Emilie Mathian had an amazing time at the 18th edition of the International Conference on Theory and Applications of Computer Vision in Lisbon, Portugal (Visapp 2023). The conference was an opportunity to learn about theoretical and applicative advances in computer vision and robotics from the best researchers in the field. Emilie presented her paper entitled « HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization, » which was selected for the best student paper award. Her paper is a pioneering research on unsupervised methods for medical images and provides an innovative solution for unsupervised anomaly detection. Our team was thrilled to participate for the first time in a theoretical conference on deep learning, and we’re grateful for the opportunity to meet and network with brilliant researchers.