78 citations · 91 across the 13 of their papers we have counts for
14 papers
Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA
Philip Müller, Nicholas Popovič, Michael Färber +1
Reliable uncertainty quantification (UQ) is essential for safe deployment of large language models (LLMs) in scientific question answering, where long-form outputs exceed practical…
Self-supervised denoising of raw tomography detector data for improved image reconstruction
Israt Jahan Tulin, Sebastian Starke, Dominic Windisch +2
Ultrafast electron beam X-ray computed tomography produces noisy data due to short measurement times, causing reconstruction artifacts and limiting overall image quality. To counte…
Data-efficient U-Net for Segmentation of Carbide Microstructures in SEM Images of Steel Alloys
Alinda Ezgi Gerçek, Till Korten, Paul Chekhonin +2
Understanding reactor-pressure-vessel steel microstructure is crucial for predicting mechanical properties, as carbide precipitates both strengthen the alloy and can initiate crack…
Simulation-Based Inference: A Practical Guide
Michael Deistler, Jan Boelts, Peter Steinbach +11
A central challenge in many areas of science and engineering is to identify model parameters that are consistent with prior knowledge and empirical data. Bayesian inference offers…
Virtual Pulse Reconstruction Diagnostic for Single-Shot Measurement of Free Electron Laser Radiation Power
Till Korten, Vladimir Rybnikov, Peter Steinbach +1
Accurate characterization of radiation pulse profiles is crucial for optimizing beam quality and enhancing experimental outcomes in Free Electron Laser (FEL) research. In this pape…
Testing Uncertainty of Large Language Models for Physics Knowledge and Reasoning
Elizaveta Reganova, Peter Steinbach
Large Language Models (LLMs) have gained significant popularity in recent years for their ability to answer questions in various fields. However, these models have a tendency to "h…
Harnessing Machine Learning for Single-Shot Measurement of Free Electron Laser Pulse Power
Till Korten, Vladimir Rybnikov, Mathias Vogt +3
Electron beam accelerators are essential in many scientific and technological fields. Their operation relies heavily on the stability and precision of the electron beam. Traditiona…
sbi reloaded: a toolkit for simulation-based inference workflows
Jan Boelts, Michael Deistler, Manuel Gloeckler +30
Scientists and engineers use simulators to model empirically observed phenomena. However, tuning the parameters of a simulator to ensure its outputs match observed data presents a…
Uncertainty Estimation in Instance Segmentation with Star-convex Shapes
Qasim M. K. Siddiqui, Sebastian Starke, Peter Steinbach
Instance segmentation has witnessed promising advancements through deep neural network-based algorithms. However, these models often exhibit incorrect predictions with unwarranted…
Detecting Adversarial Examples in Batches -- a geometrical approach
Danush Kumar Venkatesh, Peter Steinbach
Many deep learning methods have successfully solved complex tasks in computer vision and speech recognition applications. Nonetheless, the robustness of these models has been found…
Recommendations on test datasets for evaluating AI solutions in pathology
André Homeyer, Christian Geißler, Lars Ole Schwen +27
Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to…
Machine Learning State-of-the-Art with Uncertainties
Peter Steinbach, Felicita Gernhardt, Mahnoor Tanveer +2
With the availability of data, hardware, software ecosystem and relevant skill sets, the machine learning community is undergoing a rapid development with new architectures and app…
An automated workflow for parallel processing of large multiview SPIM recordings
Christopher Schmied, Peter Steinbach, Tobias Pietzsch +2
Multiview light sheet fluorescence microscopy (LSFM) allows to image developing organisms in 3D at unprecedented temporal resolution over long periods of time. The resulting massiv…
How do particle physicists learn the programming concepts they need?
Stefan Kluth, Maria Grazia Pia, Thomas Schoerner-Sadenius +1
The ability to read, use and develop code efficiently and successfully is a key ingredient in modern particle physics. We report the experience of a training program, identified as…