arXiv Open Access 2025

Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series

Martina Cádiz-Leyton Guillermo Cabrera-Vives Pavlos Protopapas Daniel Moreno-Cartagena Ignacio Becker

Lihat Sumber

Abstrak

Multiband astronomical time series exhibit heterogeneous variability patterns, sampling cadences, and signal characteristics across bands. Standard transformers apply shared parameters to all bands, potentially limiting their ability to model this rich structure. In this work, we introduce Astro-MoE, a foundational transformer architecture that enables dynamic processing via a Mixture of Experts module. We validate our model on both simulated (ELAsTiCC-1) and real-world datasets (Pan-STARRS1).

Topik & Kata Kunci

astro-ph.IM

Penulis (5)

Martina Cádiz-Leyton

Guillermo Cabrera-Vives

Pavlos Protopapas

Daniel Moreno-Cartagena

Ignacio Becker

Format Sitasi

APA MLA BibTeX

Cádiz-Leyton, M., Cabrera-Vives, G., Protopapas, P., Moreno-Cartagena, D., Becker, I. (2025). Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series. https://arxiv.org/abs/2507.12611

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