Archimedes Academic Fellow Andreas Lolos Presents Research at WACV 2026

Archimedes Academic Fellow and a third-year PhD student at the National and Kapodistrian University of Athens in Greece, Andreas Lolos recently travelled to Tucson in Arizona, USA, and presented the paper "SGPMIL: Sparse Gaussian Process Multiple Instance Learning" at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2026).

The paper is co-authored by Aris L. Moustakas and Maria Vakalopoulou, both Lead Researchers at the Archimedes Research Unit of the Athena Research Center, Greece. Aris L. Moustakas is a Professor at the Department of Physics, National and Kapodistrian University of Athens, Greece, and Maria Vakalopoulou is an Assistant Professor in applied mathematics at CentraleSupélec, University Paris-Saclay, France, where she leads the biomathematics group at MICS Laboratory. Additional co-authors are Jose Dolz, an Associate Professor in the Department of Software and IT Engineering at the ETS Montreal, Canada, and Stergios Christodoulidis, an Assistant Professor at CentraleSupélec, University Paris-Saclay, France, and a researcher at IHU PRISM, the French National Precision Medicine Center in Oncology, and a member of the biomathematics group of MICS Laboratory.

Archimedes Academic Fellow Andreas Lolos holds a bachelor's degree in physics from the Department of Physics of the National and Kapodistrian University of Athens (NKUA), Greece, with a specialization in nuclear and particle physics, and a master's degree in medical physics from NKUA's Department of Medicine, where he specialized in Magnetic Resonance Imaging (MRI). His work centres around developing probabilistic deep learning methods for biological and medical imaging, and focuses on uncertainty-aware models, adapter-based transfer learning for VLMs, and scalable Bayesian pipelines for weakly supervised whole slide image (WSI) analysis, including Gaussian-process multiple instance learning (MIL).

 

 

The paper presented can be found here: https://arxiv.org/pdf/2507.08711
A video presentation of the paper can be found here: https://youtu.be/b9N1Ikwpmwo