Papers

Our latest publications

  • Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
    Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, and Maximilian Karl (2023)
    Conference on Neural Information Processing Systems (NeurIPS)
    paper | blog
  • On the Role of the Action Space in Robot Manipulation Learning and Sim-to-Real Transfer
    Elie Aljalbout, Felix Frank, Maximilian Karl, and Patrick van der Smagt (2023)
    paper
  • AI Regulation Is (not) All You Need
    Laura Lucaj, Patrick van der Smagt, and Djalel Benbouzid (2023)
    Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency
    paper | doi
  • Filter-Aware Model-Predictive Control
    Baris Kayalibay, Atanas Mirchev, Ahmed Agha, Patrick van der Smagt, and Justin Bayer (2023)
    Learning for Dynamics and Control Conference
    paper
  • A sector-based approach to AI ethics: Understanding ethical AI-related incidents within their sectoral context
    Dafna Burema, Nicole Debowski-Weimann, Alexander von Janowski, Jill Grabowski, Mihai Maftei, Mattis Jacobs, Patrick van der Smagt, and Djalel Benbouzid (2023)
    Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society
    paper
  • Initial state preparation for quantum chemistry on quantum computers
    Stepan Fomichev, Kasra Hejazi, Modjtaba Shokrian Zini, Matthew Kiser, Joana Fraxanet Morales, Pablo Antonio Moreno Casares, Alain Delgado, Joonsuk Huh, Arne-Christian Voigt, Jonathan E. Mueller, and Juan Miguel Arrazola (2023)
    paper
  • Quantum Optimization: Potential, Challenges, and the Path Forward
    Amira Abbas and et al. (2023)
    paper
  • CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces
    Elie Aljalbout, Maximilian Karl, and Patrick van der Smagt (2023)
    Learning for Dynamics and Control Conference
    paper
  • PRISM: Probabilistic Real-Time Inference in Spatial World Models
    Atanas Mirchev, Baris Kayalibay, Ahmed Agha, Patrick van der Smagt, Daniel Cremers, and Justin Bayer (2022)
    Conference on Robot Learning
    paper | blog
  • Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphs
    Nutan Chen, Patrick van der Smagt, and Botond Cseke (2022)
    ICML workshop on Topology, Algebra, and Geometry in Machine Learning
    paper
  • Tracking and Planning with Spatial World Models
    Baris Kayalibay, Atanas Mirchev, Patrick van der Smagt, and Justin Bayer (2022)
    Learning for Dynamics and Control
    paper | blog
  • Flat latent manifolds for human-machine co-creation of music
    Nutan Chen, Djalel Benbouzid, Francesco Ferroni, Mathis Nitschke, Luciano Pinna, and Patrick van der Smagt (2022)
    Conference on AI Music Creativity
    paper | blog
  • Latent Matters: Learning Deep State-Space Models
    Alexej Klushyn, Richard Kurle, Maximilian Soelch, Botond Cseke, and Patrick van der Smagt (2021)
    Conference on Neural Information Processing Systems (NeurIPS)
    openreview.net | blog
  • Exploration via Empowerment Gain: Combining Novelty, Surprise and Learning Progress
    Philip Becker-Ehmck, Maximilian Karl, Jan Peters, and Patrick van der Smagt (2021)
    International Conference on Machine Learning (ICML) Workshop on Unsupervised Reinforcement Learning
    openreview.net
  • Less Suboptimal Learning and Control in Variational POMDPs
    Baris Kayalibay, Atanas Mirchev, Patrick van der Smagt, and Justin Bayer (2021)
    International Conference on Learning Representations (ICLR) Workshop for Self-Supervision for Reinforcement Learning
    openreview.net | blog
  • Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
    Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt, and Justin Bayer (2021)
    International Conference on Learning Representations (ICLR)
    paper | openreview.net | blog
  • Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation
    Felix Frank, Alexandros Paraschos, Patrick van der Smagt, and Botond Cseke (2021)
    IEEE Transactions on Robotics
    paper | video | doi
  • Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models
    Justin Bayer, Maximilian Soelch, Atanas Mirchev, Baris Kayalibay, and Patrick van der Smagt (2021)
    International Conference on Learning Representations (ICLR)
    paper | openreview.net | blog
