About Me

I’m a Postdoctoral Reseacher in Frank Hutter’s Machine Learning Lab. Previously, I joined the Stanford AI lab for my master’s thesis to work in Jeannette Bohg’s IPRL group on graph neural networks and robotic manipulation. As a student research assistant, I also worked at Tamim Asfour’s H2T lab with focus on cognitive robotics and robot perception. I hold a M. Sc. from KIT in CS/Machine Learning and am alumnus of the German National Academic Scholarship Foundation.

Publications

For an up-to-date publication record, please check out my Google Scholar profile.

Coding and Open-Sourcing

• Paper implementation “Information Theoretic MPC for Model-Based Reinforcement Learning” (Williams et al., 2017)

• cde, Python package (with over 3k downloads per month) for conditional density estimation with neural network-based, non/semi-parametric and normalizing flow estimators, various data generating processes (AR(1), ARMA jump diffusion, GMM etc.) and evaluation metrics (KL and JS divergence, hellinger distance, etc.)

• videofeatures, Python package (pip install videofeatures) for video/image feature extraction (ResNet, VGG, SIFT, SURF) that, based on the selected feature type, trains a fisher vector GMM and computes (improved) fisher vectors

• video2tfrecord, Python package (pip install video2tfrecord) that allows easy conversion of RGB video data to the TensorFlow tfrecords format

• Planar Manipulatior Dataset, goal-oriented 2D toy dataset for deep neural network testing

• Flying Shapes Dataset, goal-oriented 2D toy dataset for deep neural network testing

• Paper implementation “Movement Primitives via Optimization” (Dragan et al., 2015)