7 citations · 9 across the 3 of their papers we have counts for
6 papers
Force without transmission: a depth-induced rank collapse that no loss on the representation reopens
Martin Hofmann, Patrick Mäder
Training can drive a transformer into a rank collapse: all token representations point in one direction, and learning stops. In a related collapse of attention, a loss term with a…
When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screen
Martin Hofmann, Patrick Mäder
Networks that behave alike now can still learn differently when training continues. Work on loss of plasticity and critical periods shows that the path to a state shapes what follo…
Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system
Philipp Teutsch, Philipp Pfeffer, Mohammad Sharifi Ghazijahani +3
In recent years, data-driven deep learning models have gained significant interest in the analysis of turbulent dynamical systems. Within the context of reduced-order models (ROMs)…
Object classification on video data of meteors and meteor-like phenomena: algorithm and data
Rabea Sennlaub, Martin Hofmann, Mike Hankey +4
Every moment, countless meteoroids enter our atmosphere unseen. The detection and measurement of meteors offer the unique opportunity to gain insights into the composition of our s…
Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Study
Daniel Scheliga, Patrick Mäder, Marco Seeland
Gradient Inversion (GI) attacks are a ubiquitous threat in Federated Learning (FL) as they exploit gradient leakage to reconstruct supposedly private training data. Common defense…
LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation
Sambit Mohapatra, Mona Hodaei, Senthil Yogamani +5
Moving object detection and segmentation is an essential task in the Autonomous Driving pipeline. Detecting and isolating static and moving components of a vehicle's surroundings a…