English
Related papers

Related papers: Optimizing Cross-Domain Transfer for Universal Mac…

200 papers

Accurate potential energy surface (PES) descriptions are essential for atomistic simulations of materials. Universal machine learning interatomic potentials (UMLIPs)$^{1-3}$ offer a computationally efficient alternative to density…

Machine-learned interatomic potentials are revolutionising atomistic materials simulations by providing accurate and scalable predictions within the scope covered by the training data. However, generation of an accurate and robust training…

Materials Science · Physics 2025-07-30 Mariia Radova , Wojciech G. Stark , Connor S. Allen , Reinhard J. Maurer , Albert P. Bartók

Deep learning models tend to underperform in the presence of domain shifts. Domain transfer has recently emerged as a promising approach wherein images exhibiting a domain shift are transformed into other domains for augmentation or…

Image and Video Processing · Electrical Eng. & Systems 2022-10-27 Weinan Song , Gaurav Fotedar , Nima Tajbakhsh , Ziheng Zhou , Lei He , Xiaowei Ding

The quality of machine learning interatomic potentials (MLIPs) strongly depends on the quantity of training data as well as the quantum chemistry (QC) level of theory used. Datasets generated with high-fidelity QC methods are typically…

In recent years, significant progress has been made in the development of machine learning potentials (MLPs) for atomistic simulations with applications in many fields from chemistry to materials science. While most current MLPs are based…

Chemical Physics · Physics 2023-05-19 Tsz Wai Ko , Jonas A. Finkler , Stefan Goedecker , Jörg Behler

Universal Domain Adaptation (UniDA) seeks to transfer knowledge from a labeled source to an unlabeled target domain without assuming any relationship between their label sets, requiring models to classify known samples while rejecting…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Samuel Felipe dos Santos , Tiago Agostinho de Almeida , Jurandy Almeida

Once trained, machine-learned interatomic potentials (MLIPs) provide a fast and accurate way to study catalytic reaction pathways, but their performance strongly depends on the training set. Here, we compare nine MLIPs trained with…

Machine learning interatomic potentials (MLIPs) have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. In practice, MLIP-based molecular simulations often encounter the issue of…

Computational Physics · Physics 2025-04-17 Han Xu , Taoyong Cui , Chenyu Tang , Jinzhe Ma , Dongzhan Zhou , Yuqiang Li , Xiang Gao , Xingao Gong , Wanli Ouyang , Shufei Zhang , Mao Su

Molecular dynamics (MD) employing machine-learned interatomic potentials (MLIPs) serve as an efficient, urgently needed complement to ab initio molecular dynamics (aiMD). By training these potentials on data generated from ab initio…

Materials Science · Physics 2024-09-19 Kisung Kang , Thomas A. R. Purcell , Christian Carbogno , Matthias Scheffler

Understanding the behavior of light interstitial elements in multicomponent alloys remains challenging due to the complexity of local chemical environments and the high computational cost of first-principles calculations. Here we…

Materials Science · Physics 2026-03-10 Miroslav Lebeda , Jan Drahokoupil , Veronika Mazáčová , Petr Vlčák

We propose a novel approach for constructing training databases for Machine-Learned Interatomic Potential (MLIP) models, specifically designed to capture phase properties across a wide range of conditions. The framework is uniquely…

Materials Science · Physics 2025-12-03 Vincent G. Fletcher , Albert P. Bartók , Livia B. Pártay

We propose a data-driven approach for constructing machine-learning interatomic potentials (MLIPs) trained under a regularization with the aim of avoiding nonphysical heat flux. Specifically, we introduce a regularization term for the heat…

Computational Physics · Physics 2024-03-22 Kohei Shimamura , Koura Akihide , Fuyuki Shimojo

Machine-learned interatomic potentials (MILPs) are rapidly gaining interest for molecular modeling, as they provide a balance between quantum-mechanical level descriptions of atomic interactions and reasonable computational efficiency.…

Computational Physics · Physics 2024-08-30 Gustavo R. Pérez-Lemus , Yinan Xu , Yezhi Jin , Pablo F. Zubieta Rico , Juan J. de Pablo

A linear regression-based machine learned interatomic potential (MLIP) was developed for the silicon-carbon system. The MLIP was predominantly trained on structures discovered through a genetic algorithm, encompassing the entire…

Mesoscale and Nanoscale Physics · Physics 2024-03-26 Michael MacIsaac , Salil Bavdekar , Douglas Spearot , Ghatu Subhash

Machine learning interatomic potentials (MLIPs) have become increasingly effective at approximating quantum mechanical calculations at a fraction of the computational cost. However, lower errors on held out test sets do not always translate…

Computational Physics · Physics 2025-04-24 Xiang Fu , Brandon M. Wood , Luis Barroso-Luque , Daniel S. Levine , Meng Gao , Misko Dzamba , C. Lawrence Zitnick

Twisted layered van-der-Waals materials often exhibit unique electronic and optical properties absent in their non-twisted counterparts. Unfortunately, predicting such properties is hindered by the difficulty in determining the atomic…

Foundation models have been transformational in machine learning fields such as natural language processing and computer vision. Similar success in atomic property prediction has been limited due to the challenges of training effective…

Machine Learning · Computer Science 2024-05-07 Nima Shoghi , Adeesh Kolluru , John R. Kitchin , Zachary W. Ulissi , C. Lawrence Zitnick , Brandon M. Wood

Machine learning interatomic potentials (MLIPs) enable accurate atomistic modelling, but reliable uncertainty quantification (UQ) remains elusive. In this study, we investigate two UQ strategies, ensemble learning and D-optimality, within…

Materials Science · Physics 2025-08-06 Fei Shuang , Zixiong Wei , Kai Liu , Wei Gao , Poulumi Dey

Machine learning interatomic potentials (MLIPs) have become a workhorse of modern atomistic simulations, and recently published universal MLIPs, pre-trained on large datasets, have demonstrated remarkable accuracy and generalizability.…

Materials Science · Physics 2024-12-04 Juno Nam , Jiayu Peng , Rafael Gómez-Bombarelli

An adaptive physics-inspired model design strategy for machine-learning interatomic potentials (MLIPs) is proposed. This strategy relies on iterative reconfigurations of composite models from single-term models, followed by a unified…

Materials Science · Physics 2026-02-27 Weishi Wang , Mark K. Transtrum , Vincenzo Lordi , Vasily V. Bulatov , Amit Samanta