Hello! I’m an FWO PhD Fellow in Brussels studying compositionality as a mathematical foundation for deep learning. I use tensor networks and category theory to ground the analysis of neural representations in the weight geometry of their architecture.
My work proposes tensor models as a unified framework for tractable neuro-symbolic integration and mechanistic analysis. By combining structural constraints and MDL (Minimum Description Length) to disentangle spurious interactions, I aim to enable truly compositional generalisation and interpretability. Learn more here!