# FoundaRF: A Physics-Informed Foundation Model Framework for Radio-Frequency Passive Components

DevFeed: [FoundaRF: A Physics-Informed Foundation Model Framework for Radio-Frequency Passive Components](<https://devfeed.tech/articles/foundarf-a-physics-informed-foundation-model-framework-for-radio-frequency-passive-components-124604.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09003>)

Author: Houbo He, Chris Han, Hyunsu Chae, Lei Xia, Qiang Zhou, Lawrence Liu, Sensen Li, David Z. Pan, Taiyun Chi

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [few-shot](<https://devfeed.tech/topics/few-shot.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [components](<https://devfeed.tech/tags/components.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [design](<https://devfeed.tech/tags/design.md>), [design-automation](<https://devfeed.tech/tags/design-automation.md>), [eess-sp](<https://devfeed.tech/tags/eess-sp.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [framework](<https://devfeed.tech/tags/framework.md>), [layout](<https://devfeed.tech/tags/layout.md>), [ml](<https://devfeed.tech/tags/ml.md>), [mmwave](<https://devfeed.tech/tags/mmwave.md>), [model](<https://devfeed.tech/tags/model.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [physics](<https://devfeed.tech/tags/physics.md>), [physics-informed](<https://devfeed.tech/tags/physics-informed.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [radio](<https://devfeed.tech/tags/radio.md>), [semiconductor-technologies](<https://devfeed.tech/tags/semiconductor-technologies.md>), [simulations](<https://devfeed.tech/tags/simulations.md>)

## AI overview

FoundaRF aims to improve RF/mmWave passive-component design by replacing task-specific surrogate models with a framework that transfers across layout structures and semiconductor technologies. It combines a self-supervised encoder, adaptive layout processing, and physics-aware decoders for few-shot transfer. In experiments across four semiconductor technologies, it generalized to unseen structures, with up to 3.3x lower prediction error than baselines and up to fourfold lower labeled-data requirements; the abstract also reports shorter design turnaround. These results are reported in the abstract, which does not provide experimental details.

## Source excerpt

arXiv:2611.09003v1 Announce Type: cross Abstract: Designing RF/mmWave passive components is a time-consuming process that relies heavily on expert knowledge and iterative EM simulations. Although recent ML surrogate models have shown great promise in accelerating passive design, they remain task-specific and lack generalization. This paper presents FoundaRF, a foundation model framework that unifies passive layout modeling across diverse layout structures and technologies. It combines a self-supervised encoder with adaptive layout processing and physics-aware decoders to enable few-shot transfer. Experiments across four semiconductor technologies show strong generalization to unseen structures, outperforming baselines with up to a 3.3x reduction in prediction error, reducing labeled-data requirements by up to fourfold, and substantially shortening design turnaround. FoundaRF establishes a scalable and data-efficient solution for RF/mmWave passive design automation.