Miltiadis (Miltos) Kofinas [he/him] is a Postdoctoral Researcher in the Climate Extremes Group at the Institute of Environmental Studies (IVM) of Vrije Universiteit Amsterdam. His research focuses on the development of AI methods for climate science, and especially on foundation models for weather forecasting. His research interests include graph neural networks, neural fields, geometric deep learning, and parameter-space networks.
Miltos is completing his PhD in the Video & Image Sense Lab at the University of Amsterdam, supervised by Efstratios Gavves. His research initially focused on future spatio-temporal forecasting, with applications on forecasting for autonomous vehicles, and later focused on neural fields and parameter-space networks. Prior to his PhD, he received a Diploma in Electrical and Computer Engineering from the Aristotle University of Thessaloniki. For his Diploma thesis, he researched the topic of Scene Graph Generation using Graph Neural Networks, supervised by Christos Diou and Anastasios Delopoulos. During his studies, he was a computer vision & machine learning engineer at P.A.N.D.O.R.A. Robotics.
Expertise
Graph Neural Networks, Neural Fields, Geometric Deep Learning, Parameter-space Networks, AI for Climate, Interacting Dynamical Systems, Equivariance & Symmetries, Temporal Dynamics, Deep Learning and Computer Vision.
Education
2018: Diploma (MSc equivalent) in Electrical and Computer Engineering, Aristotle University of Thessaloniki.
