cv

Undergraduate Researcher

The School of Electronics and Information, Hangzhou Dianzi University

Undergraduate Researcher

Intelligent Information Processing Laboratory, Hangzhou Dianzi University

VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing

Guanyuan Pan, Shuai Wang, Yugui Lin, Tiansheng Zhou, Pietro Liò, Zhenxin Zhao, Yaqi Wang

Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning, yet they inherently suffer from spatial blindness and logical hallucinations when interpreting densely structured engineering content, such as analog circuit schematics. To address these challenges, we propose a Vision Language Model-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing (VLM-CAD) designed for robust, step-by-step reasoning over multimodal evidence. VLM-CAD bridges the modality gap by integrating a neuro-symbolic structural parsing module, Image2Net, which transforms raw pixels into explicit topological graphs and structured JSON representations to anchor VLM interpretation in deterministic facts. To ensure the reliability required for engineering decisions, we further propose ExTuRBO, an Explainable Trust Region Bayesian Optimization method. ExTuRBO serves as an explainable grounding engine, employing agent-generated semantic seeds to warm-start local searches and utilizing Automatic Relevance Determination to provide quantified evidence for the VLM's decisions. Experimental results on two complex circuit benchmarks demonstrate that VLM-CAD significantly enhances spatial reasoning accuracy and maintains physics-based explainability. VLM-CAD consistently satisfies complex specification requirements while achieving low power consumption, with a total runtime under 66 minutes, marking a significant step toward robust, explainable multimodal reasoning in specialized technical domains.

Graph Neural Networks Based Analog Circuit Link Prediction

Guanyuan Pan, Tiansheng Zhou, Jianxiang Zhao, Zhi Li, Yugui Lin, Bingtao Ma, Yaqi Wang, Pietro Liò, Shuai Wang

Circuit link prediction, which identifies missing component connections from incomplete netlists, is crucial in analog circuit design automation. However, existing methods face three main challenges: 1) Insufficient use of topological patterns in circuit graphs reduces prediction accuracy; 2) Data scarcity due to the complexity of annotations hinders model generalization; 3) Limited adaptability to various netlist formats restricts model flexibility. We propose Graph Neural Networks Based Analog Circuit Link Prediction (GNN-ACLP), a graph neural networks (GNNs) based method featuring three innovations to tackle these challenges. First, we introduce the SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction) framework and achieve port-level accuracy in circuit link prediction. Second, we propose Netlist Babel Fish, a netlist format conversion tool that leverages retrieval-augmented generation (RAG) with a large language model (LLM) to enhance the compatibility of netlist formats. Finally, we build a comprehensive dataset, SpiceNetlist, comprising 775 annotated circuits of 7 different types across 10 component classes. Experiments demonstrate accuracy improvements of 16.08% on SpiceNetlist, 11.38% on Image2Net, and 16.01% on Masala-CHAI compared to the baseline in intra-dataset evaluation, while maintaining accuracy from 92.05% to 99.07% in cross-dataset evaluation, demonstrating robust feature transfer capabilities. However, its linear computational complexity makes processing large-scale netlists challenging and requires future addressing.

Edge-Deployable Dual-Arm Manipulation Algorithms

Lead a team to remove the SEM-GD text attention block, retaining the image self-attention block to enhance image features and reduce redundant parameters, thereby increasing the success rate in single-task scenarios. Prune the parameter of π₀.₅ from 3.3B to 991M. Employ an NVIDIA RTX4060 Laptop (with 8G of GRAM) to drive two PiPER robotic arms to complete five tasks. Collect and clean over 33,000 simulation data entries based on RoboTwin 2.0 for training and fine-tuning. Serve as the spokesperson of the team.

• Embodied Intelligence
• VLA Training/Deploying
• Simulated Robot Data Collecting/Cleaning

EV Battery Thermal Runaway Early Warning System

Collaborate with a team to apply ibm-granite/granite-timeseries-tspulse-r1 with sliding window + feature fusion to achieve early warning of thermal runaway in EV power batteries. Serve as the spokesperson of the team.

• Time-Series Forecasting
• Lithium-ion Battery Safety

National Second Prize, "AI+" Special Competition, The 19th "Challenge Cup" China Mobile National College Students Extracurricular Academic Science and Technology Works Competition

China Association for Science and Technology (CAST), Chinese Academy of Social Sciences (CASS) et al.

Sliver Prize, The 19th Zhejiang Provincial 'Challenge Cup' College Student Extracurricular Academic and Technological Works Competition

Zhejiang Academy of Social Sciences, Zhejiang Association for Science and Technology et al.

Honorable Mention, The Mathematical Contest in Modeling (MCM) and Interdisciplinary Contest in Modeling (ICM) 2025

The Consortium for Mathematics and its Applications (COMAP)

National Third Prize, Enterprise-Proposed Category of The 15th SOIEC (Students Service Outsourcing Innovation and Entrepreneurship Competition)

Ministry of Education, P.R. China, Ministry of Commerce, P.R. China et al.

Undergraduate

Hangzhou Dianzi University

Computer Science