TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhysCore.8.3.046
TI  - Reconstructing hadronically decaying tau leptons with a jet foundation model
PY  - 2025/07/04
UR  - https://scipost.org/SciPostPhysCore.8.3.046
JF  - SciPost Physics Core
JA  - SciPost Phys. Core
VL  - 8
IS  - 3
SP  - 046
A1  - Tani, Laurits
AU  - Pata, Joosep
AU  - Birk, Joschka
AB  - The limited availability and accuracy of simulated data has motivated the use of foundation models in high energy physics, with the idea to first train a task-agnostic model on large and potentially unlabeled datasets. This enables the subsequent fine-tuning of the learned representation for specific downstream tasks, potentially requiring much smaller datasets to achieve performance comparable to models trained from scratch on larger datasets. We study how OmniJet-$\alpha$, one of the proposed foundation models for particle jets, can be used on a new set of tasks, and on a new dataset, in order to reconstruct hadronically decaying $\tau$ leptons. We show that the pretraining can successfully be utilized for this multi-task problem, improving the resolution of momentum reconstruction by about $50\%$ when the pretrained weights are fine-tuned, compared to training the model from scratch. While much work remains ahead to develop generic foundation models for high-energy physics, this early result of generalizing an existing model to a new dataset and to previously unconsidered tasks highlights the importance of testing the approaches on a diverse set of datasets and tasks.
ER  -

@Article{10.21468/SciPostPhysCore.8.3.046,
	title={{Reconstructing hadronically decaying tau leptons with a jet foundation model}},
	author={Laurits Tani and Joosep Pata and Joschka Birk},
	journal={SciPost Phys. Core},
	volume={8},
	pages={046},
	year={2025},
	publisher={SciPost},
	doi={10.21468/SciPostPhysCore.8.3.046},
	url={https://scipost.org/10.21468/SciPostPhysCore.8.3.046},
}