Reconstructing hadronically decaying tau leptons with a jet foundation model
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 specifi...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SciPost
2025-07-01
|
| Series: | SciPost Physics Core |
| Online Access: | https://scipost.org/SciPostPhysCore.8.3.046 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849421410332573696 |
|---|---|
| author | Laurits Tani, Joosep Pata, Joschka Birk |
| author_facet | Laurits Tani, Joosep Pata, Joschka Birk |
| author_sort | Laurits Tani, Joosep Pata, Joschka Birk |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-e21c94bbb88b40a8be3d5b8ad06ece75 |
| institution | Kabale University |
| issn | 2666-9366 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | SciPost |
| record_format | Article |
| series | SciPost Physics Core |
| spelling | doaj-art-e21c94bbb88b40a8be3d5b8ad06ece752025-08-20T03:31:27ZengSciPostSciPost Physics Core2666-93662025-07-018304610.21468/SciPostPhysCore.8.3.046Reconstructing hadronically decaying tau leptons with a jet foundation modelLaurits Tani, Joosep Pata, Joschka BirkThe 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.https://scipost.org/SciPostPhysCore.8.3.046 |
| spellingShingle | Laurits Tani, Joosep Pata, Joschka Birk Reconstructing hadronically decaying tau leptons with a jet foundation model SciPost Physics Core |
| title | Reconstructing hadronically decaying tau leptons with a jet foundation model |
| title_full | Reconstructing hadronically decaying tau leptons with a jet foundation model |
| title_fullStr | Reconstructing hadronically decaying tau leptons with a jet foundation model |
| title_full_unstemmed | Reconstructing hadronically decaying tau leptons with a jet foundation model |
| title_short | Reconstructing hadronically decaying tau leptons with a jet foundation model |
| title_sort | reconstructing hadronically decaying tau leptons with a jet foundation model |
| url | https://scipost.org/SciPostPhysCore.8.3.046 |
| work_keys_str_mv | AT lauritstanijooseppatajoschkabirk reconstructinghadronicallydecayingtauleptonswithajetfoundationmodel |