Deep Learning

Oral presentation at ICPR 2024 introducing TaylorShift, a novel reformulation of the attention mechanism using Taylor-Softmax that enables full token-to-token interactions in linear time.

We speed up diffusion classifiers by utilizing a label hierarchy and pruning unrelated paths.

We improve dataset distillation by distilling only a representative coreset.

We utilize the TaylorShift attention mechanism for global pixel-wise-attention in image super-resolution.

At its core, Albatross is a research project in the area of continual learning.

SustainML is dedicated to creating a sustainable ML framework for Green AI. By prioritizing energy efficiency, SustainML aims to pave the way for environmentally conscious AI solutions that are both efficient and effective.

Energy- and data-saving methods for environmental perception in embedded AI systems using the case study of smart factory and smart farming applications; funded by the Carl Zeiss Foundation.

We extend and test KEdge, an interpretable-by-design approach for graph neural networks, and compare it to gradient-based attribution techniques.