A fine-tuned language model on grammar derivation strings predicts architecture accuracy across datasets and improves evolutionary NAS search in the expressive einspace space.
Title resolution pending
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
-
Transferrable Surrogates in Expressive Neural Architecture Search Spaces
A fine-tuned language model on grammar derivation strings predicts architecture accuracy across datasets and improves evolutionary NAS search in the expressive einspace space.