EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

OmniCosmos: Transferring Particle Physics Knowledge Across the Cosmos

Vinicius Mikuni, Ibrahim Elsharkawy, Benjamin Nachman

PRX Intelligence · 2026

DOI: 10.1103/85gr-9vw6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PRX Intelligence, 2026. Verfasst von Vinicius Mikuni und 2 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Agency, Office of Science, U.S. Department of Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foundation models build an effective representation of data that can be deployed on diverse downstream tasks. Previous research showed that the , a foundation model for collider physics, could significantly advance discovery potential across collider experiments. In this paper, we show that foundation models trained on collider data can transfer to cosmology. Specifically, we improve the prediction of cosmological parameters and halo and galaxy velocities in different datasets from . To the best of our knowledge, this is the first time a collider physics model has been shown to generalize across scientific fields.

Förderung

  • Japan Science and Technology Agency
  • Office of Science
  • U.S. Department of Energy
  • National Energy Research Scientific Computing Center

Zitieren

APA

Mikuni, V., Elsharkawy, I., & Nachman, B. (2026). OmniCosmos: Transferring Particle Physics Knowledge Across the Cosmos. PRX Intelligence. https://doi.org/10.1103/85gr-9vw6

Vancouver

Mikuni V, Elsharkawy I, Nachman B. OmniCosmos: Transferring Particle Physics Knowledge Across the Cosmos. PRX Intelligence. 2026. doi:10.1103/85gr-9vw6

BibTeX
@article{Mikuni2026,
  author = {Mikuni, Vinicius and Elsharkawy, Ibrahim and Nachman, Benjamin},
  title = {OmniCosmos: Transferring Particle Physics Knowledge Across the Cosmos},
  journal = {PRX Intelligence},
  year = {2026},
  doi = {10.1103/85gr-9vw6}
}
Kostenlos starten →