发表机构
DEIB; Politecnico di Milano（电子与信息生物医学工程系; 米兰理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出THEIA数据集与基准，利用微调视觉-语言模型分析模拟电路GDSII布局，在五个任务上比通用VLM提升高达73%。
AI 中文摘要
人工智能与计算机辅助设计框架的集成引发了模拟集成电路（IC）设计领域的范式转变，推动该领域从依赖人工和基于算法的解决方案转向采用自动化和智能化的范式。在此背景下，GDSII文件作为行业标准数据库，包含模拟电路最终且最准确的信息来源，封装了决定流片性能的复杂物理几何形状和寄生效应现实。本文提出了THEIA，一个包含数千张布局图像及其配对的问答对话的新颖数据集，并配套一个基准，该基准采用微调的视觉-语言模型（VLM）来分析模拟电路的GDSII文件，使设计者能够将物理布局作为直观、有意义的实体进行交互和查询。使用数千个模拟设计在五个实际任务上的实验结果表明，所提出的微调VLM显著优于最先进的通用VLM，性能提升高达73%，凸显了通用多模态推理与领域特定布局理解之间的根本差距。
英文摘要
The integration of artificial intelligence into computer-aided design frameworks has sparked a shift in the design of analog integrated circuits (ICs), transitioning the field from using manual and algorithmic-based solutions to adopting automated and intelligent paradigms. In this scenario, the GDSII file represents the industry-standard database containing the ultimate and most accurate source of information of the analog circuit, encapsulating the complex physical geometries and parasitic realities that define tape out performance. This paper proposes THEIA, a novel dataset containing thousands of layout images paired with question-answer conversations, along with a benchmark that employs a fine-tuned vision-language model (VLM) to analyze GDSII files of analog circuits, enabling designers to interact with and query physical layouts as intuitive, meaningful entities. Experimental results using thousands of analog designs across five realistic tasks demonstrate that the proposed fine-tuned VLM outperforms state-of-the-art general-purpose VLMs by a significant margin (up to 73%), highlighting a fundamental gap between general-purpose multimodal reasoning and domain-specific layout understanding.
Comments10 pages, 10 figures, 14 tables, to be published in NeurIPS 2026
