- Physical Review Journals
All JournalsPhysics Magazine

PRX Intelligence

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

OmniCosmos: Transferring Particle Physics Knowledge Across the Cosmos

Vinicius Mikuni1,*, Ibrahim Elsharkawy2,3,†, and Benjamin Nachman4,5,‡

  • *Contact author: vmikuni@hepl.phys.nagoya-u.ac.jp
  • †Contact author: ibrahim.elsharkawy@mail.utoronto.ca
  • ‡Contact author: nachman@stanford.edu
PDF

PRX Intelligence 1, 023004 – Published 15 October, 2026

DOI: https://doi.org/10.1103/85gr-9vw6

Abstract

Foundation models build an effective representation of data that can be deployed on diverse downstream tasks. Previous research showed that the OmniLearned, 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 CosmoBench. To the best of our knowledge, this is the first time a collider physics model has been shown to generalize across scientific fields.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (78)

  1. F. Leclercq, Field-level inference in cosmology, in Les Houches Summer School 2025: The Dark Universe, arXiv:2509.13435.
  2. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, in Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS'17 (Curran Associates Inc., Red Hook, NY, 2017), pp. 6000–6010.
  3. V. Mikuni and B. Nachman, Solving key challenges in collider physics with foundation models, Phys. Rev. D 111, L051504 (2025).
  4. V. Mikuni and B. Nachman, Method to simultaneously facilitate all jet physics tasks, Phys. Rev. D 111, 054015 (2025).
  5. W. Bhimji, C. Harris, V. Mikuni, and B. Nachman, Foundation model framework for all tasks involving jet physics, Phys. Rev. D 113, 032020 (2026).
  6. N. Huang, R. Stiskalek, J.-Y. Lee, A. E. Bayer, C. C. Margossian, C. K. Jespersen, L. A. Perez, L. K. Saul, and F. Villaescusa-Navarro, CosmoBench: A multiscale, multiview, multitask cosmology benchmark for geometric deep learning, arXiv:2507.03707.
  7. It will be interesting to study how the results change with finer granularity/higher multiplicity cosmological simulations.
  8. It may be interesting to explore connections between pretrained collider models trained using parton shower histories for such tasks in the future.
  9. M. Feickert and B. Nachman, A living review of machine learning for particle physics, arXiv:2102.02770.
  10. J. Birk, A. Hallin, and G. Kasieczka, OmniJet-α: The first cross-task foundation model for particle physics, Mach. Learn.: Sci. Technol. 5, 035031 (2024).
  11. A. Hallin, Foundation models for high-energy physics, in 2nd European AI for Fundamental Physics Conference, arXiv:2509.21434.
  12. P. Harris, M. Kagan, J. Krupa, B. Maier, and N. Woodward, Resimulation-based self-supervised learning for pretraining physics foundation models, Phys. Rev. D 111, 032010 (2025).
  13. T. Golling, L. Heinrich, M. Kagan, S. Klein, M. Leigh, M. Osadchy, and J. A. Raine, Masked particle modeling on sets: Towards self-supervised high energy physics foundation models, Mach. Learn.: Sci. Technol. 5, 035074 (2024).
  14. M. Leigh, S. Klein, F. Charton, T. Golling, L. Heinrich, M. Kagan, I. Ochoa, and M. Osadchy, Is tokenization needed for masked particle modelling? arXiv:2409.12589.
  15. J. Bardhan, R. Agrawal, A. Tilak, C. Neeraj, and S. Mitra, HEP-JEPA: A foundation model for collider physics using joint embedding predictive architecture, arXiv:2502.03933.
  16. S. Ravanbakhsh, J. Oliva, S. Fromenteau, L. Price, S. Ho, J. Schneider, and B. Poczos, Estimating cosmological parameters from the dark matter distribution, in Proceedings of the 33rd International Conference on Machine Learning, edited by M. F. Balcan and K. Q. Weinberger (PMLR, New York, 2016), Vol. 48, pp. 2407–2416.
