Modern magnetic-memory technology requires all-electric control of perpendicular magnetization with low energy consumption. While spin–orbit torque (SOT) in heavy metal/ferromagnet (HM/FM) heterostructures1–5 holds promise for applications magnetic random access memory, until today, it has been limited to the in-plane direction. Such can switch only deterministically help additional symmetry br...

We train graph neural networks to perform field-level likelihood-free inference using galaxy catalogs from state-of-the-art hydrodynamic simulations of the CAMELS project. Our models are rotational, translational, and permutation invariant do not impose any cut on scale. From that only contain $3$D positions radial velocities $\sim 1, 000$ galaxies in tiny $(25~h^{-1}{\rm Mpc})^3$ volumes our c...