arXiv 2610.18860 · cs.AI · 2026-10-13
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
Xin Gao, Yifan Yang, Xin Li, Pan Wang, Yan Li, Muzhao Tian, Mingxi Cheng, Bei Liu 等 16 人
Microsoft
在最新榜 #46 本站收录于 2026-10-21
一句话要点
AesCode 以同提示生成的图片做审美参考，用解耦的跨模态奖励训练模型写出更好看的幻灯片和海报代码。
AesCode uses a generated image as aesthetic guidance and decoupled cross-modal rewards to produce better-looking slides and posters as code.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：代码与软件工程
- CodeMidas: Scaling Agentic Coding RL Environments from Code Itself ▲138
- LEGO-Anything: Coding Agents for 3D Scene Reconstruction ▲129
- 3DCodeVerse: Exploring 3D Worlds as Code ▲117
- Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL ▲95
- Last Secure Code Benchmark: Is the Code You Vibe Secure? ▲76
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。