  17. T. L. Makinen, T. Charnock, P. Lemos, N. Porqueres, A. Heavens, and B. D. Wandelt, The Cosmic Graph: Optimal information extraction from large-scale structure using catalogues, Open J. Astrophys. 5 (2022).
  18. P. Villanueva-Domingo and F. Villaescusa-Navarro, Learning cosmology and clustering with cosmic graphs, Astrophys. J. 937, 115 (2022).
  19. N. S. M. de Santi et al., Robust field-level likelihood-free inference with galaxies, Astrophys. J. 952, 69 (2023).
  20. A. Roncoli, A. Ćiprijanović, M. Voetberg, F. Villaescusa-Navarro, and B. Nord, Domain adaptive graph neural networks for constraining cosmological parameters across multiple data sets, in Proceedings of the 37th Conference on Neural Information Processing Systems, arXiv:2311.01588.
  21. E. Massara, F. Villaescusa-Navarro, and W. J. Percival, Predicting interloper fraction with graph neural networks, J. Cosmol. Astropart. Phys. 12 (2023) 012.
  22. H. Shao et al., Robust field-level inference of cosmological parameters with dark matter halos, Astrophys. J. 944, 27 (2023).
  23. C. Cuesta-Lazaro and S. Mishra-Sharma, Point cloud approach to generative modeling for galaxy surveys at the field level, Phys. Rev. D 109, 123531 (2024).
  24. C. K. Jespersen, M. Cranmer, P. Melchior, S. Ho, R. S. Somerville, and A. Gabrielpillai, Mangrove: Learning galaxy properties from merger trees, Astrophys. J. 941, 7 (2022).
  25. J. F. Wu and C. K. Jespersen, Learning the galaxy-environment connection with graph neural networks, in Proceedings of the 40th International Conference on Machine Learning, arXiv:2306.12327.
  26. C.-Y. Chuang, C. K. Jespersen, Y.-T. Lin, S. Ho, and S. Genel, Leaving no branches behind: Predicting baryonic properties of galaxies from merger trees, Astrophys. J. 965, 101 (2024).
  27. J. F. Wu, C. K. Jespersen, and R. H. Wechsler, How the galaxy–halo connection depends on large-scale environment, Astrophys. J. 976, 37 (2024).
  28. T. Nguyen et al., How DREAMS are made: Emulating satellite galaxy and subhalo populations with diffusion models and point clouds, Astrophys. J. 997, 336 (2026).
  29. P. Villanueva-Domingo, F. Villaescusa-Navarro, D. Anglés-Alcázar, S. Genel, F. Marinacci, D. N. Spergel, L. Hernquist, M. Vogelsberger, R. Dave, and D. Narayanan, Inferring halo masses with graph neural networks, Astrophys. J. 935, 30 (2022).
  30. M. Cranmer, P. Melchior, and B. Nord, Unsupervised resource allocation with graph neural networks, in Proceedings of the 34th Conference on Neural Information Processing Systems (PMLR, 2021).
  31. T. Wang and P. Melchior, Graph neural network-based resource allocation strategies for multi-object spectroscopy, Mach. Learn.: Sci. Technol. 3, 015023 (2022).
  32. J. W. Park, S. Birrer, M. Ueland, M. Cranmer, A. Agnello, S. Wagner-Carena, P. J. Marshall, and A. Roodman (LSST Dark Energy Science), Hierarchical inference of the lensing convergence from photometric catalogs with Bayesian graph neural networks, Astrophys. J. 953, 178 (2023).
  33. A. Chatterjee and F. Villaescusa-Navarro, Cosmology from point clouds with dark matter halos from the Quijote simulations, Astrophys. J. 985, 132 (2025).
  34. J. Balla, S. Mishra-Sharma, C. Cuesta-Lazaro, T. Jaakkola, and T. Smidt, A cosmic-scale benchmark for symmetry-preserving data processing, in The 3rd Learning on Graphs Conference, arXiv:2410.20516.
  35. V. Krishnaraj, A. E. Bayer, C. K. Jespersen, and P. Melchior, Transfer learning beyond the Standard Model, J. Cosmol. Astropart. Phys. 06 (2026) 026.
  36. N. Perraudin, M. Defferrard, T. Kacprzak, and R. Sgier, DeepSphere: Efficient spherical convolutional neural network with HEALPix sampling for cosmological applications, Astron. Comput. 27, 130 (2019).
