DESIGN STUDY · Visual direction / content illustrative
Tim ProkoschPersonal website

Mathematician and researcher

Tim Prokosch

RPTU Kaiserslautern-Landau

I am a doctoral researcher and research associate at RPTU Kaiserslautern-Landau, with a background in mathematics and web development.

Tim Prokosch

Mathematics for
real-world questions

I am pursuing a doctorate in mathematics under the supervision of Prof. Dr. Ralf Korn. My interests include financial mathematics and computational approaches to mathematical problems.

Alongside my academic work, I develop software for the web. I enjoy working between mathematical ideas and their implementation.

2026

Research article

Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation

Open Research Europe, version 1

A graph-attention model for recovering animation-ready joint rotations from 3D joint positions.

arXiv Full text Open Research Europe Project page Related SCA poster
Abstract (summary)

IK-GAT uses the skeletal hierarchy to infer bone-aligned world rotations from 3D joint positions in a single pass. These are converted analytically to parent-relative local rotations for animation rigs. The study evaluates the approach on standardized body-model and production-rig benchmarks, including robustness to noisy inputs.

Cite
@article{khan2026amortized,
  title = {{Amortized Inverse Kinematics via Graph Attention for Real-Time Human Avatar Animation}},
  author = {Khan, Muhammad Saif Ullah and Wang, Chen-Yu and Prokosch, Tim and Lorenz, Michael and Taetz, Bertram and Stricker, Didier},
  journal = {Open Research Europe},
  year = {2026},
  volume = {6},
  doi = {10.12688/openreseurope.24416.1},
  url = {https://doi.org/10.12688/openreseurope.24416.1},
  number = {314},
}
Download .bib
2024

Master’s thesis

Entropic Sparse Learning Utilising Reconstruction on Affine Subspaces

RPTU Kaiserslautern-Landau

Extensions of entropic learning using cluster-dependent rotations and reconstructive subspaces.

ResearchGate
Abstract (summary)

The thesis develops CReSPA and eSPARS to address limitations of axis-aligned feature extraction and clustering. It compares the methods with eSPA on synthetic and real-world data, exploring classification quality, computational cost, and model complexity. The reported results indicate that eSPARS can achieve comparable or improved classification performance, while CReSPA did not yet outperform the baseline overall.

Cite
@mastersthesis{prokosch2024entropic,
  title = {{Entropic Sparse Learning Utilising Reconstruction on Affine Subspaces}},
  author = {Prokosch, Tim},
  school = {RPTU Kaiserslautern-Landau},
  year = {2024},
  url = {https://www.researchgate.net/publication/408719671_Entropic_Sparse_Learning_Utilising_Reconstruction_on_Affine_Subspaces},
}
Download .bib
2022

Bachelor’s thesis

Solving Differential Equations by Means of Physics Informed Neural Networks

TU Kaiserslautern

A Python framework for approximating solutions to differential equations with physics-informed neural networks.

ResearchGate
Abstract (summary)

The thesis develops a modular Python framework using physics-informed neural networks to approximate solutions to boundary and initial value problems. It evaluates the framework on ordinary and partial differential equations, including wave, heat, and Burgers equations, and discusses the strengths and limitations of the results.

Cite
@bachelorsthesis{prokosch2022pinn,
  title = {{Solving Differential Equations by Means of Physics Informed Neural Networks}},
  author = {Prokosch, Tim},
  school = {TU Kaiserslautern},
  year = {2022},
  url = {https://www.researchgate.net/publication/364204003_Solving_differential_equations_by_means_of_Physics_Informed_Neural_Networks},
}
Download .bib

Selected projects

Browse all repositories

Background and
recent activity

Background

Experience & education ↗

A closer look at my academic and professional background.

Updates

Notes & updates ↗

Research, conferences, and things worth sharing.