8โ€“12 Sept 2025
Hamburg, Germany
Europe/Berlin timezone

Reconstructing tau leptons with a cross-task, cross-detector foundation model

9 Sept 2025, 14:30
20m
ESA B

ESA B

Oral Track 2: Data Analysis - Algorithms and Tools Track 2: Data Analysis - Algorithms and Tools

Speaker

Laurits Tani (National Institute of Chemical Physics and Biophysics (EE))

Description

The application of foundation models in high-energy physics has recently been proposed as a way to use large unlabeled datasets to efficiently train powerful task-specific models. The aim is to train a task-agnostic model on an existing large dataset such that the learned representation can later be utilized for subsequent downstream physics tasks.
The pretrained model can reduce the training dataset size needed in the fine-tuning phase to reach the same performance as the models trained from scratch. We present the first results of out-of-context and out-of-domain foundation model training for hadronically decaying tau lepton reconstruction and show that the representation learned during pretraining can successfully be utilized for this multi-task reconstruction problem.

Significance

To our knowledge, this is the first case of reusing recently-developed pretrained jet foundation models for hadronic tau reconstruction, demonstrating generalization to a new set of tasks (out-of-context) and to new datasets (out-of-domain).

References

At the date of submission nothing is published yet in a peer-reviewed journal.

Experiment context, if any None

Authors

Joosep Pata (National Institute of Chemical Physics and Biophysics (EE)) Joschka Birk (Hamburg University (DE)) Laurits Tani (National Institute of Chemical Physics and Biophysics (EE))

Presentation materials