Eike Eberhard · PhD Candidate · TUM · MDSI · MCML
Portrait of Eike Eberhard

Machine Learning for Electronic Structure

Neural network exchange-correlation functionals, differentiable SCF solvers, and equivariant architectures to accelerate quantum chemistry from first principles.

Portrait of Eike Eberhard
01 · About

Background

I am a PhD researcher at the Technical University of Munich working at the intersection of machine learning and quantum chemistry. My goal is to make density functional theory faster and more accurate by learning its hardest component, the exchange-correlation functional, directly from data.

I develop equivariant graph neural networks that operate on molecular electronic structure, differentiable self-consistent field solvers in JAX, and training paradigms that leverage physical derivatives on the Grassmannian manifold of density matrices.

02 · Research

Focus Areas

Neural XC Functionals

Learning the exchange-correlation functional of DFT using expressive neural network architectures, from semi-local mGGA models to fully equivariant graph-based functionals that see the molecular topology.

Differentiable SCF Solvers

End-to-end differentiable self-consistent field calculations in JAX, enabling gradient-based training through the iterative Kohn-Sham procedure with custom backward passes through eigendecompositions and DIIS.

Equivariant Architectures

SE(3)-equivariant graph neural networks that respect the symmetries of molecular systems, building on frameworks like e3nn, NequIP, and EquiformerV2 for electronic structure prediction.

SCF Acceleration

Learning intelligent initial guesses and convergence strategies for self-consistent field calculations to reduce the computational cost of density functional theory at scale.

03 · Selected Papers

Publications

Transferable SCF-Acceleration through Solver-Aligned Initialization Learning

Eike Eberhard*, Viktor Kotsev*, Timm Güthle, Stephan Günnemann
Preprint · 2026

3D Molecule Generation from Rigid Motifs via SE(3) Flows

Roman Poletukhin, Marcel Kollovieh, Eike Eberhard, Stephan Günnemann
Preprint · 2026

Force Generation by Enhanced Diffusion in Enzyme-Loaded Vesicles

Eike Eberhard*, Ludwig Burger*, César L. Pastrana*, Hamid Seyed-Allaei, Giovanni Giunta, Ulrich Gerland
Nano Letters · 2025
Spotlight ChemAI 2025 · 1st Place

Learning Equivariant Non-Local Electron Density Functionals

Eike Eberhard*, Nicholas Gao*, Stephan Günnemann
International Conference on Learning Representations · 2025
04 · Tools

Interactive Utilities

Markdown Utility

Markdown Counter & Compressor

Count words, characters, and tokens while compacting markdown-heavy text for tighter prompts and cleaner sharing.

Visualization

Molecule Viewer

Inspect molecular structures in an interactive viewer with alternate representations for geometry, graphs, and related views.

Quantum Chemistry

QChem Unit Converter

Convert between common quantum chemistry units quickly without leaving the browser or rebuilding your workflow.

Visualization

Architecture Builder

Design ML architecture flowcharts interactively with color-coded blocks, snap alignment, and clean PDF figure export for papers.

05 · CV

Academic CV

Academic Path

2025 Jan - Present
PhD Candidate
Data Analytics and Machine Learning Group @ TUM
Munich Data Science Institute (MDSI)
2022 Oct - Aug 2024
M.Sc. Computer Science & Engineering
Technical University of Munich (TUM)
Best of class 2024
Thesis in machine learning for density functional theory at the Data Analytics and Machine Learning chair (Prof. Günnemann).
2021 Oct - Oct 2023
M.Sc. Physics
Technical University of Munich (TUM)
Specialization in theoretical biophysics.
Thesis on effects of enhanced diffusion in enzyme-loaded vesicles: a multiscale simulation study.
2017 Oct - 2021 Oct
B.Sc. Physics
Technical University of Munich (TUM)
Thesis on mathematical particle physics: extending dispersive bounds to include sub-threshold branch cuts.

Invited Talks

2025 Nov
AMLab
Ensing & Welling groups, University of Amsterdam
2025 May
University of Heidelberg
2024 Nov
Learning on Graphs Reading Group
MIT (online format)