  • Layerwise learning for quantum neural networks
    Andrea Skolik, Jarrod R. McClean, Masoud Mohseni, Patrick van der Smagt, and Martin Leib (2021)
    Quantum Machine Intelligence 3 (1), 1-11
    paper | blog | doi
  • Continual Learning with Bayesian Neural Networks for Non-Stationary Data
    Richard Kurle, Botond Cseke, Alexej Klushyn, Patrick van der Smagt, and Stephan Günnemann (2020)
    International Conference on Learning Representations (ICLR)
    openreview.net | blog
  • Learning to Fly via Deep Model-Based Reinforcement Learning
    Philip Becker-Ehmck, Maximilian Karl, Jan Peters, and Patrick van der Smagt (2020)
    paper | blog
  • Learning Flat Latent Manifolds with VAEs
    Nutan Chen, Alexej Klushyn, Francesco Ferroni, Justin Bayer, and Patrick van der Smagt (2020)
    International Conference on Machine Learning (ICML)
    paper | blog
  • Variational Tracking and Prediction with Generative Disentangled State-Space Models
    Adnan Akhundov, Maximilian Soelch, Justin Bayer, and Patrick van der Smagt (2019)
    paper
  • Beta DVBF: Learning State-Space Models for Control from High Dimensional Observations
    Neha Das, Mximilian Karl, Philip Becker-Ehmck, and Patrick van der Smagt (2019)
    paper
  • Unsupervised real-time control through variational empowerment
    Maximilian Karl, Philip Becker-Ehmck, Maximilian Soelch, Djalel Benbouzid, Patrick van der Smagt, and Justin Bayer (2019)
    International Symposium on Robotics Research (ISRR)
    paper
  • Learning Hierarchical Priors in VAEs
    Alexej Klushyn, Nutan Chen, Richard Kurle, Botond Cseke, and Patrick van der Smagt (2019)
    Conference on Neural Information Processing Systems (NeurIPS)
    paper | blog
  • Switching Linear Dynamics for Variational Bayes Filtering
    Philip Becker-Ehmck, Jan Peters, and Patrick van der Smagt (2019)
    International Conference on Machine Learning (ICML)
    paper
  • Approximate Bayesian inference in spatial environments
    Atanas Mirchev, Baris Kayalibay, Maximilian Soelch, Patrick van der Smagt, and Justin Bayer (2019)
    Robotics: Science and Systems (RSS)
    paper | blog
  • On Deep Set Learning and the Choice of Aggregations
    Maximilian Soelch, Adnan Akhundov, Patrick van der Smagt, and Justin Bayer (2019)
    International Conference on Artificial Neural Networks (ICANN)
    paper | blog
  • Increasing the Generalisation Capacity of Conditional VAEs
    Alexej Klushyn, Nutan Chen, Botond Cseke, Justin Bayer, and Patrick van der Smagt (2019)
    International Conference on Artificial Neural Networks (ICANN)
    paper
  • Fast approximate geodesics for deep generative models
    Nutan Chen, Francesco Ferroni, Alexej Klushyn, Alexandros Paraschos, Justin Bayer, and Patrick van der Smagt (2019)
    International Conference on Artificial Neural Networks (ICANN)
    paper | blog
  • Bayesian learning of neural network architectures
    Georgi Dikov, Patrick van der Smagt, and Justin Bayer (2019)
    International Conference on Artificial Intelligence and Statistics (AISTATS)
    paper | blog
  • ORC—a lightweight, lightning-fast middleware
    Felix Frank, Alexandros Paraschos, and Patrick van der Smagt (2019)
    IEEE International Conference on Robotic Computing (IRC)
    paper | doi
  • Multi-source neural variational inference
    Richard Kurle, Stephan Guennemann, and Patrick van der Smagt (2018)
    AAAI Conference on Artficial Intelligence
    paper
  • Active learning based on data uncertainty and model sensitivity
    Nutan Chen, Alexej Klushyn, Alexandros Paraschos, Djalel Benbouzid, and Patrick van der Smagt (2018)
    International Conference on Intelligent Robots and Systems (IROS)
    paper | blog
  • Metrics for deep generative models
    Nutan Chen, Alexej Klushyn, Richard Kurle, Xueyan Jiang, Justin Bayer, and Patrick van der Smagt (2018)
    International Conference on Artificial Intelligence and Statistics (AISTATS)
    paper | blog
  • Deep variational Bayes filters: unsupervised learning of state space models from raw data
    Maximilian Karl, Maximilian Soelch, Justin Bayer, and Patrick van der Smagt (2017)
    International Conference on Learning Representations (ICLR)
    paper | blog

Previous publications