SCOPE：文本生成中的语义约束信用优化

arXiv 2610.22264 · 23 人推荐 · 附代码 MAC-AutoML/SCOPE（1 stars）。Reinforcement learning (RL) enables language models to improve text-to-image (T2I) generation by rewriting prompts for a frozen image generator. Existing methods typically apply a single signal derived from the image to individual subword tokens, although objects, counts, attributes, and relations form coherent semantic spans. We propose SCOPE, an objective based on Group Relative Policy Optimization (GRPO) that aligns update weighting with this structure. The rewriter jointly generates an enhan