L’éditeur complet pour LaTeX.
LetX est un éditeur LaTeX en ligne, gratuit et collaboratif pour les équipes d’étudiants. Compilez en quelques secondes, travaillez ensemble en temps réel et gardez vos brouillons confidentiels.
\documentclass{article} \usepackage{amsmath} \begin{document} \begin{align*} e^{i\pi} + 1 &= 0 \\[1ex] \int_{0}^{\infty} e^{-x^2} dx &= \frac{\sqrt{\pi}}{2} \end{align*} \end{document}
Une vraie session de rédaction
Invitez votre équipe, travaillez ensemble en temps réel et compilez en PDF en quelques secondes : c’est tout le principe de LetX.
Synergistic Application of Machine Learning and Computer Vision for the Detection of Exoplanets and Stars
Shihab Shahriar Antor Ashraful Kabir Alif
Department of Computer Science, BRAC University
Abstract— We present a framework that detects faint exoplanets in JWST/MIRI coronagraph imagery using contrastive and few-shot learning, separating planetary signals from bright host stars under low signal-to-noise. On held-out fields it outperforms CNN and GNN baselines while using far fewer labels.
Keywords: exoplanets, direct imaging, contrastive learning, few-shot learning, JWST
1. Introduction
Figure 1: JWST/MIRI direct imaging of a faint exoplanet (b) beside its host star.
Direct imaging of exoplanets is fundamentally limited by the overwhelming glare of the host star. Modern coronagraphs on JWST/MIRI suppress this stellar light, yet faint planetary signals remain buried in structured noise. As shown in Figure 1, the planet sits within the diffraction pattern of its star, making detection a needle-in-a-haystack problem. We cast this as a representation-learning task and show that contrastive objectives recover signals that pixel-wise classifiers miss.
2. Method
We learn a discriminative embedding with a contrastive objective, pulling together augmented views of one source and pushing apart star and planet candidates:
A few-shot head then adapts to new instruments from a handful of labelled detections, which is critical given the scarcity of confirmed direct-imaging targets.
3. Results
On held-out fields the model recovers 92% of injected planets at a false-positive rate below 0.1 per frame, outperforming CNN and GNN baselines by 14 and 9 points of recall respectively.
Synergistic Application of Machine Learning and Computer Vision for the Detection of Exoplanets and Stars
Shihab Shahriar Antor Ashraful Kabir Alif
Department of Computer Science, BRAC University
Abstract— We present a framework that detects faint exoplanets in JWST/MIRI coronagraph imagery using contrastive and few-shot learning, separating planetary signals from bright host stars under low signal-to-noise. On held-out fields it outperforms CNN and GNN baselines while using far fewer labels.
Keywords: exoplanets, direct imaging, contrastive learning, few-shot learning, JWST
1. Introduction
Figure 1: JWST/MIRI direct imaging of a faint exoplanet (b) beside its host star.
Direct imaging of exoplanets is fundamentally limited by the overwhelming glare of the host star. Modern coronagraphs on JWST/MIRI suppress this stellar light, yet faint planetary signals remain buried in structured noise. As shown in Figure 1, the planet sits within the diffraction pattern of its star, making detection a needle-in-a-haystack problem. We cast this as a representation-learning task and show that contrastive objectives recover signals that pixel-wise classifiers miss.
2. Method
We learn a discriminative embedding with a contrastive objective, pulling together augmented views of one source and pushing apart star and planet candidates:
A few-shot head then adapts to new instruments from a handful of labelled detections, which is critical given the scarcity of confirmed direct-imaging targets.
3. Results
On held-out fields the model recovers 92% of injected planets at a false-positive rate below 0.1 per frame, outperforming CNN and GNN baselines by 14 and 9 points of recall respectively.
Done in 1.4s, the figure renders. Recompile anytime, free.
Utilisé par des étudiants et des enseignants d’universités du monde entier
Des étudiants et chercheurs de BRAC University, de l’université technique de Munich, de l’université de Hambourg, de l’UPC Barcelone, de l’université d’Ottawa et de 300+ universités et laboratoires dans 55+ pays font confiance à LetX.
