The Platonic Universe: Do Foundation Models See the Same Sky?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916965406212096 |
|---|---|
| author | UniverseTBD : Duraphe, Kshitij Smith, Michael J. Sourav, Shashwat Wu, John F. |
| author_facet | UniverseTBD : Duraphe, Kshitij Smith, Michael J. Sourav, Shashwat Wu, John F. |
| contents | We test the Platonic Representation Hypothesis (PRH) in astronomy by measuring representational convergence across a range of foundation models trained on different data types. Using spectroscopic and imaging observations from JWST, HSC, Legacy Survey, and DESI, we compare representations from vision transformers, self-supervised models, and astronomy-specific architectures via mutual $k$-nearest neighbour analysis. We observe consistent scaling: representational alignment generally increases with model capacity across our tested architectures, supporting convergence toward a shared representation of galaxy astrophysics. Our results suggest that astronomical foundation models can use pre-trained general-purpose architectures, allowing us to capitalise on the broader machine learning community's already-spent computational investment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19453 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Platonic Universe: Do Foundation Models See the Same Sky? UniverseTBD : Duraphe, Kshitij Smith, Michael J. Sourav, Shashwat Wu, John F. Instrumentation and Methods for Astrophysics Machine Learning We test the Platonic Representation Hypothesis (PRH) in astronomy by measuring representational convergence across a range of foundation models trained on different data types. Using spectroscopic and imaging observations from JWST, HSC, Legacy Survey, and DESI, we compare representations from vision transformers, self-supervised models, and astronomy-specific architectures via mutual $k$-nearest neighbour analysis. We observe consistent scaling: representational alignment generally increases with model capacity across our tested architectures, supporting convergence toward a shared representation of galaxy astrophysics. Our results suggest that astronomical foundation models can use pre-trained general-purpose architectures, allowing us to capitalise on the broader machine learning community's already-spent computational investment. |
| title | The Platonic Universe: Do Foundation Models See the Same Sky? |
| topic | Instrumentation and Methods for Astrophysics Machine Learning |
| url | https://arxiv.org/abs/2509.19453 |