Large Language Models -- the Future of Fundamental Physics?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Heneka, Caroline, Nieser, Florian, Ore, Ayodele, Plehn, Tilman, Schiller, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918374642024448
author Heneka, Caroline
Nieser, Florian
Ore, Ayodele
Plehn, Tilman
Schiller, Daniel
author_facet Heneka, Caroline
Nieser, Florian
Ore, Ayodele
Plehn, Tilman
Schiller, Daniel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14757
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Models -- the Future of Fundamental Physics?
Heneka, Caroline
Nieser, Florian
Ore, Ayodele
Plehn, Tilman
Schiller, Daniel
Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
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.
title Large Language Models -- the Future of Fundamental Physics?
topic Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
High Energy Physics - Phenomenology
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2506.14757