CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence

This repository hosts the pre-trained model weights for CktGen and baseline models.

📚 For full documentation, installation, training, and evaluation instructions, please visit our GitHub repository.

---

📁 Available Models

Model	Description
CktGen	Specification-Conditioned Circuit Generator
Evaluator	Performance predictor (surrogate)
LDT	Latent Diffusion Transformer
CktGNN	Graph Neural Network
CVAEGAN	Conditional VAE-GAN
PACE	Parallel Convolution Encoder

---

🚀 Usage

For download and usage instructions, please see our GitHub repository.

---

📊 Directory Structure

├── cktgen/                         # Main CktGen models
│   ├── cktgen_cond_gen_*.pth       # Conditional generation
│   └── cktgen_recon_*.pth          # Reconstruction
├── evaluator/                      # Performance predictor
│   └── evaluator_*.pth
└── baselines/                      # Baseline models
    ├── cktgnn/
    ├── ldt/
    ├── pace/
    └── cvaegan/

---

📖 Citation

@article{hou2025cktgen,
  title = {CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence},
  journal = {Engineering},
  year = {2025},
  doi = {https://doi.org/10.1016/j.eng.2025.12.025},
  author = {Yuxuan Hou and Hehe Fan and Jianrong Zhang and Yue Zhang and Hua Chen and Min Zhou and Faxin Yu and Roger Zimmermann and Yi Yang},
}