研究人员开发了一个名为Visual-SDPO的新型自我蒸馏策略优化框架，旨在改进代码生成的大型语言模型。该方法使用渲染输出（如图表或网页）的视觉反馈来指导模型。通过精确定位导致视觉缺陷的代码片段，该系统提高了模型生成视觉准确伪影的能力，在基准测试中表现优于现有方法10多个百分点。 AI
影响 增强了LLM在生成视觉准确代码方面的能力，可能改进数据可视化和Web开发工具。
排序理由 该集群包含两篇学术论文，详细介绍了一种通过视觉反馈和自我蒸馏改进LLM代码生成的新方法。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2606.10334v1 Announce Type: new Abstract: Code-generating large language models (LLMs) increasingly produce visual artifacts such as charts, web pages, and slides by writing programs that are executed by non-differentiable renderers, committing to code before observing the …
arXiv:2606.11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this improvement when the context is not present. The method …
Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this improvement when the context is not present. The method works by matching the model's output distributio…
Self-distillation effectiveness depends on structural alignment between feedback and solver reasoning, with step-aligned critique outperforming binary rewards and reference solutions by targeting specific reasoning failures.