Movement Primitive Diffusion (MPD) is a diffusion-based imitation learning method for high-quality robotic motion generation that focuses on gentle manipulation of deformable objects.

Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations

Adaptive Swarm Mesh Refinement

Adaptive Swarm Mesh Refinement

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Parallel algorithms and data structures for tree-based adaptive mesh refinement (AMR) with arbitrary element shapes.

Movement Primitives in PyTorch

A modular, flexible framework for developing performant algorithms in Reinforcement Learning.

ClusterWork 2

Meta-repository of the LapGym project

Grounding Graph Network Simulators using Physical Sensor Observations

reproducing the examples from the FEniCS tutorial in scikit-fem

Library for easy data export from WandB to NumPy or CSV.

Implementation of different remote message passing strategies in graph neural networks for mesh-based physical simulation.

Code for "On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning" (TMLR, 2022)

Code for the paper "Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors" published at CoRL2022

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set …

🕸️ Gmsh for Python

Clean PyTorch implementations of imitation and reward learning algorithms

Python 3 library to automate and build finite element analysis (FEA) models in Calculix. Meshing uses Calculix or GMSH.

Exemplary code snippets to show my clean coding skills

Fancy Gym: Unifying interface for various RL benchmarks with support for Black Box approaches.

A Collection of Variational Autoencoders (VAE) in PyTorch.

⚡ A Fast, Extensible Progress Bar for Python and CLI

An automated time tracker (WIP)

Course descriptions and administrative tips about computer science at KIT

Kernel Density Estimation in Python

Code corresponding to "Expected Information Maximization: Using the I-Projection for Mixture Density Estimation", published at ICLR 2020

A fast Python implementation of locality sensitive hashing.