Fine-Tuning Unifies Foundational Machine-learned Interatomic Potential Architectures at ab initio Accuracy

Abstract

This work demonstrates that fine-tuning transforms foundational machine-learned interatomic potentials (MLIPs) to achieve consistent, near-ab initio accuracy across diverse architectures. Benchmarking five leading MLIP frameworks (MACE, GRACE, SevenNet, MatterSim, and ORB) across seven chemically diverse compounds reveals that fine-tuning universally enhances force predictions by factors of 5-15 and improves energy accuracy by 2-4 orders of magnitude. The investigated models span both equivariant and invariant, as well as conservative and non-conservative, architectures. While general-purpose foundation models are robust, they exhibit architecture-dependent deviations from ab initio reference data; fine-tuning eliminates these discrepancies, enabling quantitatively accurate predictions of atomistic and structural properties. Using datasets constructed from equidistantly sampled frames of short ab initio molecular dynamics trajectories, fine-tuning reduces force errors by an order of magnitude and harmonizes performance across all architectures. These findings establish fine-tuning as a universal route to achieving system-specific predictive accuracy while preserving the computational efficiency of MLIPs. To promote widespread adoption, we introduce the aMACEing Toolkit, which provides a unified and reproducible interface for fine-tuning workflows across multiple MLIP frameworks.

main article and supporting information

References in corpus (18)

• A foundation model for atomistic materials chemistry
• Scalable Parallel Algorithm for Graph Neural Network Interatomic Potentials in Molecular Dynamics Simulations
• A practical guide to machine learning interatomic potentials -- Status and future
• e3nn: Euclidean Neural Networks
• MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures
• Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models
• The Open Molecules 2025 (OMol25) Dataset, Evaluations, and Models
• Orb: A Fast, Scalable Neural Network Potential
• Orb-v3: atomistic simulation at scale
• Modelling complex proton transport phenomena -- Exploring the limits of fine-tuning and transferability of foundational machine-learned force fields
• Graph atomic cluster expansion for foundational machine learning interatomic potentials
• Acid Base Chemistry of Short Hydrogen Bonds: A Tale of Schrödinger's Cat in Glutamine-Derived Crystals
• Large-scale cooperative sulfur vacancy dynamics in two-dimensional MoS2 from machine learning interatomic potentials
• Fine-Tuning Universal Machine-Learned Interatomic Potentials: A Tutorial on Methods and Applications
• The CP2K Program Package Made Simple
• How simple can you go? An off-the-shelf transformer approach to molecular dynamics
• Statistics makes a difference: Machine learning adsorption dynamics of functionalized cyclooctine on Si(001) at DFT accuracy
• AiiDA-TrainsPot: Towards automated training of neural-network interatomic potentials