Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Georg Martius

On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks


Apr 01, 2022
Maximilian Seitzer, Arash Tavakoli, Dimitrije Antic, Georg Martius

* ICLR 2022 camera-ready version. Code available at http://github.com/martius-lab/beta-nll 

  Access Paper or Ask Questions

Hierarchical Reinforcement Learning with Timed Subgoals


Dec 06, 2021
Nico Gürtler, Dieter Büchler, Georg Martius

* Published at NeurIPS 2021. Code available at https://github.com/martius-lab/HiTS 

  Access Paper or Ask Questions

A soft thumb-sized vision-based sensor with accurate all-round force perception


Nov 10, 2021
Huanbo Sun, Katherine J. Kuchenbecker, Georg Martius

* 1 table, 5 figures, 24 pages for the main manuscript. 5 tables, 12 figures, 27 pages for the supplementary material. 8 supplementary videos 

  Access Paper or Ask Questions

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains


Oct 29, 2021
Christian Gumbsch, Martin V. Butz, Georg Martius


  Access Paper or Ask Questions

Planning from Pixels in Environments with Combinatorially Hard Search Spaces


Oct 12, 2021
Marco Bagatella, Mirek Olšák, Michal Rolínek, Georg Martius


  Access Paper or Ask Questions

Self-supervised Reinforcement Learning with Independently Controllable Subgoals


Sep 09, 2021
Andrii Zadaianchuk, Georg Martius, Fanny Yang


  Access Paper or Ask Questions

Causal Influence Detection for Improving Efficiency in Reinforcement Learning


Jun 07, 2021
Maximilian Seitzer, Bernhard Schölkopf, Georg Martius


  Access Paper or Ask Questions

Theory of Geometric Super-resolution for Haptic Sensor Design


May 25, 2021
Huanbo Sun, Georg Martius


  Access Paper or Ask Questions

Assessing aesthetics of generated abstract images using correlation structure


May 18, 2021
Sina Khajehabdollahi, Georg Martius, Anna Levina

* 2019 IEEE Symposium Series on Computational Intelligence (SSCI), 306-313 

  Access Paper or Ask Questions

Informed Equation Learning


May 13, 2021
Matthias Werner, Andrej Junginger, Philipp Hennig, Georg Martius


  Access Paper or Ask Questions

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints


May 05, 2021
Anselm Paulus, Michal Rolínek, Vít Musil, Brandon Amos, Georg Martius


  Access Paper or Ask Questions

The dynamical regime and its importance for evolvability, task performance and generalization


Mar 22, 2021
Jan Prosi, Sina Khajehabdollahi, Emmanouil Giannakakis, Georg Martius, Anna Levina

* 8 Pages, 7 Figures, Artificial Life Conference 2021 

  Access Paper or Ask Questions

Neuro-algorithmic Policies enable Fast Combinatorial Generalization


Feb 15, 2021
Marin Vlastelica, Michal Rolínek, Georg Martius

* 15 pages 

  Access Paper or Ask Questions

Demystifying Inductive Biases for $β$-VAE Based Architectures


Feb 12, 2021
Dominik Zietlow, Michal Rolinek, Georg Martius


  Access Paper or Ask Questions

How to Train Your Differentiable Filter


Dec 28, 2020
Alina Kloss, Georg Martius, Jeannette Bohg


  Access Paper or Ask Questions

Self-supervised Visual Reinforcement Learning with Object-centric Representations


Nov 29, 2020
Andrii Zadaianchuk, Maximilian Seitzer, Georg Martius


  Access Paper or Ask Questions

Sample-efficient Cross-Entropy Method for Real-time Planning


Aug 14, 2020
Cristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Georg Martius


  Access Paper or Ask Questions

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers


Mar 25, 2020
Michal Rolínek, Paul Swoboda, Dominik Zietlow, Anselm Paulus, Vít Musil, Georg Martius

* The code is available at https://github.com/martius-lab/blackbox-deep-graph-matching 

  Access Paper or Ask Questions

Optimizing Rank-based Metrics with Blackbox Differentiation


Dec 07, 2019
Michal Rolínek, Vít Musil, Anselm Paulus, Marin Vlastelica, Claudio Michaelis, Georg Martius

* The code is available at https://github.com/martius-lab/blackbox-backprop 

  Access Paper or Ask Questions

Analytical classical density functionals from an equation learning network


Dec 06, 2019
Shang-Chun Lin, Georg Martius, Martin Oettel

* Update figures and SI. Some explanations and clarifications are added 

  Access Paper or Ask Questions

Differentiation of Blackbox Combinatorial Solvers


Dec 04, 2019
Marin Vlastelica, Anselm Paulus, Vít Musil, Georg Martius, Michal Rolínek

* The code is available at https://github.com/martius-lab/blackbox-backprop 

  Access Paper or Ask Questions

Fast Non-Parametric Learning to Accelerate Mixed-Integer Programming for Online Hybrid Model Predictive Control


Nov 20, 2019
Jia-Jie Zhu, Georg Martius


  Access Paper or Ask Questions

Control What You Can: Intrinsically Motivated Task-Planning Agent


Jun 19, 2019
Sebastian Blaes, Marin Vlastelica Pogančić, Jia-Jie Zhu, Georg Martius


  Access Paper or Ask Questions

Autonomous Identification and Goal-Directed Invocation of Event-Predictive Behavioral Primitives


Feb 26, 2019
Christian Gumbsch, Martin V. Butz, Georg Martius


  Access Paper or Ask Questions

Variational Autoencoders Pursue PCA Directions (by Accident)


Dec 17, 2018
Michal Rolinek, Dominik Zietlow, Georg Martius


  Access Paper or Ask Questions

Deep Reinforcement Learning for Event-Triggered Control


Sep 13, 2018
Dominik Baumann, Jia-Jie Zhu, Georg Martius, Sebastian Trimpe


  Access Paper or Ask Questions

Learning Equations for Extrapolation and Control


Jun 19, 2018
Subham S. Sahoo, Christoph H. Lampert, Georg Martius

* 9 pages, 9 figures, ICML 2018 

  Access Paper or Ask Questions

L4: Practical loss-based stepsize adaptation for deep learning


Jun 05, 2018
Michal Rolinek, Georg Martius


  Access Paper or Ask Questions

Extrapolation and learning equations


Oct 10, 2016
Georg Martius, Christoph H. Lampert

* 13 pages, 8 figures, 4 tables 

  Access Paper or Ask Questions