Anomalyspy: A Generative Defect Localization in Semiconductor Packages, with X-Ray Microscopy

Riko I Made, Pablo Quijano Velasco, Chee Koon Ng, Leong Chang Jie, Pawan Kumar

Submission Type: I want my submission to be considered for both oral and poster presentation.

Keywords: artificial intelligence, machine learning, failure analysis, generative models, defet localization, materials, microelectronics, 3D integrated circuits, variational auto encoder, quantized

TL;DR: This paper present Anomalyspy, a VQ-VAE–based framework for detecting and localizing defects in semiconductor packaging from X-ray microscopy data, enabling scalable and reliable failure analysis even when trained on minimally defective samples

Confirmation Of Submission Requirements: I submit a previously published paper. It was published in an archival peer–reviewed venue on or after September 1st 2025, I specify the DOI in the field below, and I submit the camera-ready version of the paper.

DOI: https://doi.org/10.1109/EPTC67330.2025.11392584

Submission Number: 332