works on
active learning 1machine learning force fields 1model fine-tuning 1molecular simulations 1uncertainty estimation 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

physics.chem-ph2026

Full-data accuracy with fewer labels for training and fine-tuning machine-learning force fields

Sheng Bi, Yi-Ze Wang, Jun Cheng

The paper introduces a cheap uncertainty estimator called last-layer-projection regression (LLPR) for active learning, enabling machine‑learning force fields to achieve full‑data a…