AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

How to scale your HEP ML models: A recipe for robust architecture comparisons at scale

arXiv · AI, language, vision and robotics · article · Oct 5, 2026 · UTC

Much of the recent progress in machine learning domains such as language models has come from scaling laws that predict performance as a function of training effort. In high-energy physics (HEP) similar behavior has now been observed. To aid further study, we present a systematic procedure to derive robust scaling laws and compare design choices on the relevant budget axes for HEP tasks. We first validate the full scaling trajectory on toy problems and then apply the procedure to multi-task transformers on the ~11 billion-jet ATLAS JetSet2 dataset, in both the compute- and data-constrained reg

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-10-06T12:51:51.560Z. This is not the publication date.