Towards universal property prediction in Cartesian space: TACE is all you need
This provides a foundational paradigm for universal atomistic machine learning models that unify scalar and tensorial modeling, addressing limitations of spherical-harmonic-based methods in materials science and chemistry.
The paper tackles the problem of predicting arbitrary tensorial properties in atomistic simulations by introducing TACE, a unified Cartesian-space framework that achieves accuracy, stability, and efficiency on par with or surpassing leading equivariant frameworks across diverse benchmarks including molecules, materials, and complex systems.
Machine learning has revolutionized atomistic simulations and materials science, yet current approaches often depend on spherical-harmonic representations. Here we introduce the Tensor Atomic Cluster Expansion and Tensor Moment Potential, the first unified framework formulated entirely in Cartesian space for the systematic prediction of arbitrary structure-determined tensorial properties. TACE achieves this by decomposing atomic environments into a complete hierarchy of (irreducible) Cartesian tensors, ensuring symmetry-consistent representations that naturally encode invariance and equivariance constraints. Beyond geometry, TACE incorporates universal embeddings that flexibly integrate diverse attributes including basis sets, charges, magnetic moments and field perturbations. This allows explicit control over external invariants and equivariants in the prediction process. Long-range interactions are also accurately described through the Latent Ewald Summation module within the short-range approximation, providing a rigorous yet computationally efficient treatment of electrostatic interactions. We demonstrate that TACE attains accuracy, stability, and efficiency on par with or surpassing leading equivariant frameworks across finite molecules and extended materials, including in-domain and out-of-domain benchmarks, spectra, hessians, external-field response, charged systems, magnetic systems, multi-fidelity training, and heterogeneous catalytic systems. Crucially, TACE bridges scalar and tensorial modeling and establishes a Cartesian-space paradigm that unifies and extends beyond the design space of spherical-harmonic-based methods. This work lays the foundation for a new generation of universal atomistic machine learning models capable of systematically capturing the rich interplay of geometry, fields and material properties within a single coherent framework.