{ "meta": { "title": "Awesome AI for Astronomy", "source": "https://github.com/Xin-YuXiao/Awesome-AI-for-Astronomy", "page": "https://xin-yuxiao.github.io/Awesome-AI-for-Astronomy/", "license": "CC0-1.0", "generated": "2026-11-12", "commit": "ad98c08", "papers": 398, "links": 76 }, "papers": [ { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Machine Learning in Astronomy: A Practical Overview", "venue": "arXiv 2019", "publication_type": "Preprint", "note": "", "year": 2019, "month": 4, "arxiv_id": "1904.07248", "doi": "", "url": "https://arxiv.org/abs/1904.07248", "code": [], "links": { "Paper": "https://arxiv.org/abs/1904.07248" }, "resources": [], "modality": [], "summary": "Lecture notes from the IAC Winter School 2018 covering supervised and unsupervised learning for astronomical datasets." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "The Frontier of Simulation-Based Inference", "venue": "PNAS 2020", "publication_type": "Journal", "note": "", "year": 2019, "month": 11, "arxiv_id": "1911.01429", "doi": "10.1073/pnas.1912789117", "url": "https://arxiv.org/abs/1911.01429", "code": [], "links": { "Paper": "https://arxiv.org/abs/1911.01429", "Journal": "https://doi.org/10.1073/pnas.1912789117" }, "resources": [], "modality": [], "summary": "Review of simulation-based inference methods and the role of machine learning in inference with intractable likelihoods." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Enhancing Gravitational-Wave Science with Machine Learning", "venue": "MLST 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 5, "arxiv_id": "2005.03745", "doi": "10.1088/2632-2153/abb93a", "url": "https://arxiv.org/abs/2005.03745", "code": [], "links": { "Paper": "https://arxiv.org/abs/2005.03745", "Journal": "https://doi.org/10.1088/2632-2153/abb93a" }, "resources": [], "modality": [], "summary": "Review of machine learning for LIGO and Virgo data quality, signal modeling, searches and parameter estimation." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "The Dawes Review 10: The Impact of Deep Learning for the Analysis of Galaxy Surveys", "venue": "PASA 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 10, "arxiv_id": "2210.01813", "doi": "10.1017/pasa.2022.55", "url": "https://arxiv.org/abs/2210.01813", "code": [], "links": { "Paper": "https://arxiv.org/abs/2210.01813", "Journal": "https://doi.org/10.1017/pasa.2022.55" }, "resources": [], "modality": [], "summary": "Review of deep learning applications to galaxy surveys covering classification, property estimation, discovery and cosmological inference." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Astronomia ex machina: A History, Primer and Outlook on Neural Networks in Astronomy", "venue": "R. Soc. Open Sci. 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 11, "arxiv_id": "2211.03796", "doi": "10.1098/rsos.221454", "url": "https://arxiv.org/abs/2211.03796", "code": [], "links": { "Paper": "https://arxiv.org/abs/2211.03796", "Journal": "https://doi.org/10.1098/rsos.221454" }, "resources": [], "modality": [], "summary": "Historical review of neural networks in astronomy with a primer on deep learning and an outlook on astronomical foundation models." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Machine Learning for Observational Cosmology", "venue": "Rep. Prog. Phys. 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 3, "arxiv_id": "2303.15794", "doi": "10.1088/1361-6633/acd2ea", "url": "https://arxiv.org/abs/2303.15794", "code": [], "links": { "Paper": "https://arxiv.org/abs/2303.15794", "Journal": "https://doi.org/10.1088/1361-6633/acd2ea" }, "resources": [], "modality": [], "summary": "Review of machine learning applications in time-domain astronomy, galaxy surveys and emulation for cosmology." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Constructing Impactful Machine Learning Research for Astronomy: Best Practices for Researchers and Reviewers", "venue": "arXiv 2023", "publication_type": "Preprint", "note": "", "year": 2023, "month": 10, "arxiv_id": "2310.12528", "doi": "", "url": "https://arxiv.org/abs/2310.12528", "code": [], "links": { "Paper": "https://arxiv.org/abs/2310.12528" }, "resources": [], "modality": [], "summary": "Recommendations on baselines, validation, reproducibility and reporting for machine learning papers in astronomy." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Deep Learning Based Systems for Crater Detection: A Review", "venue": "arXiv 2023", "publication_type": "Preprint", "note": "", "year": 2023, "month": 10, "arxiv_id": "2310.07727", "doi": "", "url": "https://arxiv.org/abs/2310.07727", "code": [], "links": { "Paper": "https://arxiv.org/abs/2310.07727" }, "resources": [], "modality": [], "summary": "Review of CNN, U-Net, R-CNN and transformer crater detection algorithms for the Moon, Mars and Mercury." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "What is the Role of Large Language Models in the Evolution of Astronomy Research?", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 9, "arxiv_id": "2409.20252", "doi": "", "url": "https://arxiv.org/abs/2409.20252", "code": [], "links": { "Paper": "https://arxiv.org/abs/2409.20252" }, "resources": [], "modality": [], "summary": "Use cases, survey results and recommendations on LLM adoption in astronomy research." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.24047", "doi": "", "url": "https://arxiv.org/abs/2503.24047", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.24047" }, "resources": [], "modality": [], "summary": "Survey of LLM-based scientific agents with a section on astronomy and cosmology applications." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.14111", "doi": "", "url": "https://arxiv.org/abs/2508.14111", "code": [ "https://github.com/AgenticScience/Awesome-Agent-Scientists" ], "links": { "Paper": "https://arxiv.org/abs/2508.14111", "Code": "https://github.com/AgenticScience/Awesome-Agent-Scientists" }, "resources": [ "code" ], "modality": [], "summary": "Domain-oriented survey of autonomous scientific discovery including agentic astronomy and cosmology research." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.21148", "doi": "", "url": "https://arxiv.org/abs/2508.21148", "code": [], "links": { "Paper": "https://arxiv.org/abs/2508.21148" }, "resources": [], "modality": [], "summary": "Survey of scientific LLMs and their training data, including astronomy datasets and models." