collaborators

13 papers

cs.LG2026

Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching

Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis

A main promise of looped language models (LMs) is depth-adaptive inference. By iterating a block of shared layers a variable number of times, the model can use less compute for "ea…

cs.LG2026

Addressing Benchmarking Gaps in Large Language Models for Health and Medicine with Dynamic Red-Teaming

Jiazhen Pan, Bailiang Jian, Paul Hager +19

The paper presents a dynamic red‑teaming framework (DAS) that continuously stress‑tests large language models on health tasks for robustness, privacy, bias, and hallucination, reve…

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.LG2026

Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks

Dmitrii Seletkov, Paul Hager, Georgios Kaissis +3

Survival analysis is crucial for many medical applications, but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular cov…

cs.LG2026

How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models

Kristian Schwethelm, Daniel Rueckert, Georgios Kaissis

We measure how much one recurrence is worth to a looped (depth-recurrent) transformer, in equivalent unique parameters. From an iso-depth pretraining sweep across recurrence counts…

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…