Augmenting a neural energy-based model with a linear statistic term that encodes known data properties improves generation quality on molecules, digits, and point clouds.
Efficient learning of generativemodelsviafinite-differencescorematching
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Incorporating Inductive Biases to Energy-based Generative Models
Augmenting a neural energy-based model with a linear statistic term that encodes known data properties improves generation quality on molecules, digits, and point clouds.