Live page · Day archive

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

Read the original at HF Daily Papers

Summary

SCOPE improves text-to-image prompt engineering by aligning reinforcement learning updates with semantic spans, achieving average relative gains of 9.48% on GeneVal and 7.62% on T2I-CompBench.

Carried by: HF Daily Papers. First seen: .