MōLe-Λ: Learning the Coupled-Cluster Response State for Energies, Gradients, and Properties
Molecular Orbital Learning (MōLe) is an equivariant model that predicts coupled-cluster excitation amplitudes from Hartree-Fock molecular orbitals. We showed strong data efficiency and out-of-distribution generalization to larger molecules and off-equilibrium geometries. MōLe-Λ extends this to the full CCSD response state by jointly predicting right-hand T and left-hand Λ amplitudes. The model yields CC-quality energies and forces while recovering dipoles, polarizabilities, electron densities, and pair densities over two orders of magnitude faster than full CCSD.
