Heidelberg University Sites logo

Andreas Hermansen

PhD Student

University of Geneva

andreas.hermansen@unige.ch

Andreas Hermansen

Introduction

My research:

  • Foundation models for High Energy Physics

  • Applications of Diffusion Models & Flows

  • Former (IceCube reconstrcutions/GraphNeT)

My expertise is:

ML: GNNs, Transformers

I’ve got my eyes on:

  • Foundation Models and Consistency models

  • Incorporating physical knowledge into models 

I want to know more about:

Connections between physics and AI

Projects

Denoising diffusion probabilistic models

Develop novel methods of inverse problem solutions based on denoising diffusion probabilistic models; investigate new approaches to uncertainty estimation based on stochasticity of denoising diffusion models; introduce new techniques of conditional generation based on concatenation, cross-attention and bias.