FK Fabian Kresse

Bio

Hello there! I am a machine learning PhD student at the Institute of Science and Technology Austria (ISTA), working with Christoph Lampert and Thomas Henzinger.

My research focuses on efficient and verifiable learning systems, particularly neural architectures based on logic circuits. I am interested in models that are data-driven, but can also give us formal guarantees.

Before joining ISTA, I studied computer engineering at TU Wien. Back then I was involved in various projects, mainly autonomous racing and building rockets. As I want to get back into building non-digital things, I am currently building a RC plane.

Fabian Kresse with the Scuderia Segfault autonomous racing team
Autonomous racing with Scuderia Segfault. 1st place at IROS 2021. 2nd place at ICRA 2023. Photo: F1TENTH / mlcontests.com
Fabian Kresse with members of the TU Wien Space Team
At C'Space 2019, where I headed development of the rocket STR-09 'Asimov'. Photo: TU Wien Space Team / spaceteam.at
Research

Logic gate neural networks, Boolean networks, efficient inference, verification, and learning-based control.

Previously

TU Wien, European Space Agency, Scuderia Segfault, and the TU Wien Space Team.

Publications

  1. 2026 International Conference on Machine Learning (ICML) arXiv:2512.01467

    Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control

    Fabian Kresse, Christoph H. Lampert

    arXiv Code
    BibTeX 
    @inproceedings{kresse2026differentiableweightlesscontrollers,
  title = {Differentiable Weightless Controllers: Learning Logic Circuits for Continuous Control},
  author = {Kresse, Fabian and Lampert, Christoph H.},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://arxiv.org/abs/2512.01467}
}
  2. 2025 International Conference on Neuro-symbolic Systems (NeuS) arXiv:2505.19932

    Logic Gate Neural Networks are Good for Verification

    Fabian Kresse, Emily Yu, Christoph H. Lampert, Thomas A. Henzinger

    arXiv Code
    BibTeX 
    @inproceedings{kresse2025logicgateneuralnetworks,
  title = {Logic Gate Neural Networks are Good for Verification},
  author = {Kresse, Fabian and Yu, Emily and Lampert, Christoph H. and Henzinger, Thomas A.},
  booktitle = {International Conference on Neuro-symbolic Systems (NeuS)},
  year = {2025},
  url = {https://arxiv.org/abs/2505.19932}
}
  3. 2026 Learning for Dynamics & Control Conference (L4DC) arXiv:2511.07046

    Learning Quantized Continuous Controllers for Integer Hardware

    Fabian Kresse, Christoph H. Lampert

    arXiv Code
    BibTeX 
    @inproceedings{kresse2026learningquantizedcontinuouscontrollers,
  title = {Learning Quantized Continuous Controllers for Integer Hardware},
  author = {Kresse, Fabian and Lampert, Christoph H.},
  booktitle = {Learning for Dynamics \& Control Conference (L4DC)},
  year = {2026},
  url = {https://arxiv.org/abs/2511.07046}
}
  4. 2025 arXiv preprint arXiv:2507.02585

    Scalable Interconnect Learning in Boolean Networks

    Fabian Kresse, Emily Yu, Christoph H. Lampert

    arXiv
    BibTeX 
    @misc{kresse2025scalableinterconnectlearning,
  title = {Scalable Interconnect Learning in Boolean Networks},
  author = {Kresse, Fabian and Yu, Emily and Lampert, Christoph H.},
  year = {2025},
  eprint = {2507.02585},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  doi = {10.48550/arXiv.2507.02585},
  url = {https://arxiv.org/abs/2507.02585}
}
  5. 2025 Learning for Dynamics & Control Conference (L4DC) arXiv:2412.16564

    Predictive Monitoring of Black-Box Dynamical Systems

    Thomas A. Henzinger, Fabian Kresse, Kaushik Mallik, Emily Yu, Đorđe Žikelić

    arXiv
    BibTeX 
    @inproceedings{henzinger2025predictivemonitoring,
  title = {Predictive Monitoring of Black-Box Dynamical Systems},
  author = {Henzinger, Thomas A. and Kresse, Fabian and Mallik, Kaushik and Yu, Emily and Žikelić, Đorđe},
  booktitle = {Learning for Dynamics \& Control Conference (L4DC)},
  year = {2025},
  url = {https://arxiv.org/abs/2412.16564}
}
  6. 2025 Big Data from Space (BiDS) arXiv:2508.10712

    Lightweight CNNs for Embedded SAR Ship Target Detection and Classification

    Fabian Kresse, Georgios Pilikos, Mario Azcueta, Nicolas Floury

    arXiv
    BibTeX 
    @inproceedings{kresse2025lightweightcnns,
  title = {Lightweight CNNs for Embedded SAR Ship Target Detection and Classification},
  author = {Kresse, Fabian and Pilikos, Georgios and Azcueta, Mario and Floury, Nicolas},
  booktitle = {Big Data from Space (BiDS)},
  year = {2025},
  url = {https://arxiv.org/abs/2508.10712}
}