MXtalGFlow combines a canonical crystal parameterization with energy-based GFlowNet training to sample thermodynamic distributions of molecular crystals, recovering known polymorphs and predicting new competitive packing modes.
The classical equation of state of gaseous helium, neon and argon,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Distributional Framework for Generative Modeling of Molecular Crystals
MXtalGFlow combines a canonical crystal parameterization with energy-based GFlowNet training to sample thermodynamic distributions of molecular crystals, recovering known polymorphs and predicting new competitive packing modes.