Search papers, labs, and topics across Lattice.
3
0
5
0
Achieve high-resolution land cover mapping competitive with fully supervised methods, but with zero high-resolution training labels and a 10,000x reduction in trainable parameters.
Despite using fundamentally different machine learning architectures, PIP and PhysNet potentials yield remarkably consistent results for vibrational properties and tunneling dynamics, suggesting that both can reliably represent complex potential energy surfaces.
Monomer-based energy decomposition lets you build MLPs that are both accurate and substantially faster for energy and force evaluations in complex molecular systems.