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "The Revolution in Strong Lensing Discoveries from Euclid", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.14624", "doi": "", "url": "https://arxiv.org/abs/2508.14624", "code": [], "links": { "Paper": "https://arxiv.org/abs/2508.14624" }, "resources": [], "modality": [], "summary": "Review of how machine learning, citizen science and expert inspection found about 500 high-quality lens candidates in Euclid Q1." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Deep Learning in Astrophysics", "venue": "ARA&A 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.10713", "doi": "", "url": "https://arxiv.org/abs/2510.10713", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.10713" }, "resources": [], "modality": [], "summary": "Annual Review covering inductive biases, simulation-based inference, anomaly detection, foundation models, reinforcement learning and LLM agents in astronomy." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Advances and Challenges in Solar Flare Prediction: A Review", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.20465", "doi": "", "url": "https://arxiv.org/abs/2511.20465", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.20465" }, "resources": [], "modality": [], "summary": "Review of statistical, physics-based and deep learning flare forecasting including CNN, LSTM and transformer models." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 1, "arxiv_id": "2601.14235", "doi": "", "url": "https://arxiv.org/abs/2601.14235", "code": [], "links": { "Paper": "https://arxiv.org/abs/2601.14235" }, "resources": [], "modality": [], "summary": "LSST DESC roadmap covering photometric redshifts, transient classification, weak lensing inference, foundation models and infrastructure." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Deep Learning-Based Astronomical Multimodal Data Fusion: A Comprehensive Review", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.00699", "doi": "", "url": "https://arxiv.org/abs/2603.00699", "code": [], "links": { "Paper": "https://arxiv.org/abs/2603.00699" }, "resources": [], "modality": [], "summary": "Review of deep learning methods that fuse images, spectra, time series and catalogues in astronomy." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "The Role of Artificial Intelligence in the SKA Era", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.28493", "doi": "", "url": "https://arxiv.org/abs/2606.28493", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.28493" }, "resources": [], "modality": [], "summary": "Chapter on deep learning for source finding, RFI mitigation, imaging, anomaly detection and scheduling for the SKA." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Source Finding and Characterisation for SKAO Science", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.03736", "doi": "", "url": "https://arxiv.org/abs/2607.03736", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.03736" }, "resources": [], "modality": [], "summary": "Review of classical and machine learning source finding and morphology classification for SKAO surveys." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Machine Learning and Deep Learning for Exoplanet Detection and Atmospheric Characterization with JWST and the Upcoming Ariel Mission", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.23766", "doi": "", "url": "https://arxiv.org/abs/2606.23766", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.23766" }, "resources": [], "modality": [], "summary": "Review of machine learning for transit identification, candidate vetting, detrending and atmospheric retrieval, including neural and flow matching posterior estimation, in the context of JWST and Ariel." }, { "section": "Surveys and Reviews", "subsection": "", "name": "", "title": "Machine Learning in Gamma Astronomy", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 1, "arxiv_id": "2501.19064", "doi": "", "url": "https://arxiv.org/abs/2501.19064", "code": [], "links": { "Paper": "https://arxiv.org/abs/2501.19064" }, "resources": [], "modality": [], "summary": "Review of deep learning methods for Imaging Atmospheric Cherenkov Telescope data, covering gamma-hadron separation, event reconstruction and fast simulation." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "SSL-SDSS", "title": "Self-Supervised Representation Learning for Astronomical Images", "venue": "ApJL 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 12, "arxiv_id": "2012.13083", "doi": "10.3847/2041-8213/abf2c7", "url": "https://arxiv.org/abs/2012.13083", "code": [ "https://portal.nersc.gov/project/dasrepo/self-supervised-learning-sdss" ], "links": { "Paper": "https://arxiv.org/abs/2012.13083", "Code and Models": "https://portal.nersc.gov/project/dasrepo/self-supervised-learning-sdss", "Journal": "https://doi.org/10.3847/2041-8213/abf2c7" }, "resources": [ "code", "model" ], "modality": [ "Images" ], "summary": "Contrastive pretraining on about 1.2M SDSS galaxy images, evaluated on morphology classification and photometric redshift estimation." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Galaxy Search", "title": "Self-Supervised Similarity Search for Large Scientific Datasets", "venue": "NeurIPS 2021 Workshop (ML4PS)", "publication_type": "Workshop", "note": "", "year": 2021, "month": 10, "arxiv_id": "2110.13151", "doi": "", "url": "https://arxiv.org/abs/2110.13151", "code": [ "https://github.com/georgestein/galaxy_search" ], "links": { "Paper": "https://arxiv.org/abs/2110.13151", "Code": "https://github.com/georgestein/galaxy_search" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Self-supervised representations of 42M DESI Legacy Imaging Survey galaxies with a public similarity search tool." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Zoobot Representations", "title": "Practical Galaxy Morphology Tools from Deep Supervised Representation Learning", "venue": "MNRAS 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 10, "arxiv_id": "2110.12735", "doi": "10.1093/mnras/stac525", "url": "https://arxiv.org/abs/2110.12735", "code": [ "https://github.com/mwalmsley/zoobot" ], "links": { "Paper": "https://arxiv.org/abs/2110.12735", "Journal": "https://doi.org/10.1093/mnras/stac525", "Code": "https://github.com/mwalmsley/zoobot" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Representations learned from Galaxy Zoo labels reused for similarity search, anomaly finding and new classification tasks." