English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose masked particle modeling (MPM) as a self-supervised method forlearning generic, transferable, and reusable representations on unordered setsof inputs for use in high energy physics (HEP) scientific data. This workprovides a novel scheme to perform masked modeling based pre-training to learnpermutation invariant functions on sets. More generally, this work provides astep towards building large foundation models for HEP that can be genericallypre-trained with self-supervised learning and later fine-tuned for a variety ofdown-stream tasks. In MPM, particles in a set are masked and the trainingobjective is to recover their identity, as defined by a discretized tokenrepresentation of a pre-trained vector quantized variational autoencoder. Westudy the efficacy of the method in samples of high energy jets at colliderphysics experiments, including studies on the impact of discretization,permutation invariance, and ordering. We also study the fine-tuning capabilityof the model, showing that it can be adapted to tasks such as supervised andweakly supervised jet classification, and that the model can transferefficiently with small fine-tuning data sets to new classes and new datadomains.

Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models