Martin Schrimpf

Martin Schrimpf is a Tenure-Track Assistant Professor at EPFL where he builds artificial intelligence models of the brain. To achieve this goal, he bridges research in Machine Learning, Neuroscience, and Cognitive Science. He initiated the community-wide Brain-Score platform for evaluating models on their brain and behavioral alignment, and built state-of-the-art models such as CORnet and VOneNet. Martin completed his PhD at MIT with Jim DiCarlo, following Bachelor’s and Master’s degrees in computer science at TUM, LMU, and UNA. Previously he worked at Harvard, MetaMind/Salesforce, Oracle, and co-founded two startups. Among others, his work has been recognized in the news at Science magazine, Scientific American, and BBC; and with awards such as the Neuro-Irv and Helga Cooper Open Science Prize, the Google.org Impact Challenge prize, and the Takeda fellowship in AI + Health.

AI2050 Project

Schrimpf’s project aims to build next-generation brain models that simulate how we transform what we see into meaning. By combining large-scale brain recordings with cutting-edge artificial intelligence, they seek to understand how the brain integrates sensory information into language and thought—and how this process breaks down in disorders like dyslexia. Their models will not only offer new insights into the brain’s inner workings but also open up possibilities for predicting the effects of treatments and developing more effective interventions. The long-term vision is to create virtual brain models that support both scientific discovery and clinical applications.