientists in solving complex physics problems

Researchers from MIT and the University of Basel have developed a machine-learning framework that can automatically map out phase diagrams for novel physical systems. This physics-informed approach is more efficient than manual techniques and does not require large, labelled training datasets. The framework could help scientists investigate the thermodynamic properties of novel materials or detect entanglement in quantum systems.