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Zoobot FM", "title": "Towards Galaxy Foundation Models with Hybrid Contrastive Learning", "venue": "ICML 2022 Workshop (ML4Astro)", "publication_type": "Workshop", "note": "", "year": 2022, "month": 6, "arxiv_id": "2206.11927", "doi": "", "url": "https://arxiv.org/abs/2206.11927", "code": [ "https://github.com/mwalmsley/zoobot" ], "links": { "Paper": "https://arxiv.org/abs/2206.11927", "Code": "https://github.com/mwalmsley/zoobot" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Pretraining galaxy morphology encoders on Galaxy Zoo volunteer responses for transfer to downstream tasks." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Zoobot", "title": "Zoobot: Adaptable Deep Learning Models for Galaxy Morphology", "venue": "JOSS 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": null, "arxiv_id": "", "doi": "10.21105/joss.05312", "url": "https://doi.org/10.21105/joss.05312", "code": [ "https://github.com/mwalmsley/zoobot" ], "links": { "Journal": "https://doi.org/10.21105/joss.05312", "Code": "https://github.com/mwalmsley/zoobot", "PyPI": "https://pypi.org/project/zoobot/" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Pretrained galaxy morphology encoders and finetuning utilities, deployed in the Euclid morphology pipeline." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Rare Galaxy Classes", "title": "Rare Galaxy Classes Identified In Foundation Model Representations", "venue": "arXiv 2023", "publication_type": "Preprint", "note": "", "year": 2023, "month": 12, "arxiv_id": "2312.02910", "doi": "", "url": "https://arxiv.org/abs/2312.02910", "code": [ "https://github.com/mwalmsley/zoobot" ], "links": { "Paper": "https://arxiv.org/abs/2312.02910", "Code": "https://github.com/mwalmsley/zoobot" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Searches Zoobot representation space for rare morphological classes." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Galaxy Scaling Laws", "title": "Scaling Laws for Galaxy Images", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 4, "arxiv_id": "2404.02973", "doi": "", "url": "https://arxiv.org/abs/2404.02973", "code": [ "https://github.com/mwalmsley/zoobot" ], "links": { "Paper": "https://arxiv.org/abs/2404.02973", "Code": "https://github.com/mwalmsley/zoobot" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Supervised scaling study on 840k galaxy images with over 100M Galaxy Zoo annotations." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "AstroPT", "title": "AstroPT: Scaling Large Observation Models for Astronomy", "venue": "ICML 2024 Workshop (AI4Science)", "publication_type": "Workshop", "note": "", "year": 2024, "month": 5, "arxiv_id": "2405.14930", "doi": "", "url": "https://arxiv.org/abs/2405.14930", "code": [ "https://github.com/Smith42/astroPT" ], "links": { "Paper": "https://arxiv.org/abs/2405.14930", "Euclid Paper": "https://arxiv.org/abs/2503.15312", "Code": "https://github.com/Smith42/astroPT", "Model": "https://huggingface.co/Smith42/astroPT_v2.0" }, "resources": [ "code", "model" ], "modality": [ "Images" ], "summary": "Autoregressive transformers from 1M to 2.1B parameters pretrained on 8.6M DESI Legacy Survey galaxy images." }, { "section": "Foundation Models and Representation Learning", "subsection": "Images", "name": "Gestalt", "title": "Gestalt: A Meta-Foundation Model for Astronomy", "venue": "NeurIPS 2026 Workshop (Interpretability for Discovery)", "publication_type": "Workshop", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.38312", "doi": "", "url": "https://arxiv.org/abs/2609.38312", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.38312" }, "resources": [], "modality": [ "Images" ], "summary": "Combines frozen embeddings of 22 foundation models from eight families by whitening and randomised SVD, outperforming every member on 19 of 21 metrics for HSC, JWST and Legacy Survey galaxies." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "SDSS-VAE", "title": "Dimensionality Reduction of SDSS Spectra with Variational Autoencoders", "venue": "AJ 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": 2, "arxiv_id": "2002.10464", "doi": "10.3847/1538-3881/ab9644", "url": "https://arxiv.org/abs/2002.10464", "code": [ "https://github.com/stephenportillo/SDSS-VAE" ], "links": { "Paper": "https://arxiv.org/abs/2002.10464", "Journal": "https://doi.org/10.3847/1538-3881/ab9644", "Code": "https://github.com/stephenportillo/SDSS-VAE" }, "resources": [ "code" ], "modality": [ "Spectra" ], "summary": "Variational autoencoder compression of SDSS galaxy spectra into a low-dimensional latent space." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "Cycle-StarNet", "title": "Cycle-StarNet: Bridging the Gap between Theory and Data by Leveraging Large Data Sets", "venue": "ApJ 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 7, "arxiv_id": "2007.03109", "doi": "10.3847/1538-4357/abca96", "url": "https://arxiv.org/abs/2007.03109", "code": [ "https://github.com/teaghan/Cycle_SN" ], "links": { "Paper": "https://arxiv.org/abs/2007.03109", "Code": "https://github.com/teaghan/Cycle_SN", "Journal": "https://doi.org/10.3847/1538-4357/abca96" }, "resources": [ "code" ], "modality": [ "Spectra" ], "summary": "Domain adaptation between synthetic and observed stellar spectra with cycle-consistent networks." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "spender", "title": "Autoencoding Galaxy Spectra I: Architecture", "venue": "AJ 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 11, "arxiv_id": "2211.07890", "doi": "10.3847/1538-3881/ace0ff", "url": "https://arxiv.org/abs/2211.07890", "code": [ "https://github.com/pmelchior/spender" ], "links": { "Paper": "https://arxiv.org/abs/2211.07890", "Code": "https://github.com/pmelchior/spender", "Journal": "https://doi.org/10.3847/1538-3881/ace0ff" }, "resources": [ "code" ], "modality": [ "Spectra" ], "summary": "Attentive convolutional autoencoder that models galaxy spectra in the rest frame with explicit redshifting and resampling, trained on SDSS-II." