Papers

Our latest publications

  • 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
  • An Adaptive Mechatronic Exoskeleton for Force-Controlled Finger Rehabilitation
    Thomas Dickmann, Nikolas J. Wilhelm, Claudio Glowalla, Sami Haddadin, Patrick van der Smagt, and Rainer Burgkart  (2021)
    Frontiers in Robotics and AI
    doi
  • 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)
    paper | video
  • 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
  • Rapid Probabilistic Estimation of Type Ia Supernovae Explosion Parameters I: Single Epoch Spectrum of SN 2002bo
    John T. O'Brien, Wolfgang E. Kerzendorf, Andrew Fullard, Marc Williamson, Ruediger Pakmor, Johannes Buchner, Stephan Hachinger, Christian Vogl, James H. Gillanders, Andreas Floers, and Patrick van der Smagt (2021)
    paper | data
  • Dalek: A deep-learning emulator for TARDIS
    Wolfgang E. Kerzendorf, Christian Vogl, Johannes Buchner, Gabriella Contardo, Marc Williamson, and Patrick van der Smagt (2021)
    The Astrophysical Journal Letters, Volume 910, Number 2
    paper | 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
  • SnakeStrike: A Low-cost Open-source High-speed Multi-camera Motion Capture System
    Grady Jensen, Patrick van der Smagt, Egon Heiss, Hans Straka, and Tobias Kohl (2020)
    Behav. Neurosci., 03 August 2020
    doi
  • 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
  • Estimating Fingertip Forces, Torques, and Local Curvatures from Fingernail Images
    Nutan Chen, Göran Westling, Benoni B. Edin, and Patrick van der Smagt (2020)
    Robotica
    paper | blog | doi
  • Variational Tracking and Prediction with Generative Disentangled State-Space Models
    Adnan Akhundov, Maximilian Soelch, Justin Bayer, and Patrick van der Smagt (2019)
    paper
  • Early Integration for Movement Modeling in Latent Spaces
    Rachel Hornung, Nutan Chen, and Patrick van der Smagt (2019)
    The Handbook of Multimodal-Multisensor Interfaces, Volume 3: Language Processing, Software, Commercialization, and Emerging Directions
    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
  • CNN-based segmentation of medical imaging data
    Baris Kayalibay, Grady Jensen, and Patrick van der Smagt (2017)
    paper
  • 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
  • Dynamic movement primitives in latent space of time-dependent variational autoencoders
    Nutan Chen, Maximilian Karl, and Patrick van der Smagt (2016)
    International Conference on Humanoid Robots (Humanoids)
    paper

Previous publications