Skip to content
Hugging Face Daily Papers·· 2026-10-15AI score18

SCOPE: Semantic boundary credit optimization for text-to-image prompt engineering

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

AI briefing

SCOPE is a GRPO-based reinforcement learning objective that lets a prompt rewriting model output semantic partitions while generating enhanced prompts, pools log-probability changes according to semantic spans, and shares loss coefficients for tokens within a span. On Qwen-Image, SD3, and FLUX.1-dev, SCOPE improves by an average of 9.48% on GeneVal and 7.62% on T2I-CompBench compared with the original GRPO, without additional span rewards or image rendering.

Open original arxiv.org