179 citations · 1k across the 25 of their papers we have counts for
25 papers
Fast yet Safe: Early-Exiting with Risk Control
Metod Jazbec, Alexander Timans, Tin Hadži Veljković +4
Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural net…
Adaptive Bounding Box Uncertainties via Two-Step Conformal Prediction
Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann +1
Quantifying a model's predictive uncertainty is essential for safety-critical applications such as autonomous driving. We consider quantifying such uncertainty for multi-object det…
Max-Rank: Efficient Multiple Testing for Conformal Prediction
Alexander Timans, Christoph-Nikolas Straehle, Kaspar Sakmann +2
Multiple hypothesis testing (MHT) frequently arises in scientific inquiries, and concurrent testing of multiple hypotheses inflates the risk of Type-I errors or false positives, re…
Anomaly-Aware Semantic Segmentation via Style-Aligned OoD Augmentation
Dan Zhang, Kaspar Sakmann, William Beluch +2
Within the context of autonomous driving, encountering unknown objects becomes inevitable during deployment in the open world. Therefore, it is crucial to equip standard semantic s…
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
Maksym Yatsura, Kaspar Sakmann, N. Grace Hua +2
Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to cert…
Conserving symmetries in Bose-Einstein condensate dynamics requires many-body theory
Kaspar Sakmann, Jörg Schmiedmayer
We explain from first principles why satisfying conservation laws in Bose Einstein condensate dynamics requires many-body theory. For the Gross-Pitaevskii mean-field we show analyt…