collaborators

6 papers

cs.LG2025

Quantum Doubly Stochastic Transformers

Jannis Born, Filip Skogh, Kahn Rhrissorrakrai +3

At the core of the Transformer, the softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often de-stabilizes training and that enfo…

q-bio.TO2025

COVID-BLUeS -- A Prospective Study on the Value of AI in Lung Ultrasound Analysis

Nina Wiedemann, Dianne de Korte-de Boer, Matthias Richter +10

As a lightweight and non-invasive imaging technique, lung ultrasound (LUS) has gained importance for assessing lung pathologies. The use of Artificial intelligence (AI) in medical…

cs.CL2025

Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models

Jonas Zausinger, Lars Pennig, Anamarija Kozina +13

While language models have exceptional capabilities at text generation, they lack a natural inductive bias for emitting numbers and thus struggle in tasks involving quantitative re…

cs.LG2025

Towards generalizable single-cell perturbation modeling via the Conditional Monge Gap

Alice Driessen, Benedek Harsanyi, Marianna Rapsomaniki +1

Learning the response of single-cells to various treatments offers great potential to enable targeted therapies. In this context, neural optimal transport (OT) has emerged as a pri…

cs.AI2025

We Need Improved Data Curation and Attribution in AI for Scientific Discovery

Mara Graziani, Antonio Foncubierta, Dimitrios Christofidellis +5

As the interplay between human-generated and synthetic data evolves, new challenges arise in scientific discovery concerning the integrity of the data and the stability of the mode…

cs.CL2025

Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling

Eric Egli, Matteo Manica, Jannis Born

Bytes form the basis of the digital world and thus are a promising building block for multimodal foundation models. Recently, Byte Language Models (BLMs) have emerged to overcome t…