Jul 21 – 23, 2025
Europe/Berlin timezone

Session

Young Scientists Talks: Session 7

Jul 23, 2025, 2:00 PM

Conveners

Young Scientists Talks: Session 7

  • Ayodele Ore

Presentation materials

There are no materials yet.

  1. Humberto Reyes-Gonzalez (RWTH Aachen)
    7/23/25, 2:00 PM

    Jets are ubiquitous observables in collider experiments, composed of complex collections of particles that require classification. Over the past decade, machine learning-based classifiers have significantly enhanced our jet tagging capabilities, with increasingly sophisticated models leading to further improvements. This raises a fundamental question: How close are we to the theoretical limit...

    Go to contribution page
  2. Daniel Schiller (Institute for Theoretical Physics, Heidelberg University)
    7/23/25, 2:20 PM

    Foundation models are a very successful approach to linguistic tasks. Naturally, there is the desire to develop foundation models for physics data. Currently, existing networks are much smaller than publicly available Large Language Models (LLMs), the latter having typically billions of parameters. By applying pretrained LLMs in an unconventional way, we introduce large networks for cosmological data.

    Go to contribution page
  3. Sophia Vent
    7/23/25, 2:40 PM

    Established Machine learning taggers are a perfect challenge for explainability concepts in a fundamental physics context. For the theoretically challenging quark-gluon tagging, we first identify a small set of learned latent features that correlate strongly with physics observables. Then we use symbolic regression to derive compact analytic expressions to approximate the tagger in terms of...

    Go to contribution page
Building timetable...