Related papers: AstroPT: Scaling Large Observation Models for Astr…
Microlensing of stars in our Galaxy has long been used to detect and characterize stellar populations, exoplanets, brown dwarfs, stellar remnants and whatever objects may magnify the source stars with their gravitational fields. The…
Competitive access to modern observatories has intensified as proposal volumes outpace available telescope time, making timely, consistent, and transparent peer review a critical bottleneck for the advancement of astronomy. Automating parts…
Li-rich giants serve as valuable tracers of stellar evolution and surface enrichment processes, for which a statistically large and homogeneous sample is crucial. Using the massive low-resolution ($R \sim 1800$) spectroscopic dataset from…
StarFinder is a new code for the deep analysis of stellar fields, designed for well-sampled images with high and low Strehl ratio. It is organized in the form of a self-contained IDL widget-based application, with a 'user-friendly' graphic…
Machine learning models in astrophysics are often limited in scope and cannot adapt to data from new instruments or tasks. We introduce SpectraFM, a Transformer-based foundation model architecture that can be pre-trained on stellar spectra…
The Large Synoptic Survey Telescope (LSST) will provide for unbiased sampling of variability properties of objects with $r$ mag $<$ 24. This should allow for those objects whose variations reveal their orbital periods ($P_{orb}$), such as…
As the potential of foundation models in visual tasks has garnered significant attention, pretraining these models before downstream tasks has become a crucial step. The three key factors in pretraining foundation models are the pretraining…
Image restoration in astronomy has been considered a vital step in many ground-based observational programs that often suffer from sub-optimal seeing due to atmospheric turbulence, distortion of stellar shapes due to instrumental…
The semi-analytical model A-SLOTH (Ancient Stars and Local Observables by Tracing Halos) is the first public code that connects the formation of the first stars and galaxies to observables. After several successful projects with this model,…
There is enormous enthusiasm and concerns in using large language models (LLMs) in healthcare, yet current assumptions are all based on general-purpose LLMs such as ChatGPT. This study develops a clinical generative LLM, GatorTronGPT, using…
Astrometric precision and knowledge of the point spread function are key ingredients for a wide range of astrophysical studies including time-delay cosmography in which strongly lensed quasar systems are used to determine the Hubble…
The Large Synoptic Survey Telescope (LSST) will be a discovery machine for the astronomy and physics communities, revealing astrophysical phenomena from the Solar System to the outer reaches of the observable Universe. While many…
Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…
The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way. Traditional isochrone methods for these estimations are inherently limited due to overlapping isochrones in the Hertzsprung-Russell…
We present a multi-modal foundation model for astrophysical galaxy data, designed to map between simulation- and observation-based galactic features. Our encoder-only transformer flexibly ingests scalar quantities (e.g., redshifts, galaxy…
We are performing a transient, microsecond timescale radio sky survey, called "Astropulse," using the Arecibo telescope. Astropulse searches for brief (0.4 {\mu}s to 204.8 {\mu}s), wideband (relative to its 2.5 MHz bandwidth) radio pulses…
Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general…
Timeseries regression models often struggle to leverage large volumes of labeled multimodal data, particularly when the data are irregularly sampled or contain missing values. This is common in domains like healthcare and predictive…
We present a new approach to measure the shapes of galaxies, a fundamental task in observational astronomy. This approach is based on the decomposition of a galaxy image into a series of orthogonal basis functions, or `shapelets'. Our…
We explore full-shape analysis with simulation-based priors, which is the simplest approach to galaxy clustering data analysis that combines effective field theory (EFT) on large scales and numerical simulations on small scales. The core…