collaborators

17 papers

cs.CV2026

The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography

Kaiyuan Yang, Fabio Musio, Yihui Ma +112

The paper introduces the TopCoW Challenge, a benchmark for automatically segmenting the Circle of Willis in CT and MR angiography using deep learning, and provides a new annotated…

cs.LG2026

Efficient numeracy in language models through single-token number embeddings

Linus Kreitner, Paul Hager, Jonathan Mengedoht +3

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is…

cs.CL2026

Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting

Alexander Weers, Daniel Rueckert, Martin J. Menten

Training vision-language models (VLMs) for medical report generation is often hindered by the scarcity of high-quality annotated data. This work evaluates the use of a weighted los…

cs.LG2026

On Arbitrary Predictions from Equally Valid Models

Sarah Lockfisch, Kristian Schwethelm, Martin Menten +4

Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In m…

cs.LG2026

Step-resolved data attribution for looped transformers

Georgios Kaissis, David Mildenberger, Juan Felipe Gomez +2

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for recurrent iterations to enable latent reas…

cs.LG2025

Stochastic Siamese MAE Pretraining for Longitudinal Medical Images

Taha Emre, Arunava Chakravarty, Thomas Pinetz +9

Temporally aware image representations are crucial for capturing disease progression in 3D volumes of longitudinal medical datasets. However, recent state-of-the-art self-supervise…