Speaker
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 |
|---|