DrEleonora Giunchiglia

I am a Lecturer in the Department of Electrical and Electronic Engineering at Imperial College London, affiliated with Imperial-X, where I lead the DUCK Lab (Data, Uncertainty, Constraints & Knowledge Lab). My research focuses on neurosymbolic AI and on developing machine learning systems that can satisfy explicit requirements, constraints, and domain knowledge.

My work spans constrained deep generative models, learning with logical and structural requirements, safe synthetic data generation, formal methods for machine learning, and neural approaches to symbolic reasoning. The central goal of my research is to make AI systems more reliable, controllable, and suitable for high-stakes settings where correctness and trustworthiness matter.

Before joining Imperial, I was a postdoctoral researcher at TU Wien. I completed my DPhil at the University of Oxford. My work has been published in leading AI venues including NeurIPS, ICML and ICLR.