EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Large language models – the future of fundamental physics?

Caroline Heneka, Florian Nieser, Ayodele Ore, Tilman Plehn, Daniel Schiller

SciPost Physics · 05.03.2026 · 20 (3)

DOI: 10.21468/scipostphys.20.3.070 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SciPost Physics, online erschienen am 05.03.2026. Verfasst von Caroline Heneka und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 148 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Baden-Württemberg Stiftung, Bundesministerium für Bildung und Forschung, Deutsche Forschungsgemeinschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For many fundamental physics applications, transformers, as the state of the art in learning complex correlations, benefit from pretraining on quasi-out-of-domain data. The obvious question is whether we can exploit Large Language Models, requiring proper out-of-domain transfer learning. We show how the Qwen2.5 LLM can be used to analyze and generate SKA data, specifically 3D maps of the cosmological large-scale structure for a large part of the observable Universe. We combine the LLM with connector networks and show, for cosmological parameter regression and lightcone generation, that this Lightcone LLM (L3M) with Qwen2.5 weights outperforms standard initialization and compares favorably with dedicated networks of matching size.

Förderung

  • Baden-Württemberg Stiftung
  • Bundesministerium für Bildung und Forschung
  • Deutsche Forschungsgemeinschaft

Zitieren

APA

Heneka, C., Nieser, F., Ore, A., Plehn, T., & Schiller, D. (2026). Large language models – the future of fundamental physics?. SciPost Physics, 20(3). https://doi.org/10.21468/scipostphys.20.3.070

Vancouver

Heneka C, Nieser F, Ore A, Plehn T, Schiller D. Large language models – the future of fundamental physics?. SciPost Physics. 2026;20(3). doi:10.21468/scipostphys.20.3.070

BibTeX
@article{Heneka2026,
  author = {Heneka, Caroline and Nieser, Florian and Ore, Ayodele and Plehn, Tilman and Schiller, Daniel},
  title = {Large language models – the future of fundamental physics?},
  journal = {SciPost Physics},
  year = {2026},
  volume = {20},
  number = {3},
  doi = {10.21468/scipostphys.20.3.070}
}
Kostenlos starten →