Machine-learned particle flow as a foundation model for collider physics
Abstract
The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks. We show that casting event reconstruction as a machine learning problem naturally produces such a shared representation. We repurpose a machine learning model trained for particle-flow reconstruction (MLPF) to perform three distinct analysis tasks: jet flavor identification, jet energy regression, and missing momentum regression. By appending the per-particle latent representations learned during reconstruction as additional input features, we substantially improve over baselines that use conventional particle-level features alone. We further demonstrate that a single linear layer trained using only the latent representations achieves competitive performance against state-of-the-art baseline architectures, and outperforms the baseline for missing momentum regression with approximately 35 times fewer parameters. These results demonstrate that the latent representations learned during reconstruction encode essential physics information needed for downstream analysis, establishing MLPF as a foundation model and offering a concrete step toward an end-to-end pipeline from detector data to physics analysis.
Versions
Related
- Fast and Precise Learned Charged-Particle Trajectory Regression at the Large Hadron Collider
- Track finding and particle identification performance with particle physics foundation models
- Leveraging Industrial Foundation Models at the Edge of Particle Physics Detectors via Distillation Learning and Hardware Co-design
- Panda Diplomacy: Foundation Model Pre-training across Particle Imaging Detectors for High Energy and Nuclear Physics
- Towards Foundation Models on Hardware Accelerators for Particle Physics
BibTeX
@misc{mokhtar2026machinelearned,
title = {{Machine-learned particle flow as a foundation model for collider physics}},
author = {Farouk Mokhtar and Joosep Pata and Michael Kagan and Javier Duarte},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2606.14373},
eprint = {2606.14373},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.14373},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Machine-learned particle flow as a foundation model for collider physics
AU - Farouk Mokhtar
AU - Joosep Pata
AU - Michael Kagan
AU - Javier Duarte
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2606.14373
UR - https://arxiv.org/abs/2606.14373
AB - The workflow from particle collision to physics analysis passes through a series of reconstruction steps that are traditionally modular and disconnected, with no shared representation linking low-level detector data to high-level analysis tasks. We show that casting event reconstruction as a machine learning problem naturally produces such a shared representation. We repurpose a machine learning model trained for particle-flow reconstruction (MLPF) to perform three distinct analysis tasks: jet flavor identification, jet energy regression, and missing momentum regression. By appending the per-particle latent representations learned during reconstruction as additional input features, we substantially improve over baselines that use conventional particle-level features alone. We further demonstrate that a single linear layer trained using only the latent representations achieves competitive performance against state-of-the-art baseline architectures, and outperforms the baseline for missing momentum regression with approximately 35 times fewer parameters. These results demonstrate that the latent representations learned during reconstruction encode essential physics information needed for downstream analysis, establishing MLPF as a foundation model and offering a concrete step toward an end-to-end pipeline from detector data to physics analysis.
ER -