研究人员正在探索使用大型语言模型 (LLM) 进行神经架构搜索 (NAS) 的新颖方法。一种名为 SPARK 的方法旨在通过显式选择功能因素进行修改来改进 LLM 知识集成，从而减少意外的副作用并提高效率。另一种技术，Delta-Code Generation，专注于微调 LLM 以生成紧凑的代码差异，以改进现有架构而不是从头开始生成它们，从而显著减少代码冗余和计算成本。一项调查还根据效率、鲁棒性和持续学习对 NAS 方法进行了分类，并提出了一个名为 HERCULES 的框架来指导这些领域的未来研究。 AI
影响 新的 LLM 驱动的 NAS 技术有望实现更高效、更鲁棒的模型开发，从而可能加速 AI 系统的部署。
排序理由 多篇 arXiv 论文介绍了使用 LLM 进行神经架构搜索 (NAS) 的新方法和调查。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
arXiv:2605.04057v1 Announce Type: new Abstract: This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs under expensive evaluations. Large language models (LLMs) are a promising assista…
arXiv:2605.04103v1 Announce Type: new Abstract: Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transitions from static benchmarks to real-world deployment…
arXiv:2605.04903v1 Announce Type: new Abstract: Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose De…
Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code Generation, where fine-tuned LLMs gener…