DiffER, an ensemble of categorical diffusion models with random-padding length prediction, achieves state-of-the-art top-1 accuracy among template-free retrosynthesis models on USPTO-50K.
Advances in Neural Information Processing Systems 34, 12454–12465 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
DiffER: Categorical Diffusion for Chemical Retrosynthesis
DiffER, an ensemble of categorical diffusion models with random-padding length prediction, achieves state-of-the-art top-1 accuracy among template-free retrosynthesis models on USPTO-50K.