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "Stellar FM", "title": "Towards an Astronomical Foundation Model for Stars with a Transformer-Based Model", "venue": "MNRAS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 8, "arxiv_id": "2308.10944", "doi": "", "url": "https://arxiv.org/abs/2308.10944", "code": [ "https://github.com/henrysky/astroNN_stars_foundation" ], "links": { "Paper": "https://arxiv.org/abs/2308.10944", "Code": "https://github.com/henrysky/astroNN_stars_foundation" }, "resources": [ "code" ], "modality": [ "Spectra", "Tabular" ], "summary": "Transformer trained on cross-survey APOGEE, Gaia and 2MASS data that performs discriminative and generative stellar tasks without task-specific finetuning." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "SpectraFM", "title": "SpectraFM: Tuning into Stellar Foundation Models", "venue": "NeurIPS 2024 Workshop (FM4Science)", "publication_type": "Workshop", "note": "", "year": 2024, "month": 11, "arxiv_id": "2411.04750", "doi": "", "url": "https://arxiv.org/abs/2411.04750", "code": [], "links": { "Paper": "https://arxiv.org/abs/2411.04750" }, "resources": [], "modality": [ "Spectra" ], "summary": "Transformer pretrained on synthetic stellar spectra and transferred to real spectra across wavelength ranges." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "", "title": "Applying Vision Transformers on Spectral Analysis of Astronomical Objects", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 6, "arxiv_id": "2506.00294", "doi": "", "url": "https://arxiv.org/abs/2506.00294", "code": [], "links": { "Paper": "https://arxiv.org/abs/2506.00294" }, "resources": [], "modality": [ "Spectra" ], "summary": "Converts one-dimensional spectra into images for pretrained ViT backbones in classification and regression." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "SpecCLIP", "title": "SpecCLIP: Aligning and Translating Spectroscopic Measurements for Stars", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 7, "arxiv_id": "2507.01939", "doi": "", "url": "https://arxiv.org/abs/2507.01939", "code": [], "links": { "Paper": "https://arxiv.org/abs/2507.01939", "LoRA Fine-tuning": "https://arxiv.org/abs/2507.20972" }, "resources": [], "modality": [ "Spectra" ], "summary": "Contrastive alignment of LAMOST low-resolution and Gaia XP spectra foundation models for parameter estimation and cross-spectrum prediction." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "OmniSpectra", "title": "OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 1, "arxiv_id": "2601.15351", "doi": "", "url": "https://arxiv.org/abs/2601.15351", "code": [], "links": { "Paper": "https://arxiv.org/abs/2601.15351" }, "resources": [], "modality": [ "Spectra" ], "summary": "Masked-modeling transformer pretrained on 5.5 million spectra from eight surveys at native resolution." }, { "section": "Foundation Models and Representation Learning", "subsection": "Spectra", "name": "", "title": "Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.17959", "doi": "", "url": "https://arxiv.org/abs/2510.17959", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.17959" }, "resources": [], "modality": [ "Spectra" ], "summary": "Transformer tokenizer that reads spectra on their native wavelength grids, pretrained on SDSS, DESI, GALAH and APOGEE and adapted to object classification and stellar parameter regression." }, { "section": "Foundation Models and Representation Learning", "subsection": "Time Series", "name": "", "title": "Domain-Informed Multi-View Self-Distillation for Astronomical Light-Curve Representation Learning with JEPA", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.28446", "doi": "", "url": "https://arxiv.org/abs/2606.28446", "code": [ "https://github.com/ruiyicheng/domain-informed-lightcurve-jepa" ], "links": { "Paper": "https://arxiv.org/abs/2606.28446", "Code": "https://github.com/ruiyicheng/domain-informed-lightcurve-jepa", "Model": "https://huggingface.co/ruiyicheng/domain-informed-lightcurve-jepa-exp21" }, "resources": [ "code", "model" ], "modality": [ "Time series" ], "summary": "Domain-informed JEPA combines raw, periodogram and phase-folded light-curve views with uncertainty-aware tokenization and multi-view self-distillation, trained on LEAVES and evaluated on StarEmbed and 12 irregular time-series datasets." }, { "section": "Foundation Models and Representation Learning", "subsection": "Time Series", "name": "ASTROMER", "title": "ASTROMER: A Transformer-Based Embedding for the Representation of Light Curves", "venue": "A&A 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 5, "arxiv_id": "2205.01677", "doi": "10.1051/0004-6361/202243928", "url": "https://arxiv.org/abs/2205.01677", "code": [ "https://github.com/astromer-science" ], "links": { "Paper": "https://arxiv.org/abs/2205.01677", "Code": "https://github.com/astromer-science", "Journal": "https://doi.org/10.1051/0004-6361/202243928", "Astromer 2": "https://arxiv.org/abs/2502.02717" }, "resources": [ "code" ], "modality": [ "Time series" ], "summary": "Self-supervised light-curve encoder pretrained with masked magnitude prediction on MACHO R-band data." }, { "section": "Foundation Models and Representation Learning", "subsection": "Time Series", "name": "Astroconformer", "title": "Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models", "venue": "MNRAS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 9, "arxiv_id": "2309.16316", "doi": "10.1093/mnras/stae068", "url": "https://arxiv.org/abs/2309.16316", "code": [], "links": { "Paper": "https://arxiv.org/abs/2309.16316", "Journal": "https://doi.org/10.1093/mnras/stae068", "Workshop Version": "https://arxiv.org/abs/2207.02787" }, "resources": [], "modality": [ "Time series" ], "summary": "Conformer model for Kepler light curves that infers surface gravity and frequency of maximum oscillation power." }, { "section": "Foundation Models and Representation Learning", "subsection": "Time Series", "name": "Maven", "title": "Maven: A Multimodal Foundation Model for Supernova Science", "venue": "MLST 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": 8, "arxiv_id": "2408.16829", "doi": "", "url": "https://arxiv.org/abs/2408.16829", "code": [ "https://github.com/ThomasHelfer/multimodal-supernovae" ], "links": { "Paper": "https://arxiv.org/abs/2408.16829", "Code": "https://github.com/ThomasHelfer/multimodal-supernovae" }, "resources": [ "code" ], "modality": [ "Spectra", "Time series" ], "summary": "Contrastive alignment of supernova photometry and spectroscopy, pretrained on 0.5M synthetic events and finetuned on