Professor & IEEE Fellow · Northeastern University London
I work at the intersection of information theory, machine learning, and quantum information processing. My group develops principled methods for reliable and efficient communication, computing, and learning systems — from Bayesian learning and neuromorphic computing to quantum machine learning and conformal prediction.
Postdoctoral Research Associate in Reliable Neuromorphic, Classical, and Quantum AI at Northeastern University London.
Classical and Quantum Information Theory published by Cambridge University Press.
Spotlight paper (top 3.1%) at NeurIPS 2025 on adaptive prediction-powered evaluation.
Fundamental limits for communication and learning systems.
Quantum machine learning, communication, and information-theoretic aspects of quantum computing.
Bayesian learning, conformal prediction, meta-learning, and principled approaches to uncertainty.
Spiking neural networks and brain-inspired architectures for efficient learning and inference.
Conformal calibration and AI-native wireless design.
I am always looking for motivated PhD students and postdoctoral researchers with interests in information theory, machine learning, quantum computing, or wireless systems. If you are interested, please get in touch with a CV and a brief description of your research interests.
Get in touch
