Mathematical Physics M.Sc. with a background in differential geometry, PDE theory and field theory, now working mainly on scientific software and machine learning. I am as comfortable with the maths as with the code: I have built differentiable physics simulators, graph generative models, and a discrete differential geometry library, most of it written from scratch in PyTorch. My recurring interest is how structured systems grow out of simple local rules.
Fabian Lander, Erik Löffelholz, Diaaeldin Taha, Steve Trettel, Anna Wienhard.
"Illustrating Hyperbolic Surfaces with Mesh Embeddings."
Submitted to the Bridges Conference 2026 (Regular Papers Track). Under Review.
Python · JavaScript · TypeScript · C++
PyTorch (Autograd, PINNs, GNNs) · Diffusion Models · VAEs · Neural ODEs
Numerical Integration (Runge-Kutta, Monte Carlo) · Differentiable Simulation · NumPy · SciPy
Functional analysis · PDE theory · variational methods · differential geometry · discrete differential geometry · group theory
Git · Docker · FastAPI · LaTeX · Agentic Coding Models · AI Data Labeling · RLHF / LLM Evaluation
German (native) · English (C1, full professional proficiency)
Dr. Diaaeldin Taha
Research Group Leader (Mathematical Structures in AI)
Max Planck Institute for Mathematics in the Sciences, Leipzig
taha@mis.mpg.de
Mesh Embeddings & Discrete Differential Geometry. GPU mesh embedding into hyperbolic and spherical spaces by spring-mass energy minimization, with a discrete differential geometry operator library (cotangent Laplacian, curvature, heat-method geodesics). Computational basis for the Bridges 2026 paper.
Graph ML Lab. GCN, GAT, graph VAE, discrete diffusion, and joint discrete-continuous diffusion over graph structure and 3D positions, all from scratch. PyTorch only, no external GNN libraries. github.com/erik2810/ml-projects
DiffQFT. Differentiable quantum field theory in Euclidean AdS₂: Witten-diagram integration, neural surrogates, and a PINN solver for the Klein-Gordon equation. github.com/erik2810/DiffQFT
Differentiable Physics Engine. A neural ODE that learns chaotic Lorenz dynamics from scratch in the browser, with backpropagation and an Adam optimizer written by hand in JavaScript. github.com/erik2810/differentiable-physics-engine
Full project portfolio with live demos at erik2810.github.io/projects