6 papers
Quantifying the Uncertainty of Foundation Models with Singular Value Ensembles
Mehmet Ozgur Turkoglu, Dominik J. Mühlematter, Alexander Becker +2
Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pretraining. However, they often yi…
LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks
Dominik J. Mühlematter, Michelle Halbheer, Alexander Becker +4
Numerous real-world decisions rely on machine learning algorithms and require calibrated uncertainty estimates. However, modern methods often yield overconfident, uncalibrated pred…
Continuous Space-Time Video Super-Resolution with 3D Fourier Fields
Alexander Becker, Julius Erbach, Dominik Narnhofer +1
We introduce a novel formulation for continuous space-time video super-resolution. Instead of decoupling the representation of a video sequence into separate spatial and temporal c…
Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
Alexander Becker, Rodrigo Caye Daudt, Dominik Narnhofer +4
Recent approaches to arbitrary-scale single image super-resolution (ASR) use neural fields to represent continuous signals that can be sampled at arbitrary resolutions. However, po…
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
Massimiliano Viola, Kevin Qu, Nando Metzger +4
Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constra…
The unrealized potential of agroforestry for an emissions-intensive agricultural commodity
Alexander Becker, Jan D. Wegner, Evans Dawoe +7
Reconciling agricultural production with climate-change mitigation is a formidable sustainability problem. Retaining trees in agricultural systems is one proposed solution, but the…