ZTF." }, { "section": "Foundation Models and Representation Learning", "subsection": "Time Series", "name": "FALCO", "title": "FALCO: A Foundation Model of Astronomical Light Curves for Time Domain Astronomy", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 4, "arxiv_id": "2504.20290", "doi": "", "url": "https://arxiv.org/abs/2504.20290", "code": [], "links": { "Paper": "https://arxiv.org/abs/2504.20290" }, "resources": [], "modality": [ "Time series" ], "summary": "Self-supervised transformer on Kepler light curves for variability classification, surface gravity estimation and flare identification." }, { "section": "Foundation Models and Representation Learning", "subsection": "Time Series", "name": "", "title": "What Does Self-supervision Add to Engineered Features for Stellar Light Curves?", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 10, "arxiv_id": "2610.14283", "doi": "", "url": "https://arxiv.org/abs/2610.14283", "code": [], "links": { "Paper": "https://arxiv.org/abs/2610.14283" }, "resources": [], "modality": [ "Time series" ], "summary": "Measures the information that self-supervised light-curve encoders add beyond engineered periodogram and variability features." }, { "section": "Foundation Models and Representation Learning", "subsection": "Multimodal", "name": "AstroCLIP", "title": "AstroCLIP: A Cross-Modal Foundation Model for Galaxies", "venue": "MNRAS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 10, "arxiv_id": "2310.03024", "doi": "10.1093/mnras/stae1450", "url": "https://arxiv.org/abs/2310.03024", "code": [ "https://github.com/PolymathicAI/AstroCLIP" ], "links": { "Paper": "https://arxiv.org/abs/2310.03024", "Code": "https://github.com/PolymathicAI/AstroCLIP", "Journal": "https://doi.org/10.1093/mnras/stae1450" }, "resources": [ "code" ], "modality": [ "Images", "Spectra" ], "summary": "Contrastive alignment of DESI galaxy images and spectra in a shared embedding space." }, { "section": "Foundation Models and Representation Learning", "subsection": "Multimodal", "name": "MPP", "title": "Multiple Physics Pretraining for Physical Surrogate Models", "venue": "NeurIPS 2024", "publication_type": "Conference", "note": "", "year": 2023, "month": 10, "arxiv_id": "2310.02994", "doi": "", "url": "https://arxiv.org/abs/2310.02994", "code": [ "https://github.com/PolymathicAI/multiple_physics_pretraining" ], "links": { "Paper": "https://arxiv.org/abs/2310.02994", "Code": "https://github.com/PolymathicAI/multiple_physics_pretraining" }, "resources": [ "code" ], "modality": [ "Simulations" ], "summary": "Autoregressive pretraining of a single surrogate model across heterogeneous physical simulation systems." }, { "section": "Foundation Models and Representation Learning", "subsection": "Multimodal", "name": "PAPERCLIP", "title": "PAPERCLIP: Associating Astronomical Observations and Natural Language with Multi-Modal Models", "venue": "COLM 2024", "publication_type": "Conference", "note": "", "year": 2024, "month": 3, "arxiv_id": "2403.08851", "doi": "", "url": "https://arxiv.org/abs/2403.08851", "code": [ "https://github.com/smsharma/PAPERCLIP-Hubble" ], "links": { "Paper": "https://arxiv.org/abs/2403.08851", "Code": "https://github.com/smsharma/PAPERCLIP-Hubble" }, "resources": [ "code" ], "modality": [ "Images", "Text" ], "summary": "CLIP finetuned on Hubble Space Telescope observations paired with observing proposal abstracts." }, { "section": "Foundation Models and Representation Learning", "subsection": "Multimodal", "name": "AstroM3", "title": "AstroM3: A Self-Supervised Multimodal Model for Astronomy", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 11, "arxiv_id": "2411.08842", "doi": "", "url": "https://arxiv.org/abs/2411.08842", "code": [ "https://github.com/MeriDK/AstroM3" ], "links": { "Paper": "https://arxiv.org/abs/2411.08842", "Code": "https://github.com/MeriDK/AstroM3" }, "resources": [ "code" ], "modality": [ "Spectra", "Time series", "Tabular" ], "summary": "Trimodal CLIP-style pretraining on variable-star light curves, spectra and metadata." }, { "section": "Foundation Models and Representation Learning", "subsection": "Multimodal", "name": "AION-1", "title": "AION-1: Omnimodal Foundation Model for Astronomical Sciences", "venue": "NeurIPS 2025", "publication_type": "Conference", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.17960", "doi": "", "url": "https://arxiv.org/abs/2510.17960", "code": [ "https://github.com/PolymathicAI/AION" ], "links": { "Paper": "https://arxiv.org/abs/2510.17960", "Code": "https://github.com/PolymathicAI/AION", "Model": "https://huggingface.co/polymathic-ai/aion-base" }, "resources": [ "code", "model" ], "modality": [ "Images", "Spectra", "Tabular" ], "summary": "Token-based masked modeling over 39 modalities from Legacy Survey, HSC, SDSS, DESI and Gaia, released at 300M to 3.1B parameters." }, { "section": "Foundation Models and Representation Learning", "subsection": "Multimodal", "name": "", "title": "Self-Supervised Representation Learning for JWST Galaxy Images and Low Resolution Spectra", "venue": "NeurIPS 2026 Workshop (RPS)", "publication_type": "Workshop", "note": "", "year": 2026, "month": 10, "arxiv_id": "2610.31078", "doi": "", "url": "https://arxiv.org/abs/2610.31078", "code": [ "https://github.com/2003cy/neurips2026_ssl_jwst" ], "links": { "Paper": "https://arxiv.org/abs/2610.31078", "Code": "https://github.com/2003cy/neurips2026_ssl_jwst" }, "resources": [ "code" ], "modality": [ "Images", "Spectra" ], "summary": "Joint representation of F150W imaging and 1 to 2 micron PRISM spectra that recovers stellar mass at 1 < z < 3 with R2 of about 0.9, with CLIP alignment improving single-modality inference." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "astroBERT", "title": "Building astroBERT, a Language Model for Astronomy & Astrophysics", "venue": "arXiv 2021", "publication_type": "Preprint", "note": "", "year": 2021, "month": 12, "arxiv_id": "2112.00590", "doi": "", "url": "https://arxiv.org/abs/2112.00590", "code": [], "links": { "Paper": "https://arxiv.org/abs/2112.00590", "Model": "https://huggingface.co/adsabs/astroBERT" }, "resources": [ "model" ], "modality": [], "summary": "BERT model with 110M parameters trained on NASA ADS papers for named entity recognition and classification." