EBMol is the first energy-based model for 3D molecular generation to reach state-of-the-art performance on QM9 and GEOM-Drugs by learning a physically grounded energy landscape without explicit simulation during training.
Training products of experts by minimizing contrastive divergence.Neural computation, 14(8):1771–1800, 2002
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
citing papers explorer
-
Generating Physically Consistent Molecules with Energy-Based Models
EBMol is the first energy-based model for 3D molecular generation to reach state-of-the-art performance on QM9 and GEOM-Drugs by learning a physically grounded energy landscape without explicit simulation during training.
-
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.