activity
20222025
most citedWinning the Lottery Ahead of Time: Efficient Early Network Pruning

4 citations · 6 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2025

Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation

Johanna Sommer, John Rachwan, Nils Fleischmann +2

Flow matching models generate high-fidelity molecular geometries but incur significant computational costs during inference, requiring hundreds of network evaluations. This inferen…

cs.LG2024

Structurally Prune Anything: Any Architecture, Any Framework, Any Time

Xun Wang, John Rachwan, Stephan Günnemann +1

Neural network pruning serves as a critical technique for enhancing the efficiency of deep learning models. Unlike unstructured pruning, which only sets specific parameters to zero…

cs.CV2022

3D Labeling Tool

John Rachwan, Charbel Zalaket

Training and testing supervised object detection models require a large collection of images with ground truth labels. Labels define object classes in the image, as well as their l…

cs.LG2022★ 2 cited

On the Robustness and Anomaly Detection of Sparse Neural Networks

Morgane Ayle, Bertrand Charpentier, John Rachwan +3

The robustness and anomaly detection capability of neural networks are crucial topics for their safe adoption in the real-world. Moreover, the over-parameterization of recent netwo…

cs.LG2022★ 4 cited

Winning the Lottery Ahead of Time: Efficient Early Network Pruning

John Rachwan, Daniel Zügner, Bertrand Charpentier +3

Pruning, the task of sparsifying deep neural networks, received increasing attention recently. Although state-of-the-art pruning methods extract highly sparse models, they neglect…