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "AstroLLaMA", "title": "AstroLLaMA: Towards Specialized Foundation Models in Astronomy", "venue": "IJCNLP-AACL 2023 Workshop (WIESP)", "publication_type": "Workshop", "note": "", "year": 2023, "month": 9, "arxiv_id": "2309.06126", "doi": "", "url": "https://arxiv.org/abs/2309.06126", "code": [], "links": { "Paper": "https://arxiv.org/abs/2309.06126", "ACL Anthology": "https://aclanthology.org/2023.wiesp-1.7/", "Model": "https://huggingface.co/universeTBD" }, "resources": [ "model" ], "modality": [], "summary": "LLaMA-2-7B finetuned on over 300k astro-ph abstracts." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "AstroLLaMA-Chat", "title": "AstroLLaMA-Chat: Scaling AstroLLaMA with Conversational and Diverse Datasets", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 1, "arxiv_id": "2401.01916", "doi": "", "url": "https://arxiv.org/abs/2401.01916", "code": [], "links": { "Paper": "https://arxiv.org/abs/2401.01916", "Model": "https://huggingface.co/universeTBD" }, "resources": [ "model" ], "modality": [], "summary": "Continual pretraining on abstracts, introductions and conclusions followed by domain conversational finetuning." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "cosmosage", "title": "cosmosage: A Natural-Language Assistant for Cosmology", "venue": "Astron. Comput. 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.04420", "doi": "10.1016/j.ascom.2025.100934", "url": "https://arxiv.org/abs/2407.04420", "code": [ "https://github.com/tijmen/cosmosage" ], "links": { "Paper": "https://arxiv.org/abs/2407.04420", "Code": "https://github.com/tijmen/cosmosage", "Model": "https://huggingface.co/Tijmen2/cosmosage-v3.1", "Journal": "https://doi.org/10.1016/j.ascom.2025.100934" }, "resources": [ "code", "model" ], "modality": [], "summary": "Cosmology assistant built by continued pretraining on cosmology papers and textbooks followed by question-answer finetuning." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "AstroLLaMA-2-70B", "title": "AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy", "venue": "SC 2024 Workshop (AI4S)", "publication_type": "Workshop", "note": "", "year": 2024, "month": 9, "arxiv_id": "2409.19750", "doi": "", "url": "https://arxiv.org/abs/2409.19750", "code": [], "links": { "Paper": "https://arxiv.org/abs/2409.19750", "Model": "https://huggingface.co/AstroMLab" }, "resources": [ "model" ], "modality": [], "summary": "Releases AstroLLaMA-3-8B and AstroLLaMA-2-70B and reports that the 7B AstroLLaMA series underperforms its base model." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "AstroSage-8B", "title": "AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model", "venue": "Sci. Rep. 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 11, "arxiv_id": "2411.09012", "doi": "10.1038/s41598-025-97131-y", "url": "https://arxiv.org/abs/2411.09012", "code": [], "links": { "Paper": "https://arxiv.org/abs/2411.09012", "Model": "https://huggingface.co/AstroMLab/AstroSage-8B", "Journal": "https://doi.org/10.1038/s41598-025-97131-y" }, "resources": [ "model" ], "modality": [], "summary": "Llama-3.1-8B with continued pretraining on about 250k astro-ph and gr-qc preprints, SFT and model merging. Scores 80.9% on AstroMLab 1." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "Astro-HEP-BERT", "title": "Astro-HEP-BERT: A Bidirectional Language Model for Studying the Meanings of Concepts in Astrophysics and High Energy Physics", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 11, "arxiv_id": "2411.14877", "doi": "", "url": "https://arxiv.org/abs/2411.14877", "code": [], "links": { "Paper": "https://arxiv.org/abs/2411.14877", "Model": "https://huggingface.co/arnosimons/astro-hep-bert" }, "resources": [ "model" ], "modality": [], "summary": "BERT model adapted to astrophysics and high energy physics literature for concept analysis." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "AstroLLaVA", "title": "AstroLLaVA: Towards the Unification of Astronomical Data and Natural Language", "venue": "ICLR 2025 Workshop (SCI-FM)", "publication_type": "Workshop", "note": "", "year": 2025, "month": 4, "arxiv_id": "2504.08583", "doi": "", "url": "https://arxiv.org/abs/2504.08583", "code": [ "https://github.com/UniverseTBD/AstroLLaVA" ], "links": { "Paper": "https://arxiv.org/abs/2504.08583", "Code": "https://github.com/UniverseTBD/AstroLLaVA" }, "resources": [ "code" ], "modality": [], "summary": "LLaVA finetuned on about 30k captioned images from APOD, ESO and Hubble for astronomical visual question answering." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "AstroSage-70B", "title": "AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.17592", "doi": "", "url": "https://arxiv.org/abs/2505.17592", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.17592", "Model": "https://huggingface.co/AstroMLab/AstroSage-70B-20251009" }, "resources": [ "model" ], "modality": [], "summary": "Llama-3.1-70B with continued pretraining and reasoning-chain SFT. Scores 89.0% on a validated 3,846-question subset of AstroMLab 1." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "", "title": "Rethinking Domain Specialization for Open-Ended Scientific Reasoning in Astronomy Language Models", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.17644", "doi": "", "url": "https://arxiv.org/abs/2609.17644", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.17644" }, "resources": [], "modality": [], "summary": "Evaluates whether continued pretraining and instruction tuning on astronomy corpora help open-ended scientific reasoning." }, { "section": "Language and Vision-Language Models", "subsection": "", "name": "Spec-o3", "title": "Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection", "venue": "ACL 2026", "publication_type": "Conference", "note": "Oral", "year": 2026, "month": 1, "arxiv_id": "2601.06498", "doi": "", "url": "https://arxiv.org/abs/2601.06498", "code": [ "https://github.com/Maxwell-Jia/spec-o3" ], "links": { "Paper": "https://arxiv.org/abs/2601.06498", "ACL Anthology": "https://aclanthology.org/2026.acl-long.256/", "Code": "https://github.com/Maxwell-Jia/spec-o3", "Model": "https://huggingface.co/Maxwell-Jia/spec-o3-7b", "Data": "https://huggingface.co/datasets/Maxwell-Jia/SpecVI-Bench" }, "resources": [ "code", "model", "data" ], "modality": [], "summary": "Tool-using vision-language agent trained with supervised fine-tuning on expert inspection trajectories and outcome-based reinforcement learning, which vets rare-object candidates by iteratively inspecting spectral regions, raising macro-F1 on five LAMOST tasks from 28.3 to 76.5 with transfer to SDSS and DESI." