A masked discrete diffusion model trained with token-wise GRPO and a long short-term risk-seeking replay pool improves symbolic regression solution rates and expression simplicity on SRBench.
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
-
Diffusion-Based Symbolic Regression
A masked discrete diffusion model trained with token-wise GRPO and a long short-term risk-seeking replay pool improves symbolic regression solution rates and expression simplicity on SRBench.