  37. M. Defferrard, N. Perraudin, T. Kacprzak, and R. Sgier, DeepSphere: Towards an equivariant graph-based spherical CNN, in ICLR Workshop on Representation Learning on Graphs and Manifolds (ICLR, 2019).
  38. T. S. Cohen, M. Geiger, J. Koehler, and M. Welling, Spherical CNNs, Proceedings of the International Conference on Learning Representations (ICLR, 2018).
  39. J. Ocampo, M. A. Price, and J. D. McEwen, Scalable and equivariant spherical CNNs by discrete-continuous (DISCO) convolutions, in International Conference on Learning Representations (ICLR, 2023).
  40. C. Esteves, A. Makadia, and K. Daniilidis, Spin-weighted spherical CNNs, in Advances in Neural Information Processing Systems, edited by H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin (Curran Associates, Inc., Red Hook, NY, 2020), Vol. 33, pp. 8614–8625.
  41. N. Krachmalnicoff and M. Tomasi, Convolutional neural networks on the HEALPix sphere: A pixel-based algorithm and its application to CMB data analysis, Astron. Astrophys. 628, A129 (2019).
  42. J. A. P. Castro, H. J. Hortúa, J. E. García-Farieta, and R. A. Hurtado, Bayesian inference of primordial magnetic field parameters from CMB with spherical graph neural networks, Universe 12, 34 (2026).
  43. B. Dai and U. Seljak, Translation and rotation equivariant normalizing flow (TRENF) for optimal cosmological analysis, Mon. Not. R. Astron. Soc. 516, 2363 (2022).
  44. Y. Jagvaral, F. Lanusse, and R. Mandelbaum, Geometric deep learning for galaxy-halo connection: A case study for galaxy intrinsic alignments, Mon. Not. R. Astron. Soc. 542, 2560 (2025).
  45. D.-A. Onutu, Y. Zhao, J. Vanschoren, and V. Menkovski, Score matching on large geometric graphs for cosmology generation, arXiv:2508.16990.
  46. L. Thiele, M. Cranmer, W. Coulton, S. Ho, and D. N. Spergel, Predicting the thermal Sunyaev–Zel’dovich field using modular and equivariant set-based neural networks, Mach. Learn.: Sci. Technol. 3, 035002 (2022).
  47. K. Minartz, Y. Poels, S. M. Koop, and V. Menkovski, Equivariant neural simulators for stochastic spatiotemporal dynamics, in Proceedings of the 37th Conference on Neural Information Processing Systems (NIPS, CA, 2023).
  48. S. Villar, D. W. Hogg, K. Storey-Fisher, W. Yao, and B. Blum-Smith, Scalars are universal: Equivariant machine learning, structured like classical physics, in Advances in Neural Information Processing Systems, edited by M. Ranzato, A. Beygelzimer, Y. Dauphin, P. Liang, and J. W. Vaughan (Curran Associates, Inc., Red Hook, NY, 2021), Vol. 34, pp. 28848–28863.
  49. M. de los Rios, S. Di Gioia, F. Iocco, and R. Trotta, Dark matter profiles of insilico galaxies: Deep learning inference, J. Cosmol. Astropart. Phys. 05 (2026) 094.
  50. M. Weiler, M. Geiger, M. Welling, W. Boomsma, and T. Cohen, 3D steerable CNNs: Learning rotationally equivariant features in volumetric data, in Advances in Neural Information Processing Systems, edited by S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Curran Associates, Inc., Red Hook, NY, 2018), Vol. 31.
  51. J. E. Gerken, J. Aronsson, O. Carlsson, H. Linander, F. Ohlsson, C. Petersson, and D. Persson, Geometric deep learning and equivariant neural networks, Artif. Intell. Rev. 56, 14605 (2023).
  52. B. Xia, N. Ramachandra, A. I. Wells, S. Habib, and J. Wise, Multi-modal foundation model for cosmological simulation data, arXiv:2510.07684.
  53. L. Parker, F. Lanusse, S. Golkar, L. Sarra, M. Cranmer, A. Bietti, M. Eickenberg, G. Krawezik, M. McCabe, R. Morel, R. Ohana, M. Pettee, B. Régaldo-Saint Blancard, K. Cho, and S. A. Ho, AstroCLIP: A cross-modal foundation model for galaxies, Mon. Not. R. Astron. Soc. 531, 4990 (2024).
