Steven Lang

prof_pic.jpg

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 computer vision. In specific, I work on bridging the gap between probabilistic circuits and deep neural networks. We want to push the limits of Sum-Product Networks and aim to combine their strengths with the modeling capacity of neural networks.

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

News

Oct 21, 2021 Our paper Elevating Perceptual Sample Quality in Probabilistic Circuits through Differentiable Sampling has been accepted for the NeurIPS 2021 Workshop on Pre-registration in Machine Learning!
Jun 15, 2021 I’ve joined the Artificial Intelligence and Machine Learning Lab (AIML) at TU-Darmstadt as a PhD student!

Selected Publications [full list]

  1. NeurIPS
    Elevating Perceptual Sample Quality in Probabilistic Circuits through Differentiable Sampling
    Lang, Steven, Mundt, Martin, Ventola, Fabrizio, Peharz, Robert, and Kersting, Kristian
    In Conference on Neural Information Processing Systems (NeurIPS) Pre-registration Workshop 2021
  2. arXiv
    CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
    Mundt, Martin, Lang, Steven, Delfosse, Quentin, and Kersting, Kristian
    2021
  3. arXiv
    DAFNe: A One-Stage Anchor-Free Deep Model for Oriented Object Detection
    Lang, Steven, Ventola, Fabrizio, and Kersting, Kristian
    2021
  4. ICML
    Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits
    Peharz, Robert, Lang, Steven, Vergari, Antonio, Stelzner, Karl, Molina, Alejandro, Trapp, Martin, Van Den Broeck, Guy, Kersting, Kristian, and Ghahramani, Zoubin
    In Proceedings of the 37th International Conference on Machine Learning 13–18 jul 2020