Our group investigates foundational research problems that enable artificial intelligence (AI) systems to become a reliable component of our everyday lives.

The most important limitation of current AI systems is that they fail to give reliable predictions in unseen or adverse conditions. For example, computer vision systems are unreliable when objects are partially occluded, seen in an unusual pose or context, or in bad weather. This lack of robustness in AI systems is generally acknowledged but largely remains unsolved. Our working hypothesis is that AI models need to develop a causal generative understanding of our world to become a truly reliable component of our everyday lives.

Dr. Adam Kortylewski
Group Leader


Google Scholar
Github
Twitter
Youtube
LinkedIn



We are constantly looking for highly motivated PhD students, visiting students and interns to join our team.

News

[Mar 2023] We will organize the 2nd Workshop on Out Of Distribution Generalization in Computer Vision at ICCV 2023.
[Mar 2023] We will organize the 4th Workshop on Adversarial Robustness in the Real World at ICCV 2023.
[Mar 2023] Adam will give a talk at the 5th Workshop on Vision for All Seasons: Adverse Weather and Lighting Conditions at CVPR 2023.
[Mar 2023] Our paper was selected as highlight at CVPR 2023 (top 2.5%)! .
[Mar 2023] Adam will serve as Area Chair for NeurIPS 2023. Great honour!
[Feb 2023] Three papers accepted at CVPR 2023.
[Feb 2023] Adam will give a talk at the TrustML Young Scientist Seminar in March.
[Feb 2023] Adam will give a talk at the Workshop on Practical Deep Learning in the Wild at AAAI 2023.
[Jan 2023] Two papers accepted at ICLR 2023.
[Jan 2023] Two papers accepted at EUROGRAPHICS 2023.
[Dec 2023] We will organize the Workshop on Generative Models for Computer Vision at CVPR 2023.
[Oct 2022] Join us at ECCV 2022 in the Workshop on Out Of Distribution Generalization in Computer Vision.
[Oct 2022] Two papers accepted at WACV 2023.
[Sep 2022] Best paper honorable mention at VMV 2022.
[Jul 2022] Three papers (one Oral) at ECCV 2022 .
[Jul 2022] Adam Kortylewski was appointed as Emmy Noether group leader at the University of Freiburg.
[Apr 2022] We organize three Workshops at ECCV 2022! We cover different aspects of robustness in computer vision:
Out-of-distribution generalization, Cross-dataset generalization, and Adversarial Robustness.
[Mar 2022] Four papers (one Oral) at CVPR 2022.
[Feb 2022] Adam Kortylewski was appointed as research group leader at the Max Planck Instutite for Informatics He will lead the Generative Vision research group with a focus on developing an analysis-by-synthesis approach to computer vision..
[Feb 2022] Adam Kortylewski was awarded an Emmy Noether Grant. He will receive 1.7 Million Euros to research how deep learning and generative models can be combined to better understand the 3D compositional structure of visual scenes in images.