Learning ab initio phase-field models

arXiv:2610.01432 · cond-mat.stat-mech, cond-mat.mtrl-sci, cs.LG · Submitted 2026-10-01 · Read on arXiv

cond-mat.stat-mech, cond-mat.mtrl-sci, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/mengyi-chen/ab-initio-phase-field-models

Terminology

• Ab Initio — 1× in this paper · explained in 1 episode

Sources

• Equivariant learning of a transferable three-dimensional classical density functional
• Hypothesis-driven construction of mesoscopic dynamics
• A foundation model for atomistic materials chemistry
• Statistical-Physics-Informed Neural Networks (Stat-PINNs): A Machine Learning Strategy for Coarse-graining Dissipative Dynamics
• Interfacial-melt stability as a thermodynamic prerequisite for solid-state synthesis

Related papers

• Decoherence-controlled collective criticality in a two-dimensional quantum Stag Hunt
• Measurement-induced phase transitions in disordered fermions
• Quantum Thermalization beyond Non-Integrability and Quantum Scars in a Multispecies Bose-Josephson Junction
• Markov length can diverge in systems whose universal physics is spatially Markovian
• Protected domains and cooperative invasion on weighted networks
• Quantum many-body operator cascade as a route to chaos