76 → 9.2meV/atom energy RMSE after LoRA
The full story, figures and data will appear here when the paper is out.
Try the method now. Compare model predictions with reference labels in a parity plot (the demo compares two foundation models), then follow the LoRA fine-tuning recipe used for MoS₂ with N₂. Open the tutorial →
Next case study · Uncertainty-driven training data for interface potentials → · Back to Machine-learning potentials research
