Selected work

Representative Papers

LLMs for Analog Circuit Design Continuum (ACDC)

Dec 09, 2025

This study systematically evaluates the human-AI collaboration suitability of large language models (LLMs) in analog and custom digital circuit design (ACDC), focusing on their reliability and robustness in domain-specific reasoning, adherence to physical constraints, and structured representation tasks. Through controlled comparative experiments, we assess models—including T5, GPT-2, Mistral-7B, and GPT-oss-20B—on multimodal circuit data: netlists, natural-language descriptions, and symbolic constraints. Results show that smaller models exhibit greater robustness on constrained subtasks, whereas larger models suffer from poor generalization and frequent violations of fundamental physical laws. We introduce, for the first time, an engineering-deployment-oriented reliability evaluation framework that identifies critical limitations—including data representation sensitivity and design inconsistency—under real-world ACDC conditions. This work establishes a methodological foundation and practical guidelines for AI-assisted, high-reliability circuit design.

0 citationsRead paper

Wireless Sensing of Temperature, Strain and Crack Growth in 3D-Printed Metal Structures via Magnetoelastic and Thermomagnetic Inclusions

Oct 09, 2025

To address the challenge of real-time, in-situ monitoring of strain, temperature, and crack propagation in additively manufactured metallic structures operating under harsh conditions—currently reliant on inefficient periodic disassembly—this study pioneers the co-integration of magnetostrictive and thermomagnetic functional materials within microtubes, embedded directly into the metal matrix during additive manufacturing. Leveraging electromagnetic coil impedance modulation and eddy-current non-destructive evaluation principles, the approach enables wireless, passive, multi-parameter sensing within the structural interior. The method detects plasticity onset and fatigue crack initiation/propagation thousands of cycles earlier than conventional techniques, enabling condition-based maintenance. Experimental validation demonstrates strain measurement accuracy of ±27 με (full-scale 600 με), temperature accuracy of ±0.75 °C (0–70 °C, 95% confidence level), significantly enhancing in-service structural health awareness and service-life prediction fidelity.

0 citationsRead paper

Recent publications

Latest Papers

LLMs for Analog Circuit Design Continuum (ACDC)

Dec 09, 2025

This study systematically evaluates the human-AI collaboration suitability of large language models (LLMs) in analog and custom digital circuit design (ACDC), focusing on their reliability and robustness in domain-specific reasoning, adherence to physical constraints, and structured representation tasks. Through controlled comparative experiments, we assess models—including T5, GPT-2, Mistral-7B, and GPT-oss-20B—on multimodal circuit data: netlists, natural-language descriptions, and symbolic constraints. Results show that smaller models exhibit greater robustness on constrained subtasks, whereas larger models suffer from poor generalization and frequent violations of fundamental physical laws. We introduce, for the first time, an engineering-deployment-oriented reliability evaluation framework that identifies critical limitations—including data representation sensitivity and design inconsistency—under real-world ACDC conditions. This work establishes a methodological foundation and practical guidelines for AI-assisted, high-reliability circuit design.

0 citationsRead paper

Wireless Sensing of Temperature, Strain and Crack Growth in 3D-Printed Metal Structures via Magnetoelastic and Thermomagnetic Inclusions

Oct 09, 2025

To address the challenge of real-time, in-situ monitoring of strain, temperature, and crack propagation in additively manufactured metallic structures operating under harsh conditions—currently reliant on inefficient periodic disassembly—this study pioneers the co-integration of magnetostrictive and thermomagnetic functional materials within microtubes, embedded directly into the metal matrix during additive manufacturing. Leveraging electromagnetic coil impedance modulation and eddy-current non-destructive evaluation principles, the approach enables wireless, passive, multi-parameter sensing within the structural interior. The method detects plasticity onset and fatigue crack initiation/propagation thousands of cycles earlier than conventional techniques, enabling condition-based maintenance. Experimental validation demonstrates strain measurement accuracy of ±27 με (full-scale 600 με), temperature accuracy of ±0.75 °C (0–70 °C, 95% confidence level), significantly enhancing in-service structural health awareness and service-life prediction fidelity.

0 citationsRead paper