Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
2
6
Bypassing intractable force calculations entirely, score matching scales bottom-up coarse-graining to thousands of atoms per interaction site with a fraction of the standard training data.
Injecting curvature information into MLIP training via Hessian-vector products achieves the accuracy of full-Hessian training with >24x speedups, opening the door to more efficient and accurate potential energy surface learning.
Temperature-dependent coarse-grained models, notoriously hard to train, become far more transferable thanks to a new method that learns thermal response forces.