24–28 Aug 2026
Kirchhoff Institute for Physics (KIP)
Europe/Berlin timezone

Jet representations transfer across radii: toward foundation models for high-energy physics

26 Aug 2026, 14:40
8m
1.404

1.404

Foundation Models 🔀 Foundation Models

Speaker

Una Alberti (University of Bern)

Description

The high-energy physics pipeline already resembles a multi-modal foundation model: a general-purpose representation built once and reused across downstream tasks - but it lacks scale and differentiability. Already, we are seeing the gains from large-scale pre-training in individual pieces of the ATLAS pipeline, such as jet flavour identification. Flavour taggers, however, are normally trained in isolation - a separate model from scratch for each task such as small-R and large-R classification - leaving the benefits of scale untapped. In this work, using ATLAS simulation, we show that the representations learned by a small-R tagger, pre-trained on billions of jets, transfer to the large-R H→bb tagging task, demonstrating that the tagger learns general jet features that generalise across radii. This goes beyond H→bb: the same transfer that carries across radii motivates a unification of taggers - a step toward the foundation-model view of the high-energy physics pipeline.

Author

Una Alberti (University of Bern)

Co-authors

Alexander Froch (Université de Genève) Dan Guest (Humboldt University of Berlin) Jackson Barr (UCL) Lukas Heinrich (Technical University of Munich) Matthias Vigl (TUM) Michael Kagan (SLAC National Accelerator Laboratory) Nicole Hartman (TUM) Nikita Pond (UCL) Dr Stefano Franchellucci (The University of Bern)

Presentation materials

There are no materials yet.