Miltiadis Kofinas 💭

Miltiadis Kofinas

(he/him)

Postdoctoral researcher, AI for Climate

Climate Extremes Group, Vrije Universiteit Amsterdam

Professional Summary

My name is Miltiadis (Miltos) Kofinas and I am a Postdoctoral researcher in the Climate Extremes Group at the Vrije Universiteit Amsterdam, advised by Dim Coumou. My research focuses on the development of AI methods for climate science, and especially on foundation models for weather forecasting. My research interests include graph neural networks, neural fields, geometric deep learning, and parameter-space networks.

I completed my PhD in the Video & Image Sense Lab at the University of Amsterdam, supervised by Efstratios Gavves. My research initially focused on future spatio-temporal forecasting, with applications on forecasting for autonomous vehicles, and later switched focus to neural fields and parameter-space networks.

Prior to my PhD, I received a Diploma in Electrical and Computer Engineering from the Aristotle University of Thessaloniki. For my Diploma thesis, I researched the topic of Scene Graph Generation using Graph Neural Networks, supervised by Christos Diou and Anastasios Delopoulos. During my studies, I was a computer vision & machine learning engineer at P.A.N.D.O.R.A. Robotics.

Education

Postdoc in Artificial Intelligence for Climate

Vrije Universiteit Amsterdam

PhD in Computer Science (Artificial Intelligence), expected 2025

University of Amsterdam

Diploma (M.Sc. equivalent) in Electrical and Computer Engineering

Aristotle University of Thessaloniki

Interests

AI for Climate Graph Neural Networks Neural Fields Geometric Deep Learning Parameter-space Networks
📚 My Research 🖥️

I believe that climate change is one of the most urgent challenges of our time, and I am excited to use my expertise in AI to help address it.

My research focuses on the development of AI methods for climate science, and especially on foundation models for weather forecasting. My research interests include graph neural networks, neural fields, geometric deep learning, and parameter-space networks.

Please reach out to collaborate 😃

Featured Publications
From MLP to NeoMLP: Leveraging Self-Attention for Neural Fields featured image

From MLP to NeoMLP: Leveraging Self-Attention for Neural Fields

From MLP to NeoMLP: Leveraging Self-Attention for Neural Fields

avatar
Miltiadis Kofinas
Amortized Equation Discovery in Hybrid Dynamical Systems featured image

Amortized Equation Discovery in Hybrid Dynamical Systems

Amortized Equation Discovery in Hybrid Dynamical Systems

Yongtuo Liu
Graph Neural Networks for Learning Equivariant Representations of Neural Networks featured image

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

avatar
Miltiadis Kofinas*
How to Train Neural Field Representations: A Comprehensive Study and Benchmark featured image

How to Train Neural Field Representations: A Comprehensive Study and Benchmark

How to Train Neural Field Representations: A Comprehensive Study and Benchmark

Samuele Papa

Data Augmentations in Deep Weight Spaces

Data Augmentations in Deep Weight Spaces

Aviv Shamsian*
Posts
Visualizing Spherical Harmonics featured image

Visualizing Spherical Harmonics

Visualizations of spherical harmonics, glyph plots, Wigner D-matrices

avatar
Miltiadis Kofinas
Visualizing Circular Harmonics featured image

Visualizing Circular Harmonics

Visualizations of circular harmonics, including polar plots and animations

avatar
Miltiadis Kofinas
TikZ Is All You Need featured image

TikZ Is All You Need

TikZ tutorial

Roto-translation Equivariance and Local Coordinate Frames featured image

Roto-translation Equivariance and Local Coordinate Frames

Simple equivariant graph networks with local coordinate frames

avatar
Miltiadis Kofinas
Recent Talks

Learning on Graphs Conference Amsterdam Meetup

Invited talk at *Learning on Graphs Conference Amsterdam Meetup* on "**From MLP to NeoMLP: Leveraging Self-Attention for Neural Fields**"

Learning on Graphs Conference Amsterdam Meetup featured image

Learning on Graphs Conference Amsterdam Meetup

Invited talk at *Learning on Graphs Conference Amsterdam Meetup* on "**Neural Networks Are Graphs! Graph Neural Networks for Equivariant Processing of Neural Networks**"

Geometric Deep Learning Study Visit

Invited talk at *Geometric Deep Learning Study Visit* on "**Roto-translated Local Coordinate Frames For Interacting Dynamical Systems**"

Amsterdam Applied ML Meetup featured image

Amsterdam Applied ML Meetup

Invited talk at *Amsterdam Applied ML Meetup* on "**Roto-translated Local Coordinate Frames For Interacting Dynamical Systems**"

LoGaG: Learning on Graphs and Geometry Reading Group featured image

LoGaG: Learning on Graphs and Geometry Reading Group

Invited talk at *LoGaG: Learning on Graphs and Geometry Reading Group* on "**Roto-translated Local Coordinate Frames For Interacting Dynamical Systems**"