SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
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 enhanced prompt and its semantic partition. SCOPE pools shifts in policy log probabilities within each span to derive a shared coefficient for its token losses while retaining a single advantage for eac...
| Authors | Yufei Jiao, Jinfa Huang, Zeyue Xue et al. |
|---|---|
| Primary category | cs.CV |
| Published | 15 October 2026 |
| Last updated at source | 15 October 2026 |
Recent changes
- 16 Oct 2026 Description: 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 t → 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 t
- 16 Oct 2026 Topics added cs.CV removed hf-daily-papers, reinforcement learning, group relative policy optimization, grpo, text-to-image generation, semantic spans, policy log probabilities, prompt rewriting
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.