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "GalaxyWiki", "title": "Extracting Published Discussions of 13,616 Galaxies with Language Models", "venue": "WASP 2026 Workshop", "publication_type": "Workshop", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.13118", "doi": "", "url": "https://arxiv.org/abs/2611.13118", "code": [ "https://github.com/NolanKoblischke/galaxywiki-paper" ], "links": { "Paper": "https://arxiv.org/abs/2611.13118", "ACL Anthology": "https://aclanthology.org/2026.wasp-1.19/", "Code": "https://github.com/NolanKoblischke/galaxywiki-paper", "Project": "https://galaxywiki.nolank.ca/" }, "resources": [ "code" ], "modality": [], "summary": "GPT-5.5 agents extract source-linked discussions from arXiv papers and coordinate matching groups the evidence into 13,616 galaxy entries." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "pathfinder", "title": "pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy", "venue": "ApJS 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": 8, "arxiv_id": "2408.01556", "doi": "", "url": "https://arxiv.org/abs/2408.01556", "code": [], "links": { "Paper": "https://arxiv.org/abs/2408.01556", "Demo": "https://pfdr.app" }, "resources": [], "modality": [], "summary": "Retrieval-augmented literature search and synthesis over about 350k ADS papers with time and citation weighting." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "cmbagent", "title": "Multi-Agent System for Cosmological Parameter Analysis", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 12, "arxiv_id": "2412.00431", "doi": "", "url": "https://arxiv.org/abs/2412.00431", "code": [ "https://github.com/CMBAgents/cmbagent" ], "links": { "Paper": "https://arxiv.org/abs/2412.00431", "Follow-up": "https://arxiv.org/abs/2507.07257", "Code": "https://github.com/CMBAgents/cmbagent" }, "resources": [ "code" ], "modality": [], "summary": "Planning and control system of about 30 LLM agents for autonomous cosmological data analysis." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "StarWhisper Telescope", "title": "StarWhisper Telescope: An AI Framework for Automating End-to-End Astronomical Observations", "venue": "Commun. Eng. 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 12, "arxiv_id": "2412.06412", "doi": "10.1038/s44172-025-00520-4", "url": "https://arxiv.org/abs/2412.06412", "code": [ "https://github.com/Yu-Yang-Li/StarWhisper/tree/main/projects/ngss" ], "links": { "Paper": "https://arxiv.org/abs/2412.06412", "Code": "https://github.com/Yu-Yang-Li/StarWhisper/tree/main/projects/ngss", "Journal": "https://doi.org/10.1038/s44172-025-00520-4" }, "resources": [ "code" ], "modality": [], "summary": "LLM agent that plans observations, controls a 10-telescope network and runs transient detection for the Nearby Galaxy Supernovae Survey." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "AstroAgents", "title": "AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.23170", "doi": "", "url": "https://arxiv.org/abs/2503.23170", "code": [ "https://github.com/amirgroup-codes/AstroAgents" ], "links": { "Paper": "https://arxiv.org/abs/2503.23170", "Code": "https://github.com/amirgroup-codes/AstroAgents" }, "resources": [ "code" ], "modality": [], "summary": "Multi-agent system that proposes astrobiology hypotheses from mass spectrometry data." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "", "title": "AI Agents for Ground-Based Gamma Astronomy", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.00821", "doi": "", "url": "https://arxiv.org/abs/2503.00821", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.00821" }, "resources": [], "modality": [], "summary": "LLM agent prototypes for CTAO control software and Gammapy analysis code generation with retrieval augmentation." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "AI Cosmologist", "title": "The AI Cosmologist I: An Agentic System for Automated Data Analysis", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 4, "arxiv_id": "2504.03424", "doi": "", "url": "https://arxiv.org/abs/2504.03424", "code": [ "https://github.com/adammoss/aicosmologist" ], "links": { "Paper": "https://arxiv.org/abs/2504.03424", "Code": "https://github.com/adammoss/aicosmologist" }, "resources": [ "code" ], "modality": [], "summary": "Agents for planning, coding, execution, analysis and synthesis that run machine learning experiments on cosmological datasets." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "Mephisto", "title": "Mephisto: Self-Improving Large Language Model-Based Agents for Automated Interpretation of Multi-band Galaxy Observations", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.08354", "doi": "", "url": "https://arxiv.org/abs/2510.08354", "code": [ "https://zenodo.org/records/15589045" ], "links": { "Paper": "https://arxiv.org/abs/2510.08354", "Short Paper": "https://arxiv.org/abs/2409.14807", "Code": "https://zenodo.org/records/15589045" }, "resources": [ "code" ], "modality": [], "summary": "Multi-agent tree search over CIGALE SED models with a self-updating knowledge base, applied to JWST Little Red Dots." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "Denario", "title": "The Denario Project: Deep Knowledge AI Agents for Scientific Discovery", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.26887", "doi": "", "url": "https://arxiv.org/abs/2510.26887", "code": [ "https://github.com/AstroPilot-AI/Denario" ], "links": { "Paper": "https://arxiv.org/abs/2510.26887", "Code": "https://github.com/AstroPilot-AI/Denario", "Demo": "https://huggingface.co/spaces/astropilot-ai/Denario" }, "resources": [ "code" ], "modality": [], "summary": "Modular multi-agent research assistant for idea generation, analysis and paper drafting, using cmbagent as its analysis backend." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "CTAgent / Gammapygpt", "title": "Domain-Specific Agents for Cherenkov Telescope Array Control Software and Gamma-Ray Data Analysis", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.01299", "doi": "", "url": "https://arxiv.org/abs/2510.01299", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.01299" }, "resources": [], "modality": [], "summary": "Agents that generate and validate CTAO control software and Gammapy analysis scripts with automated self-correction." