Data Science Day 2025

Posters

5. Assessing Segmentation Errors in Multiplexed Imaging for Tissue Property Inference

Multiplexed tissue imaging provides an unprecedented understanding of tissue biology by capturing the spatial relationships between cells and their protein expression profiles. Common approaches use highly multiplexed fluorescence microscopy to measure tissue slides as images where each channel represents the intensity of a particular protein marker. Single-cell features are generated by...

2. CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series

Causal discovery from observational data is a challenging problem, with many proposed methods lacking thorough real-world evaluation. Most studies rely on synthetic data or limited real-world examples under idealized assumptions, which do not accurately reflect the complexity of real-world systems.

To address this issue, we introduce CausalRivers, a comprehensive benchmarking kit for causal...

4. Data Literacy – More Than Just Data Science for Beginners

The increasing digitalization and datafication of society have made data competencies essential for all citizens, not just for specialists in computer science or data science. As data-driven decision-making becomes central to business, government, and everyday life, the ability to critically engage with data is emerging as a key qualification for the 21st century. Especially in light of recent...

1. EIFER: Electromyography-Informed Facial Expression Reconstruction via Unpaired Image-to-Image Translation

Tim Büchner (Computer Vision Group)

Analyzing facial expressions through muscle activity, captured via surface electromyography (sEMG), offers rich insights for psychology, medicine, and animation. However, sEMG electrodes introduce significant occlusion, hindering accurate facial expression analysis, particularly for monocular 3D face reconstruction. Our method, **EIFER: Electromyography-Informed Facial Expression...

9. Explainable Seismic Signal Discrimination: A Comparative Analysis of Convolutional Neural Networks and Vision Transformers

Traditionally, the discrimination of seismic signals has been carried out manually by expert analysts, who assign events – such as earthquakes, quarry blasts, and other anthropogenically induced events – to specific categories. This process often involves the use of cross-correlation techniques for pattern recognition. Although methods from the field of deep learning, particularly...

6. LLMs for Information Extraction from Clinical Trials

Natural Language Processing plays a crucial role in the automated parsing of clinical data. This data encompasses a wide range of sources including clinical notes, trial documents, imaging and sensor data, and patient-reported outcomes. In the project Avatar, we explore clinical trial documentation. These describe the circumstances of a trial: which patient groups shall be in- or excluded, and...

3. Reinforcement Learning for Laser Alignment

Manual alignment of optical systems can be time consuming and the achieved performance of the system varies depending on the operator doing the alignment. A reinforcement learning approach using the PPO algorithm was used to train agents to align simple two-mirror optical setups, as well as a full regenerative laser amplifier. The goal is to produce agents that can reproducibly align the setup...

8. Spatial and Dynamics Informed Latent-Variable Estimation with Deep Gaussian Processes

Marcello Zago (University of Tübingen)

Spatial transcriptomics is an emerging field enabling the study of gene expression within its spatial tissue context, offering critical insights into cellular function and organization. Incorporating spatial information is essential for accurate biological hypothesis generation, as it provides context often lost in traditional single-cell analyses. A key challenge in this area is the inference...

7. Towards Reliable AI: Applications of Uncertainty Quantification in Deep Learning

As deep learning systems are increasingly deployed in high-stakes domains such as medical diagnostics, climate modeling, and autonomous decision-making, their ability to express uncertainty in their predictions becomes crucial. Traditional neural networks, while powerful, often produce overconfident predictions, even when presented with out-of-distribution data, that are different from the...