Latent defect screening is challenged by extremely low failure rates, high-dimensional test data, and absence of labeled anomalies. We propose the first unsupervised anomaly detection framework incorporating a Diffusion Transformer. Raw test measurements are first compressed by an autoencoder, then reshaped into a structured token sequence enriched with sinusoidal and per-device wafer-position embeddings. Anomaly scores are derived from the noise-prediction error over mid-range diffusion timesteps, enabling fast wafer-scale screening without any labeled defects or manual feature engineering. Our approach achieves state-of-the-art performance on industrial 16nm IC test data under extreme class imbalance, offering interpretable failure localization through latent-space reconstruction residuals.
@article{arxiv.2605.26468,
title = {Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection},
author = {Yuxuan Yin and Chen He and Todd Jacobs and Jialei He and Boxun Xu and Robert Jin and Peng Li},
journal= {arXiv preprint arXiv:2605.26468},
year = {2026}
}