Speaker
Zixun Kou
(Peking University)
Description
A foundation jet model aims to achieve optimal performance across all jet analysis tasks while ensuring strong generalization. Building on Sophon, a pre-trained jet classification model, we develop Sophon++, which employs contrastive learning to connect initial, parton-level, and reconstruction-level particles, enabling continuous encoding of generator-level particle configurations into the model’s latent space. While matching Sophon in classification performance, Sophon++ demonstrates stronger generalization through several fine-tuning tasks. This work provides a promising pathway towards a foundation jet model for analysis.
Primary authors
Zixun Kou
(Peking University)
Congqiao Li
(Peking University)
Qiang Li
(School of physics, Peking University)
