9 papers
AGNFormer I: Reconstruction of AGN spectra using a probabilistic transformer model
Benedict L. Rouse, Franz E. Bauer, Tomasz RóżaÅski +8
We explore how an uncertainty-aware transformer-based architecture can leverage information embedded across the entire observed optical spectra of AGN, focusing on the algorithm's…
Querying an astronomical database using large language models: the ALeRCE text-to-SQL system
P. A. Estevez, J. Espejo-Moreira, S. Sanfeliu-Alvarez +10
We develop a text-to-SQL (structured query language) system based on large language models (LLMs) using in-context learning and apply it to the Automatic Learning for the Rapid Cla…
Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
Daniel Moreno-Cartagena, Pavlos Protopapas, Guillermo Cabrera-Vives +3
This study investigates the potential of a pre-trained vision Transformer (VT) model, specifically the Swin Transformer V2 (SwinV2), to classify photometric light curves without th…
ASTROCO: Self-Supervised Conformer-Style Transformers for Light-Curve Embeddings
Antony Tan, Pavlos Protopapas, Martina Cádiz-Leyton +3
We present AstroCo, a Conformer-style encoder for irregular stellar light curves. By combining attention with depthwise convolutions and gating, AstroCo captures both global depend…
Astro-MoE: Mixture of Experts for Multiband Astronomical Time Series
Martina Cádiz-Leyton, Guillermo Cabrera-Vives, Pavlos Protopapas +2
Multiband astronomical time series exhibit heterogeneous variability patterns, sampling cadences, and signal characteristics across bands. Standard transformers apply shared parame…
Image-Based Multi-Survey Classification of Light Curves with a Pre-Trained Vision Transformer
Daniel Moreno-Cartagena, Guillermo Cabrera-Vives, Alejandra M. Muñoz Arancibia +10
We explore the use of Swin Transformer V2, a pre-trained vision Transformer, for photometric classification in a multi-survey setting by leveraging light curves from the Zwicky Tra…