  54. L. Parker et al., AION-1: Omnimodal foundation model for astronomical sciences, in The 39th Annual Conference on Neural Information Processing Systems (NIPS, 2025).
  55. H. W. Leung and J. Bovy, Towards an astronomical foundation model for stars with a transformer-based model, Mon. Not. R. Astron. Soc. 527, 1494 (2023).
  56. T. D. Nguyen et al., AstroLLaMA: Towards specialized foundation models in astronomy, arXiv:2309.06126.
  57. M. Walmsley, I. V. Slijepcevic, M. Bowles, and A. M. M. Scaife, Towards galaxy foundation models with hybrid contrastive learning, arXiv:2206.11927.
  58. M. Walmsley et al., Scaling laws for galaxy images, arXiv:2404.02973.
  59. R. Chakkappai et al., Fair universe Higgs uncertainty challenge, arXiv:2509.22247.
  60. FAIR Universe Collaboration, FAIR Universe—Weak lensing ML uncertainty challenge: Competition overview, neurIPS 2025 Machine Learning Competition, 2025, https://fair-universe.lbl.gov/tutorials/WL_Competition_Overview.pdf.
  61. A. J. Larkoski, I. Moult, and B. Nachman, Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning, Phys. Rep. 841, 1 (2020).
  62. A. Butter et al., How to GAN LHC events, SciPost Phys. 7, 075 (2019).
  63. L. de Oliveira, M. Kagan, L. Mackey, B. Nachman, and A. Schwartzman, Jet-images—Deep learning edition, J. High Energy Phys. 07 (2016) 069.
  64. D. Guest, J. Collado, P. Baldi, S.-C. Hsu, G. Urban, and D. Whiteson, Jet flavor classification in high-energy physics with deep neural networks, Phys. Rev. D 94, 112002 (2016).
  65. I. Henrion, J. Brehmer, J. Bruna, K. Cho, K. Cranmer, G. Louppe, and G. Rochette, Neural message passing for jet physics, in Proceedings of the Deep Learning for Physical Sciences (DLPS 2017) (NIPS, Long Beach, CA, 2017).
  66. H. Qu and L. Gouskos, Jet tagging via particle clouds, Phys. Rev. D 101, 056019 (2020).
  67. L. de Oliveira, M. Paganini, and B. Nachman, Learning particle physics by example: Location-aware generative adversarial networks for physics synthesis, Comput. Software Big Sci. 1, 4 (2017).
  68. P. T. Komiske, E. M. Metodiev, and J. Thaler, Energy flow networks: Deep sets for particle jets, J. High Energy Phys. 01 (2019) 121.
  69. V. Mikuni and F. Canelli, ABCNet: An attention-based method for particle tagging, Eur. Phys. J. Plus 135, 463 (2020).
  70. V. Mikuni and F. Canelli, Point cloud transformers applied to collider physics, Mach. Learn.: Sci. Technol. 2, 035027 (2021).
  71. H. Qu, C. Li, and S. Qian, Particle transformer for jet tagging, arXiv:2202.03772.
  72. Y. Wu, K. Wang, C. Li, H. Qu, and J. Zhu, Jet tagging with more-interaction particle transformer, Chin. Phys. C 49, 013110 (2025).
  73. J. Brehmer, V. Bresó, P. de Haan, T. Plehn, H. Qu, J. Spinner, and J. Thaler, A Lorentz-equivariant transformer for all of the LHC, SciPost Phys. 19, 108 (2025).
  74. F. Villaescusa-Navarro et al., The Quijote simulations, Astrophys. J. Suppl. Ser. 250, 2 (2020).
  75. L. A. Perez, S. Genel, F. Villaescusa-Navarro, R. S. Somerville, A. Gabrielpillai, D. Anglés-Alcázar, B. D. Wandelt, and L. Y. A. Yung, Constraining cosmology with machine learning and galaxy clustering: The CAMELS-SAM suite, Astrophys. J. 954, 11 (2023).
  76. E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, LoRA: Low-rank adaptation of large language models, arXiv:2106.09685.
  77. Q. Sun, E. Cetin, and Y. Tang, Transformer-squared: Self-adaptive LLMs, arXiv:2501.06252.
  78. https://github.com/ViniciusMikuni/OmniLearned.

Outline

Information

PRX Intelligence 1, 023004– Published 15 October, 2026
  • Received 3 May 2026
  • Accepted 24 August 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation