English(EN) Mesh-Native Physics-Informed Graph Surrogates for TCAD-in-the-Loop Design Space Exploration

新的GAT代理模型加速FinFET器件仿真

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-04 04:00

研究人员开发了一种新颖的物理信息图注意力网络（GAT）代理模型，该模型直接在TCAD网格上运行，以模拟FinFET器件的行为。该方法预测每个网格节点上的静电势和载流子准费米能级，将载流子传输物理嵌入训练目标中。该代理模型展示了尺寸泛化能力，允许在较小网格上训练的模型应用于更大、更复杂的器件几何结构。与Sentaurus Device相比，GAT代理模型实现了数量级更高的吞吐量，同时保持了高精度，从而能够对多鳍三栅FinFET进行高效的设计空间探索。 AI

影响能够对先进半导体器件实现更快、更高效的设计空间探索。

排序理由该集群包含一篇详细介绍用于科学仿真的新型机器学习模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍用于科学仿真的新型机器学习模型的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Leonid Popryho, Ayoub Sadeghi, Inna Partin-Vaisband · 2026-09-04 04:00

用于TCAD闭环设计空间探索的网格原生物理信息图代理模型

arXiv:2609.02988v1 Announce Type: new Abstract: High-fidelity TCAD simulation of drift-diffusion transport remains the workhorse of emerging FinFET device design, but it is computationally expensive, especially for 3D structures where runtime escalates steeply with mesh complexit…

本文如何被排名

报道来源 [1]

用于TCAD闭环设计空间探索的网格原生物理信息图代理模型

相关实体

相关话题