arXiv Machine Learning July 13, 2026 By Mingxiang Luo, Xinnan Mao, Lu Wang, Lei Bai, Feng Ding, Yuqiang Li

Active rejection enables reliable generalization of universal machine-learning interatomic potentials

Read the original on arXiv Machine Learning →

arXiv:2607. 09456v1 Announce Type: new Abstract: Universal machine learning interatomic potentials (uMLIPs) bridge quantum-mechanical accuracy and large-scale molecular dynamics, but the cost of high-accuracy calculations such as r$^2$SCAN limits training to datasets that remain small relative to the open materials space.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

benchmarks

arXiv Machine Learning

Jul 17

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

arXiv:2607. 14486v1 Announce Type: cross Abstract: Machine-learning force fields (MLFFs) are reliable only near their training distribution, making efficient construction of diverse training sets a major bottleneck for both train-from-scratch and foundation fine-tuning workflows.

By Sheng Bi, Yi-Ze Wang, Jun Cheng

fine-tuning

arXiv AI

Jun 2

From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures

arXiv:2602. 04861v2 Announce Type: replace-cross Abstract: Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to erroneous behavior in downstream simulations that standard energy and force regression evaluations can miss.

By Ryan Liu, Eric Qu, Tobias Kreiman, Samuel M. Blau, Aditi S. Krishnapriyan

llms benchmarks

arXiv Machine Learning

Jun 10

Gradient-Guided Furthest Point Sampling for Robust Training Set Selection

arXiv:2510. 08906v2 Announce Type: replace-cross Abstract: Training set sampling methods are used to improve model performance and lower data costs in machine learning problems relevant to chemistry.

By Morris Trestman, Stefan Gugler, Felix A. Faber, O. A. von Lilienfeld

arXiv AI

Jun 15

A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Prediction

arXiv:2606. 14498v1 Announce Type: cross Abstract: Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels, and electronic-structure observables that energy-only surrogates cannot resolve.

By Yunhong Lou, Xihang Yue, Xinran Wei, Tianqi Deng, Linchao Zhu

fine-tuning benchmarks

arXiv AI

Aug 3

Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations

arXiv:2607. 29158v1 Announce Type: cross Abstract: We introduce implicit machine learning force fields (I-MLFFs), which replace explicit stacks of neural network layers with self-consistent fixed-point equations.

By Johannes Mae{\ss}, Leon Werner, J. Thorben Frank, Winfried Ripken, Martin Michajlow, Joshua Futterer, Klaus-Robert M\"uller, Stefan Chmiela

efficiency

arXiv Machine Learning

Jun 19

Evaluating Universal Machine Learning Force Fields Against Experimental Measurements

arXiv:2508. 05762v2 Announce Type: replace-cross Abstract: Universal machine learning force fields (UMLFFs) promise to revolutionize materials science by enabling rapid atomistic simulations across the periodic table.

By Sajid Mannan, Vaibhav Bihani, Carmelo Gonzales, Kin Long Kelvin Lee, Nitya Nand Gosvami, Sayan Ranu, Santiago Miret, N M Anoop Krishnan

benchmarks

Related stories

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

From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures

Gradient-Guided Furthest Point Sampling for Robust Training Set Selection

A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Prediction

Implicit Machine Learning Force Fields Accelerate Molecular Dynamics Simulations

Evaluating Universal Machine Learning Force Fields Against Experimental Measurements