Felix Draxler
Forscher (Postdoktorand) at UC Irvine
Irvine, California, United States
Summary
👤
Senior🎓
Top SchoolFelix Draxler is a machine learning researcher and postdoctoral fellow at UC Irvine with eight years of experience bridging theoretical deep learning and practical generative modeling. He completed a PhD in Computer Science at Heidelberg after training in physics, and has published work on deep learning theory and invertible generative architectures. A hands-on engineer, Felix contributed core mathematical features to the FrEIA invertible-flow framework—implementing Jacobian calculations, shape handling, and coupling/block transforms—highlighting his focus on rigorous algorithmic correctness. He combines project leadership and clear scientific communication with a knack for turning abstract theory into reliable code, making him effective both in academia and open-source projects.
8 years of coding experience
Ludwig Maximilian University of MunichMaster, Physics, Master, Physics at Ruprecht-Karls-Universität HeidelbergPhD, Computer Science, PhD, Computer Science at Universität Heidelberg
Github Skills (6)
web-framework10
pytorch10
machine-learning10
python10
linear-algebra9
deep-learning9
Programming languages (4)
Github contributions (5)
vislearn/FrEIA
Feb 2020 - Jan 2023
Framework for Easily Invertible Architectures
Role in this project:
ML Engineer
ML EngineerContributions:18 reviews, 93 commits, 45 PRs in 2 years 11 months
Contributions summary:Felix primarily contributed to the framework's core functionality, focusing on invertible architectures. Their commits involved refining existing modules such as `GLOWCouplingBlock`, `FixedLinearTransform`, and `InvertibleModule`, implementing Jacobian calculations and ensuring consistency across different components. Furthermore, they addressed shape handling within the network and implemented features for distributions. This indicates a focus on the mathematical and algorithmic aspects of the framework.
architecturesopenflowframeworkdata-mesharchitecture
fdraxler/PyTorch-AutoNEB
Jun 2018 - Sep 2022
Contributions:58 commits, 28 pushes, 14 comments in 4 years 4 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.