3 papers
cs.AI2026
PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation
Claire Schlesinger, Circe Hsu, Peter Schindler +1
Rapid identification of candidate materials with target properties has become a key task in materials science. Machine learning has emerged as an alternative to physics-based simul…
cond-mat.mtrl-sci2025
FIRE-GNN: Force-informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties
Circe Hsu, Claire Schlesinger, Karan Mudaliar +3
The work function and cleavage energy of a surface are critical properties that determine the viability of materials in electronic emission applications, semiconductor devices, and…
cs.LG2025
MatrixNet: Learning over symmetry groups using learned group representations
Lucas Laird, Circe Hsu, Asilata Bapat +1
Group theory has been used in machine learning to provide a theoretically grounded approach for incorporating known symmetry transformations in tasks from robotics to protein model…