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

## TL;DR

Fine-tuning machine-learned interatomic potentials improves their accuracy to match ab initio methods across different architectures.

## Contribution

Fine-tuning is shown to universally enhance accuracy and harmonize performance across diverse MLIP frameworks.

## Key findings

- Fine-tuning improves force predictions by factors of 5-15 and energy accuracy by 2-4 orders of magnitude.
- Fine-tuning reduces force errors by an order of magnitude and harmonizes performance across MLIP architectures.
- The aMACEing Toolkit is introduced to provide a unified interface for fine-tuning workflows.

## 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; specialized
system-specific training (fine-tuning) eliminates these discrepancies,
enabling quantitatively accurate predictions of atomistic and structural
properties. Using datasets constructed from 2000 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.