Dr. Sam Gijsen

Machine Learning Researcher
Representation Learning & Multimodal Modeling
for Biological Time Series

Currently a Postdoctoral Researcher at:

I research multimodal representation learning and build foundation models for neural and physiological time series. Previously, I completed a PhD in Computational Cognitive Neuroscience (Freie Universität Berlin) and worked on pharmaco-imaging at King's College London and Maastricht University.

Dr. Sam Gijsen

GitHub  github LinkedIn  linkedin Google Scholar  scholar

Recent Work


Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics

We propose a per-timestep conditioned diffusion transformer for generating realistic neural time series during unseen experimental tasks by injecting both compositional language and optional spatial priors in-context. Its zero-shot generation can facilitate counterfactual neuroscience by supporting in-silico design and evaluation of novel cognitive experiments before empirical validation. arXiv forthcoming!


[ICLR26] Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model Sam Gijsen, Marc-André Schulz, Kerstin Ritter
Project 2

We develop a self-distilled foundation model for brain dynamics that pretrains in 2 hours and eliminates the need for finetuning. We stabilize self-distillation for noisy time series through learned tokenization, and find log-linear scaling laws for pretraining data on cross-dataset downstream tasks.

ICLR PaperCodePretrained Models


[ICML25] EEG-Language Pretraining for Highly Label-Efficient Clinical Phenotyping Sam Gijsen, Kerstin Ritter
Project 2

First-of-its-kind EEG-language model for downstream clinical tasks. We show a multiple-instance learning extension of the infoNCE loss enables multimodal models which align physiological time series with natural language, yielding more useful representations.

ICML PaperCodePretrained Models


2025 NeurIPS EEG Competition: 7th / 1,183 teams
Project 2

Led a small team that placed highly using a multi-modal fusion architecture designed from scratch, without any pretraining. Code and report to come!

Challenge Link


Some Previous Work


Neural surprise in somatosensory Bayesian learning Sam Gijsen, Miro Grundei, Robert T. Lange, Dirk Ostwald, Felix Blankenburg
Project 2

Computational modeling of neural signals using information-theoretic measures shows perceptual learning can be described as a process of probabilistic inference.

PLOS Computational BiologyCode


Active inference and the two-step task Sam Gijsen, Miro Grundei, Felix Blankenburg
Project 2

We develop active inference models using probabilistic surprise minimization and show these to describe human sequential decision-making better compared to reinforcement learning.

Scientific ReportsCode


Latest Blog post

Project 2

Hillsbrad Diffusion: A World Diffusion Model Criminally Undertrained
A qualitative look at a world diffusion model undertrained on two hours of sparse exploration of a large map.

Blog post