Tokenized autoregressive generation of incentive amounts with a lambda-conditioned policy and constraint-aware alignment (SCPO) reports higher revenue, higher ROI, and fewer ROI violations than six baselines on one industrial and one synthetic dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Generative Optimization for Incentivized Advertising with Global Level Constraints
Tokenized autoregressive generation of incentive amounts with a lambda-conditioned policy and constraint-aware alignment (SCPO) reports higher revenue, higher ROI, and fewer ROI violations than six baselines on one industrial and one synthetic dataset.