17–23 Aug 2025
California Institute of Technology
US/Pacific timezone

HEP-JEPA: Towards a found model for high energy physics using joint embedding predictive architecture [Remote]

21 Aug 2025, 11:40
20m
Chen 100

Chen 100

Chen Neuroscience Research Building

Speaker

Jai Bardhan

Description

We present HEP-JEPA, a transformer architecture-based foundation model for tasks at high-energy particle colliders such as the Large Hadron Collider. We pre-train the model on particle jets using a self-supervised strategy inspired by the Joint Embedding Predictive Architecture on the large-scale JetClass dataset containing 100M jets. We evaluate and compare HEP-JEPA to other foundation models on several downstream tasks, such as jet classification and jet observable prediction. HEP-JEPA outperforms or matches the performance of contemporary approaches on these benchmarks.

Authors

Jai Bardhan Abhiram Tilak Radhikesh Agrawal Cyrin Neeraj Subhadip Mitra

Presentation materials