NF-BO is a latent Bayesian optimization framework that uses normalizing flows for a one-to-one input-latent mapping and token-level adaptive sampling, outperforming prior LBO methods on Guacamol and PMO benchmarks.
Each task’s performance is averaged over five trials
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
-
Latent Bayesian Optimization via Autoregressive Normalizing Flows
NF-BO is a latent Bayesian optimization framework that uses normalizing flows for a one-to-one input-latent mapping and token-level adaptive sampling, outperforming prior LBO methods on Guacamol and PMO benchmarks.