From the 2 of 21 linked papers with an AI index.
21 papers
Rotational equivariance and locality in data-driven subgrid-scale closures
Ryley McConkey, Julia Balla, Elyssa Hofgard +2
The paper evaluates how enforcing rotational equivariance in data‑driven subgrid‑scale models for large‑eddy simulation impacts accuracy, parameter efficiency, and generalization,…
Learning Lattice Parameters from Powder X-Ray Diffraction Data Using Invariants
Elyssa Hofgard, Kyucheol Min, Nofit Segal +7
We present a machine learning (ML) method to determine unit cell parameters from powder X-Ray diffraction (XRD) data using a novel invariant lattice representation. In ML, the data…
Reconstructing local environments from concise atomistic representations
Jigyasa Nigam, Tuong Phung, Ameya Daigavane +2
Symmetry-based representations of local atomic structure, such as the power spectrum or bispectrum, are routinely used to characterize the structural diversity of datasets and as i…
Turbulence teaches equivariance to neural networks
Ryley McConkey, Julia Balla, Jeremiah Bailey +5
The paper investigates how the rotational symmetries of turbulent flows influence neural network learning, showing that models respecting these symmetries generalize better and tha…
PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
Teddy Koker, Abhijeet Gangan, Mit Kotak +2
Many materials properties depend on higher-order derivatives of the potential energy surface, yet machine learned interatomic potentials (MLIPs) trained with a standard loss on ene…
EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
Yi-Lun Liao, Alexander J. Hoffman, Sabrina C. Shen +3
As -equivariant graph neural networks mature as a core tool for 3D atomistic modeling, improving their efficiency, expressivity, and physical consistency has become a centra…