← Back to all news
arXiv Machine Learning

End-to-End Neural Modeling of EM Response and Design Performance for Free-Form RFIC Passives

The paper presents an end-to-end neural framework that predicts electromagnetic (EM) response and design performance for free-form RFIC passive matching networks across varying frequencies and circuit contexts. It combines a frequency-conditioned neural simulator with a circuit-conditioned neural solver, outputting both explicit EM response and a complementary response to capture orthogonal information. The 21‑million‑parameter model, trained on a large dataset of expert‑designed and random passive layouts, achieves $R^2>0.98$ for most targets and is orders of magnitude faster than traditional EM simulation.

Related stories

arXiv Machine Learning
Sep 22

TARGet: Topology-Aware Fusion-based Radio Frequency Circuit Functional Modeling using Graph Neural Networks

TARGet is an open‑source, topology‑aware machine‑learning framework for modeling RF circuits. It uses S‑parameter representations of sub‑circuits and a fusion architecture that combines Graph Neural Networks with sub‑circuit connectivity‑aware networks, enabling learning across multiple topologies. Experiments show TARGet achieves sub‑1% prediction error, reduces training data needs by up to 35.5×, and improves accuracy by 9.7× over state‑of‑the‑art models, with zero‑shot transfer to unseen sub‑circuit topologies.

By Soroosh Noorzad, Sebastian Bodero, Morteza Fayazi
benchmarks
More like this →
arXiv Machine Learning
Sep 22

K-TRAIL: Simulator-Guided Generative Design of EM/RF Circuits

K-TRAIL is a simulator-guided generative framework that uses diffusion-based layout generation combined with derivative-free ensemble Kalman guidance to design RF and electromagnetic circuits. It allows a black-box EM simulator to refine candidate layouts during generation, supporting synthesis from target S-parameter responses or direct RF performance constraints. Experiments on multi-layer RFIC structures demonstrate improved agreement with target responses and the ability to discover structurally distinct layouts that meet design requirements.

By Piyush Saha, Evan Newell, Hanna O'Leary, Arun Natarajan, Alireza Aghasi
diffusion
More like this →
arXiv Machine Learning
Jul 16

RF-Informed Graph Neural Networks for Accurate and Data-Efficient Circuit Performance Prediction

arXiv:2508. 16403v3 Announce Type: replace Abstract: Accurately predicting the performance of active radio frequency (RF) circuits is essential for modern wireless systems but remains challenging due to highly nonlinear behavior and the high computational cost of traditional simulation tools.

By Anahita Asadi, Leonid Popryho, Inna Partin-Vaisband
multimodalbenchmarks
More like this →
arXiv Machine Learning
Sep 10

Deep Learning to Automate Parameter Extraction and Model Fitting of Two-Dimensional Transistors

arXiv:2507.05134v2 Announce Type: replace Abstract: We present a deep learning approach to extract physical parameters (e.g., mobility, Schottky contact barrier height, defect profiles) of two-dimens...

By Robert K. A. Bennett, Jan-Lucas Uslu, Harmon F. Gault, Asir Intisar Khan, Lauren Hoang, Tara Pe\~na, Kathryn Neilson, Young Suh Song, Zhepeng Zhang, Andrew J. Mannix, Eric Pop
More like this →
arXiv AI
Jul 14

Physics-Informed Structure Anchoring With Capture-Aware Prototype Calibration for Cross-Environment RF Fingerprinting

arXiv:2607. 09760v1 Announce Type: cross Abstract: Radio frequency fingerprint identification (RFFI) uses transmitter-specific hardware imperfections as a physicallayer identity cue for Internet of Things (IoT) devices, but deep RFFI models often degrade when the acquisition environment changes.

By Fengchong Yao, Jianbing Li, Qing Liu, Qikun Liu, Kefeng Song, Haitao Li, Song Wang
ragbenchmarks
More like this →
arXiv AI
Aug 20

Physics-Unrolled Neural Operator for Wireless Field Modeling

The paper introduces Physics-Unrolled Hybrid Neural Operator (PU‑HNO), a three‑stage cascade that transforms low‑fidelity ray‑tracing outputs and scene priors into high‑fidelity indoor radio maps by sequentially modeling reflection, diffraction, and scattering. It demonstrates that, under conditionally unbiased label noise, the model can learn stable propagation structures and surpass its own training labels. Experiments on varied floorplans show PU‑HNO outperforming image‑to‑image baselines, wireless learning models, and monolithic neural operators in both image quality and wireless deployment metrics.

By Rafid Umayer Murshed, Saif Ur Rahman, Mingyue Tang, Elahe Soltanaghai
More like this →