arXiv 2610.22264 · cs.CV · 2026-10-15
SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation
Yufei Jiao, Jinfa Huang, Zeyue Xue, Tianyu Xie, Yuexiao Ma, Rongrong Ji, Xiawu Zheng, Jiebo Luo
University of Rochester
在最新榜 #244 本站收录于 2026-10-21
一句话要点
SCOPE 基于 GRPO，按语义片段而非单个子词分配奖励，训练文生图提示词改写模型。
SCOPE, a GRPO-based objective, credits semantic spans rather than sub-word tokens when training prompt rewriters for text-to-image.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：强化学习
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation ▲218
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。