Steven Braun


I’m a PhD student at the Artificial Intelligence and Machine Learning Lab, TU Darmstadt. My main research interests cover a broad range of Machine Learning related topics such as deep models, tractable probabilistic circuits and their applications. In specific, I work on bridging the gap between probabilistic circuits and deep neural networks. We want to push the limits of probabilistic circuits and aim to combine their strengths with the modeling capacity of neural networks.

If you are a motivated student looking for a thesis topic and are interested in the subjects mentioned above, feel free to contact me.

Note: Until 2022 known as Steven Lang.

Contact: steven (dot) braun (at) cs (dot) tu-darmstadt (dot) de


  1. braun2023tdi.png
    Probabilistic Circuits That Know What They Don’t Know
    Fabrizio Ventola*, Steven Braun*, Zhongjie Yu, Martin Mundt, and Kristian Kersting
    arXiv preprint, arXiv:2302.06544, 2023
  2. trapp2022towards.png
    Towards Coreset Learning in Probabilistic Circuits
    Martin Trapp, Steven Lang, Aastha Shah, Martin Mundt, Kristian Kersting, and Arno Solin
    In The 5th Workshop on Tractable Probabilistic Modeling (UAI), 2022
  3. mundt2021clevacompass.png
    CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
    Martin Mundt, Steven Lang, Quentin Delfosse, and Kristian Kersting
    In International Conference on Learning Representations (ICLR), 2022
  4. lang2022diff-sampling-spns.jpg
    Elevating Perceptual Sample Quality in Probabilistic Circuits through Differentiable Sampling
    Steven Lang, Martin Mundt, Fabrizio Ventola, Robert Peharz, and Kristian Kersting
    In NeurIPS 2021 Workshop on Pre-registration in Machine Learning, 2022
  5. lang2021dafne.jpg
    DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection
    Steven Lang, Fabrizio Ventola, and Kristian Kersting
    arXiv preprint, arXiv:2109.06148, 2021
  6. pmlr-v119-peharz20a.png
    Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
    Robert Peharz, Steven Lang, Antonio Vergari, Karl Stelzner, Alejandro Molina, Martin Trapp, Guy Van Den Broeck, Kristian Kersting, and Zoubin Ghahramani
    In Proceedings of the 37th International Conference on Machine Learning, 13–18 jul 2020
  7. lang2019wekadeeplearning4j.jpg
    WekaDeeplearning4j: A deep learning package for Weka based on Deeplearning4j
    Steven Lang, Felipe Bravo-Marquez, Christopher Beckham, Mark Hall, and Eibe Frank
    Knowledge-Based Systems, 13–18 jul 2019