Metraipolis › archive › dc_cd4735ee37bc

Gestalt: a meta-foundation model for astronomy — arXiv:2609.38312

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38312
License (as archived): CC0-1.0
Archived: 2026-10-07T13:47:09.031Z
SHA-256 of the archived text: ac8760198048b78dfe3c57feb8cf4a8eb5c9c1e354bdb4c833e0240cd0a6b09c
Stable URL of this page: https://metraipolis.com/documento/dc_cd4735ee37bc

How to cite

Gestalt: a meta-foundation model for astronomy — arXiv:2609.38312 — arXiv (en), https://arxiv.org/abs/2609.38312 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd4735ee37bc (Metraipolis archive dc_cd4735ee37bc, sha256 ac8760198048b78dfe3c57feb8cf4a8eb5c9c1e354bdb4c833e0240cd0a6b09c)

BibTeX

@misc{dccd4735ee37bc,
  title = {Gestalt: a meta-foundation model for astronomy — arXiv:2609.38312},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38312},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd4735ee37bc; sha256 ac8760198048b78dfe3c57feb8cf4a8eb5c9c1e354bdb4c833e0240cd0a6b09c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38312. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Platonic Representation Hypothesis predicts that sufficiently scaled foundation models converge on a shared representation of the world. As each non-converged model gives a noisy view of a common structure when passed the same input, we ask whether we can combine models into a representation that outperforms its individual components. We test this on galaxies: we embed images via a basket of 22 frozen foundation models from eight families, whiten each view, and take a randomised SVD of the embedding concatenation. The resulting 1024-dimensional embedding outperforms every basket member on 19/21 of our tested metrics for physical property and galaxy morphology estimation for HSC, JWST, and DESI Legacy Survey imagery. We find that performance rises with basket size and basket architectural diversity, and that the meta-foundation model's performance transfers across astronomical surveys. We conclude that a useful astronomical foundation model can be assembled from existing generalist models with no training required beyond a single unsupervised projection. By leveraging the community's already-spent work, we save a lot of compute: a fresh pre-train of a comparable single-domain model would cost $\mathcal{O}(10^{4}$--$10^{5})$ A100 GPU hours (emitting several tonnes of CO$_2$eq.), whereas assembling Gestalt requires minutes on a single machine.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Instrumentation and Methods for Astrophysics (astro-ph.IM) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.38312 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T13:18:10.553Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).