BRAC UniversityBangladesh
TU MunichGermany
University of OttawaCanadaUGAUniversity of GeorgiaUSA
UPC BarcelonaSpain
University of WarsawPoland
IIIT DelhiIndia
NIT HamirpurIndia
North South UniversityBangladeshHCMHCMC Univ. of TechnologyVietnam
BYU–IdahoUSA
Daffodil Int'l UniversityBangladesh
United International Univ.BangladeshPMPolitecnica delle MarcheItalyHLHTWK LeipzigGermanyBPBITS PilaniIndiaUDPUniv. Diego PortalesChileBJUTBeijing Univ. of Tech.ChinaESPESPRITTunisiaUABCUABCMexicoBUBenha UniversityEgyptMUMarwadi UniversityIndiaAUSTAUSTBangladeshUHHUniversity of HamburgGermanyUSALUniversity of SalamancaSpainTULŁódź Univ. of TechnologyPolandINGVINGV (Geophysics)ItalyENITENITTunisiaCUCairo UniversityEgyptUFBAFederal Univ. of BahiaBrazilUTECUTECPeruNTUTTaipei Tech (NTUT)TaiwanBUETBUETBangladeshCUETCUETBangladeshUVCEUVCE BangaloreIndiaBRAC UniversityBangladeshTU MunichGermanyUniversity of OttawaCanadaUGAUniversity of GeorgiaUSAUPC BarcelonaSpainUniversity of WarsawPolandIIIT DelhiIndiaNIT HamirpurIndiaNorth South UniversityBangladeshHCMHCMC Univ. of TechnologyVietnamBYU–IdahoUSADaffodil Int'l UniversityBangladeshUnited International Univ.BangladeshPMPolitecnica delle MarcheItalyHLHTWK LeipzigGermanyBPBITS PilaniIndiaUDPUniv. Diego PortalesChileBJUTBeijing Univ. of Tech.ChinaESPESPRITTunisiaUABCUABCMexicoBUBenha UniversityEgyptMUMarwadi UniversityIndiaAUSTAUSTBangladeshUHHUniversity of HamburgGermanyUSALUniversity of SalamancaSpainTULŁódź Univ. of TechnologyPolandINGVINGV (Geophysics)ItalyENITENITTunisiaCUCairo UniversityEgyptUFBAFederal Univ. of BahiaBrazilUTECUTECPeruNTUTTaipei Tech (NTUT)TaiwanBUETBUETBangladeshCUETCUETBangladeshUVCEUVCE BangaloreIndiaCollaboration en temps réel
Écrivez ensemble en temps réel. Les modifications fusionnent sans conflit : plus de fichiers .tex envoyés par e-mail ni de modifications écrasées. L’historique complet des versions vous permet de revenir à n’importe quel moment.
- Conflict-free editing (Yjs CRDT)
- Unlimited collaborators: free
- Full version history
Direct Imaging of Exoplanets
Coronagraphs on JWST/MIRI suppress the host star’s glare, yet faint planetary signals stay buried in structured stellar noise.
We recover them with contrastive and few-shot learning, separating planet candidates from the star even at very low signal-to-noise.
Un assistant qui modifie votre document
Décrivez simplement votre demande. Lexi lit votre projet, propose la modification, la compile pour vérifier qu’elle fonctionne, puis l’applique là où vous travaillez.
This is the editor
Your files, your source, your PDF.
A file tree, the LaTeX source, a live PDF, and whoever else is in the document with you. Lexi waits at the bottom of the editor until you ask it something.
A replica of the editor, running the real tool sequence. Pick any one to jump to it.
Des modèles prêts à l’emploi
Ne partez pas de zéro. Des modèles prêts à publier : articles de revue, thèses, CV universitaires ou professionnels, et bien plus.
Plébiscité par les étudiants et les enseignants
Du labo au bureau des enseignants, voici ce que les premiers utilisateurs de BRAC University et de BUET disent de leur expérience sur LetX.
LetX lets several people edit at once, and I have not run into a cap on how many.
Prêt à rédiger votre prochain article ?
Rejoignez 3,500+ étudiants et chercheurs qui écrivent sur LetX dès aujourd’hui.
Créé par des chercheurs, pour des chercheurs.
Accélérer la découverte scientifique en éliminant les obstacles à la rédaction.
Shihab Shahriar Antor
"Simplifying the future of academic writing for researchers everywhere."
Ashraful Kabir Alif
"Empowering scientists to focus on their ideas, not on the formatting."
Soutenu par
Contactez-nous
Des questions, des remarques ou besoin d’aide ? Nous serions ravis de vous lire.
Envoyez-nous un message
Questions fréquentes
Tout savoir sur LetX, l’éditeur LaTeX collaboratif en ligne.
What is LetX?
LetX is a free online collaborative LaTeX editor, an Overleaf alternative that runs in your browser with no installation. Teams write LaTeX together in real time, compile to PDF in seconds, and use SyncTeX to jump between source and output.
Is LetX free?
Yes. LetX is free to use with unlimited projects, unlimited collaborators, and 40 compiles a day. Unlike Overleaf, which limits free collaborators, LetX never charges per collaborator, and Pro removes the daily compile limit.
How is LetX different from Overleaf?
LetX offers free unlimited real-time collaborators (Overleaf charges beyond one on its free tier), faster compiles with no queue throttling, and 1000+ ready-to-use academic and CV templates. Both run in the browser with no installation.
Do I need to install anything to use LetX?
No. LetX is fully web-based and works on Mac, Windows, and Linux in any modern browser. There is no LaTeX distribution to install, compilation runs on LetX's servers.
Can I collaborate with others in real time?
Yes. LetX uses Yjs CRDT technology (the same algorithm class as Figma) for merge-conflict-free real-time editing. Multiple people can edit the same document simultaneously and see each other's cursors.
Can I import my existing Overleaf or LaTeX project?
Yes. Use '+ New Project' and select 'Upload ZIP' to import an existing LaTeX project, including projects exported from Overleaf.
Who uses LetX?
Students and researchers at over 300 universities and research labs across 55+ countries write on LetX, including BRAC University, the Technical University of Munich (TUM), UC San Diego, De La Salle University, the University of Bologna, the University of Ottawa, UPC Barcelona, IIIT Delhi, and national labs such as Italy's INGV and Brazil's INPE. It is widely used for theses, journal papers, and lab reports.