collaborators

5 papers

cs.LG2026

N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation

Aleksander Lorenc, Frédéric Berdoz, Joël Mathys +1

Improving the inference efficiency of autoregressive transformers typically means reducing FLOPs per token, usually through approximations that degrade model quality. We introduce…

cs.LG2026

From Message-Passing to Linearized Graph Sequence Models

Joël Mathys, Basil Rohner, Saku Peltonen +1

Message-passing based approaches form the default backbone of most learning architectures on graph-structured data. However, the rapid progress of modern deep learning architecture…

cs.LG2025

Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies

Joël Mathys, Federico Errica

Message-passing architectures struggle to sufficiently model long-range dependencies in node and graph prediction tasks. We propose a novel approach exploiting hierarchical graph s…

cs.CV2025

Synthetic Data for Blood Vessel Network Extraction

Joël Mathys, Andreas Plesner, Jorel Elmiger +1

Blood vessel networks in the brain play a crucial role in stroke research, where understanding their topology is essential for analyzing blood flow dynamics. However, extracting de…

cs.LG2025

Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks

Niccolò Grillo, Andrea Toccaceli, Joël Mathys +3

Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable wa…