<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Astronomy |</title><link>https://lelain.net/tags/astronomy/</link><atom:link href="https://lelain.net/tags/astronomy/index.xml" rel="self" type="application/rss+xml"/><description>Astronomy</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Fri, 11 Apr 2025 00:00:00 +0000</lastBuildDate><image><url>https://lelain.net/media/icon.svg</url><title>Astronomy</title><link>https://lelain.net/tags/astronomy/</link></image><item><title>AstroLLaVA: towards the unification of astronomical data and natural language</title><link>https://lelain.net/publications/astrollava/</link><pubDate>Fri, 11 Apr 2025 00:00:00 +0000</pubDate><guid>https://lelain.net/publications/astrollava/</guid><description/></item><item><title>Foundation Models in Astronomy: Why They Matter</title><link>https://lelain.net/blog/foundation-models-astronomy/</link><pubDate>Mon, 10 Feb 2025 00:00:00 +0000</pubDate><guid>https://lelain.net/blog/foundation-models-astronomy/</guid><description>&lt;p&gt;Foundation models — large neural networks pre-trained on massive datasets — are starting to transform astronomical data analysis. Models like DINOv2 or CLIP, originally trained on natural images, can be fine-tuned for astronomical tasks with surprisingly good results. At
, I presented early comparisons of these models on galaxy morphological classification, and my
paper digs into how to best specialize DINOv2 for astronomy.&lt;/p&gt;
&lt;p&gt;The key challenge is the domain gap: astronomical images (multi-band, high dynamic range, specific noise) look nothing like everyday photos. Choosing the right fine-tuning strategy turns out to matter a lot — and is the core focus of my current work.&lt;/p&gt;
&lt;p&gt;On the multimodal side, I am involved in the
collaboration, where I contribute to
— a vision-language model for astronomy presented at ICLR 2025.&lt;/p&gt;</description></item><item><title>STAROS Projects</title><link>https://lelain.net/projects/staros/</link><pubDate>Fri, 01 Sep 2023 00:00:00 +0000</pubDate><guid>https://lelain.net/projects/staros/</guid><description>&lt;p&gt;STAROS Projects develops spectroscopy tools and observation campaigns to foster professional–amateur (pro-am) collaborations in astronomy.&lt;/p&gt;
&lt;p&gt;As a member of the
group, I participate in several instrumentation and spectroscopy-focused initiatives for observational astronomy.&lt;/p&gt;
&lt;h3 id="spectroscopic-database-development"&gt;Spectroscopic Database Development&lt;/h3&gt;
&lt;p&gt;Creation of a dedicated spectroscopic database derived from multiple observing campaigns. This resource supports analysis workflows for stellar, solar, and atmospheric spectra.&lt;/p&gt;
&lt;h3 id="collaborative-observation-campaigns"&gt;Collaborative Observation Campaigns&lt;/h3&gt;
&lt;p&gt;Organizing multi-month observation campaigns where astronomers contribute spectroscopic data. The alpha Draconis campaign mobilized several astronomers over several months, consolidating more than 10 consecutive days of observations from over 200 spectra.&lt;/p&gt;
&lt;h3 id="alpha-draconis--orbital-parameters"&gt;Alpha Draconis — Orbital Parameters&lt;/h3&gt;
&lt;p&gt;Results of a STAROS monitoring campaign on the bright eclipsing binary star α Draconis. Over 200 high-resolution spectra were obtained by an international group of amateur astronomers.&lt;/p&gt;
&lt;p&gt;
·
&lt;/p&gt;
&lt;h3 id="ohp-spectro-workshop"&gt;OHP Spectro Workshop&lt;/h3&gt;
&lt;p&gt;Co-organized a
with Shelyak Instruments (2025).&lt;/p&gt;
&lt;p&gt;
&lt;/p&gt;</description></item></channel></rss>