EQUATE fine-tunes a pre-trained symbolic regression transformer with symbolic-numeric alignment and evaluator-guided embedding search, outperforming its backbone and most baselines on Feynman, Strogatz, and black-box benchmarks.
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
-
Data-Efficient Symbolic Regression via Foundation Model Distillation
EQUATE fine-tunes a pre-trained symbolic regression transformer with symbolic-numeric alignment and evaluator-guided embedding search, outperforming its backbone and most baselines on Feynman, Strogatz, and black-box benchmarks.