Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation

• 类型：arxiv
• 标识：2608.06751
• 链接：https://arxiv.org/abs/2608.06751
• 主分类：multimodal
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：Atelier, a shortcut-aware control-state planning framework for artist-grounded image generation, improves artist-level style fidelity, preserves source structure more faithfully, and substantially reduces shortcut substitution compared with prompt-engineered, retrieval-augmented, and general-purpose agent baselines.
• 待LLM分类：否
• 标题中文：Beyond Starry Night: Shortcut-Aware Control-State Planning for Artist-Grounded Text to Image Generation
• TLDR中文：Atelier 是一种面向艺术家风格图像生成的捷径感知控制状态规划框架，可提升艺术家级风格保真度，更忠实地保持源结构，并相较提示工程、检索增强与通用 agent 基线大幅减少捷径替换。
• 来源文件：
• /inbox/tom/_candidates/2026-08-12-agent-rag-longcontext-candidates.json
• [S2 enrich]