Steven Braun

I’m a research scientist working on deep neural networks and probabilistic models. I did my PhD in the Artificial Intelligence and Machine Learning Lab at TU Darmstadt and focused on bridging probabilistic circuits and deep neural networks. Outside of research, I love writing software, tinkering with Linux, macOS, Emacs, and my self-hosting homelab. I also play badminton and co-lead the badminton department of my local sports club.

GitHub · Google Scholar

Blog

• 2024-11-15 Emacs org-mode: org-emphasize-dwim
• 2022-10-06 Tiling macOS: Moving from i3wm to yabai
• 2021-10-27 Optimizing matplotlib visualizations for scientific papers
• 2021-09-21 A short review of axis-aligned and oriented object detection
• 2021-07-12 An arXiv PDF command-line interface downloader

Publications

• Bridging Probabilistic Circuits and Deep Neural Networks
  Steven Braun — Ph.D. Thesis, Technische Universität Darmstadt, 2026 · PDF · Website
• Tractable Representation Learning with Probabilistic Circuits
  Steven Braun, Sahil Sidheekh, Antonio Vergari, Martin Mundt, Sriraam Natarajan, Kristian Kersting — Transactions on Machine Learning Research (TMLR), 2025 · PDF · Poster
• Deep Classifier Mimicry without Data Access
  Steven Braun, Martin Mundt, Kristian Kersting — International Conference on Artificial Intelligence and Statistics (AISTATS) – Oral & Student Paper Highlight Award, 2024 · PDF · Poster · Slides
• Probabilistic Circuits That Know What They Don’t Know
  Fabrizio Ventola*, Steven Braun*, Zhongjie Yu, Martin Mundt, Kristian Kersting — Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI), 2023 · PDF · Supp · Code · Poster · Slides · Video
• Towards Coreset Learning in Probabilistic Circuits
  Martin Trapp, Steven Lang, Aastha Shah, Martin Mundt, Kristian Kersting, Arno Solin — The 5th Workshop on Tractable Probabilistic Modeling (UAI), 2022 · PDF
• CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
  Martin Mundt, Steven Lang, Quentin Delfosse, Kristian Kersting — International Conference on Learning Representations (ICLR), 2022 · PDF · Code
• Elevating Perceptual Sample Quality in Probabilistic Circuits through Differentiable Sampling
  Steven Lang, Martin Mundt, Fabrizio Ventola, Robert Peharz, Kristian Kersting — Proceedings of Machine Learning Research, Workshop on Preregistration in Machine Learning (NeurIPS), 2022 · PDF · Poster · Slides
• DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection
  Steven Lang, Fabrizio Ventola, Kristian Kersting — arXiv preprint, arXiv:2109.06148, 2021 · arXiv · Code
• 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, Zoubin Ghahramani — Proceedings of the 37th International Conference on Machine Learning (ICML), 2020 · PDF · Code
• WekaDeeplearning4j: A deep learning package for Weka based on Deeplearning4j
  Steven Lang, Felipe Bravo-Marquez, Christopher Beckham, Mark Hall, Eibe Frank — Knowledge-Based Systems, 2019 · PDF · Code