Research Domain

Advancing preference learning, optimisation theory, and scalable human centric AI systems for complex decision environments.

Core Paradigms

We push the boundaries of how intelligent agents model human intent and navigate uncertainty. Our research translates strong theoretical foundations into actionable architectures.

Preference Learning

Structured modelling of human values and trade-offs in complex multi-objective environments.

Optimisation Under Uncertainty

Robust decision frameworks for high-dimensional, partially observed systems.

Human-in-the-Loop Intelligence

Interactive architectures that combine algorithmic precision with expert oversight.

Selected Research Directions