Lampert Group
Machine Learning and Computer Vision
The Lampert group performs research on how to make artificial intelligence methods more trustworthy. It investigates questions like: Can we understand not only what modern machine learning systems are doing, but also why? Can we give guarantees for their behavior? Can we build systems that learn and one day might become intelligent without sacrificing our rights to data protection and privacy?
Computers are becoming increasingly powerful at processing data, and they have learned to perform many tasks that were thought beyond their reach, such as making successful financial investments, diagnosing cancer from medical images, and even driving cars in traffic. So why don’t we rely on them as financial advisors, oncologists, and chauffeurs? It is likely because we do not trust computers enough to let them operate important systems autonomously and outside of our control. Besides theoretical research, the group applies its results to applications in computer vision, such as image understanding, where the goal is to develop automatic systems that can analyze the contents of natural images.
Group Leader
Administrative Support
Team
Current Projects
Trustworthy machine learning | Transfer and lifelong learning | Theory of deep learning
Publications
Prach B. 2025. Robust image classification with 1-Lipschitz networks. Institute of Science and Technology Austria. View
Lutsai K, Lampert C. 2024. Predicting the geolocation of tweets using transformer models on customized data. Journal of Spatial Information Science. (29), 69–99. View
Súkeník P, Lampert C. 2024. Generalization in multi-objective machine learning. Neural Computing and Applications. View
Kalinin N, Lampert C. 2024. Banded square root matrix factorization for differentially private model training. 38th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 37. View
Súkeník P, Lampert C, Mondelli M. 2024. Neural collapse versus low-rank bias: Is deep neural collapse really optimal? 38th Annual Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 37. View
ReX-Link: Christoph Lampert
Career
Since 2015 Professor, Institute of Science and Technology Austria (ISTA)
2010 – 2015 Assistant Professor, Institute of Science and Technology Austria (ISTA)
2007 – 2010 Senior Research Scientist, Max Planck Institute for Biological Cybernetics, Tübingen, Germany
2004 – 2007 Senior Researcher, German Research Center for Artificial Intelligence, Kaiserslautern, Germany
2003 PhD, University of Bonn, Germany
Selected Distinctions
Since 2015 Associate Editor in Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI)
2012 ERC Starting Grant (consolidator phase)
2008 Best Paper Award, IEEE Conference for Computer Vision and Pattern Recognition (CVPR)
2008 Best Student Paper Award, European Conference for Computer Vision (ECCV)
2008 Main Prize, German Society for Pattern Recognition (DAGM)
