Normalizing-flow kernels generate coarse-grained forces from configuration-only data, reducing local distortions found with Gaussian noise kernels while preserving global conformational accuracy.
These model-derived forces can then be used to train any MLCG force matching framework, such as CGSchNet, en- tirely without requiring atomistic force labels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.chem-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Operator Forces For Coarse-Grained Molecular Dynamics
Normalizing-flow kernels generate coarse-grained forces from configuration-only data, reducing local distortions found with Gaussian noise kernels while preserving global conformational accuracy.