In this seminar, I will introduce the Lund jet plane, a powerful representation of the radiation patterns within a jet, and adopt this framework to explore a range of recent machine learning methods of particular relevance for LHC physics. Drawing on methods inspired from generative models, computer vision, reinforcement learning, and graph neural networks, I will show how to tackle important collider physics problems in novel ways. I will focus on three concrete issues: fast event simulations with detector reconstruction effects; the removal of background radiation in proton-proton events; and the identification of boosted heavy particles at the TeV scale. Through creative approaches to these problems, I will show how recent advances in machine learning can be harnessed to improve the performance on key benchmarks.
