The Michael Spannowsky Lab

Michael Spannowsky’s lab works in theoretical particle physics, with a strong focus on collider phenomenology, jet substructure, effective field theory, and machine learning for high-energy physics. The group develops methods to understand how new physics could appear in data from the Large Hadron Collider and future colliders, especially through precision measurements, resonance distortions, and higher-dimensional operators in SMEFT. A major theme is learning from complex final states: the lab builds physics-informed neural networks, tensor-network autoencoders, and topological or quantum-inspired representations to improve classification, anomaly detection, and event reconstruction in collider data. The group also explores quantum-phase and interferometry ideas for axion searches, and studies how quantum information concepts can help represent particle correlations in a more structured and interpretable way. Students can expect work that combines field theory, collider simulation, statistical inference, and modern machine learning, often with a strong emphasis on interpretability and links back to first-principles theory. The lab is especially suited to students who enjoy theoretical physics, data-driven methods, and using advanced computation to probe fundamental questions about nature.