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "auto_research", "title": "A Semi-autonomous Multi-agent Pipeline for High-energy Astrophysics Research with Enforced Provenance and Verifiable Self-extension", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.05251", "doi": "", "url": "https://arxiv.org/abs/2611.05251", "code": [], "links": { "Paper": "https://arxiv.org/abs/2611.05251" }, "resources": [], "modality": [], "summary": "Multi-agent pipeline that retrieves HEASARC data and writes its own tools, tested by reproducing IXPE polarimetry results." }, { "section": "Agents and Retrieval Systems", "subsection": "", "name": "", "title": "Competing with AI Scientists: Agent-Driven Approach to Astrophysics Research", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.09621", "doi": "", "url": "https://arxiv.org/abs/2604.09621", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.09621" }, "resources": [], "modality": [], "summary": "Cmbagent multi-agent workflow with human intervention that builds a weak lensing inference pipeline and took first place in the FAIR Universe Weak Lensing Uncertainty Challenge." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "LenghuSky-8", "title": "LenghuSky-8: An 8-Year All-Sky Cloud Dataset with Star-Aware Masks and Alt-Az Calibration for Segmentation and Nowcasting", "venue": "CVPR Findings 2026", "publication_type": "Conference", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.16429", "doi": "", "url": "https://arxiv.org/abs/2603.16429", "code": [ "https://github.com/ruiyicheng/LenghuSky-8" ], "links": { "Paper": "https://arxiv.org/abs/2603.16429", "Code": "https://github.com/ruiyicheng/LenghuSky-8", "Data": "https://huggingface.co/datasets/ruiyicheng/LenghuSky-8" }, "resources": [ "code", "data" ], "modality": [ "Images", "Time series" ], "summary": "Eight-year dataset of 429,620 all-sky images with star-aware cloud masks and per-pixel altitude-azimuth calibration, supporting DINOv3-based segmentation and short-horizon cloud nowcasting benchmarks for observatory operations." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "", "title": "The Strong Gravitational Lens Finding Challenge", "venue": "A&A 2019", "publication_type": "Journal", "note": "", "year": 2018, "month": 2, "arxiv_id": "1802.03609", "doi": "", "url": "https://arxiv.org/abs/1802.03609", "code": [], "links": { "Paper": "https://arxiv.org/abs/1802.03609" }, "resources": [], "modality": [ "Images" ], "summary": "Open challenge in which participants classified 100,000 simulated space-based and ground-based cutouts as lenses or non-lenses, comparing CNNs, SVMs, arc finders and visual inspection." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "MLGWSC-1", "title": "MLGWSC-1: The First Machine Learning Gravitational-Wave Search Mock Data Challenge", "venue": "PRD 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 9, "arxiv_id": "2209.11146", "doi": "10.1103/PhysRevD.107.023021", "url": "https://arxiv.org/abs/2209.11146", "code": [ "https://github.com/gwastro/ml-mock-data-challenge-1" ], "links": { "Paper": "https://arxiv.org/abs/2209.11146", "Journal": "https://doi.org/10.1103/PhysRevD.107.023021", "Code": "https://github.com/gwastro/ml-mock-data-challenge-1" }, "resources": [ "code" ], "modality": [ "Time series" ], "summary": "Common datasets and metrics for comparing machine learning gravitational-wave search algorithms." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "SKA SDC2", "title": "SKA Science Data Challenge 2: Analysis and Results", "venue": "MNRAS 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 3, "arxiv_id": "2303.07943", "doi": "10.1093/mnras/stad1375", "url": "https://arxiv.org/abs/2303.07943", "code": [], "links": { "Paper": "https://arxiv.org/abs/2303.07943", "Journal": "https://doi.org/10.1093/mnras/stad1375" }, "resources": [], "modality": [ "Data cubes" ], "summary": "Detection and characterisation of 233,245 simulated HI sources in a 2,000 h SKA-MID spectral line cube, with reproducibility awards for open pipelines." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "MiraBest", "title": "MiraBest: A Dataset of Morphologically Classified Radio Galaxies for Machine Learning", "venue": "RASTI 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 5, "arxiv_id": "2305.11108", "doi": "10.1093/rasti/rzad017", "url": "https://arxiv.org/abs/2305.11108", "code": [ "https://github.com/fmporter/MiraBest-full" ], "links": { "Paper": "https://arxiv.org/abs/2305.11108", "Code": "https://github.com/fmporter/MiraBest-full", "Journal": "https://doi.org/10.1093/rasti/rzad017" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "1,256 NVSS and FIRST radio-loud AGN labelled by Fanaroff-Riley class with confidence flags, distributed as a batched dataset for deep learning libraries." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "RadioGalaxyNET", "title": "RadioGalaxyNET: Dataset and Novel Computer Vision Algorithms for the Detection of Extended Radio Galaxies and Infrared Hosts", "venue": "PASA 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 12, "arxiv_id": "2312.00306", "doi": "10.1017/pasa.2023.64", "url": "https://arxiv.org/abs/2312.00306", "code": [], "links": { "Paper": "https://arxiv.org/abs/2312.00306", "Journal": "https://doi.org/10.1017/pasa.2023.64" }, "resources": [], "modality": [ "Images" ], "summary": "2,800 radio and infrared images with 4,155 expert-annotated galaxies in COCO format for multi-component radio galaxy and host detection." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "CosmoBench", "title": "CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning", "venue": "NeurIPS 2025 (Datasets and Benchmarks)", "publication_type": "Conference", "note": "", "year": 2025, "month": 7, "arxiv_id": "2507.03707", "doi": "", "url": "https://arxiv.org/abs/2507.03707", "code": [], "links": { "Paper": "https://arxiv.org/abs/2507.03707" }, "resources": [], "modality": [ "Point clouds" ], "summary": "About 34,000 point clouds from Quijote, CAMELS-SAM and CAMELS together with 25,000 merger trees for cosmological parameter inference and tree tasks." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "SuryaBench", "title": "SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.14107", "doi": "", "url": "https://arxiv.org/abs/2508.14107", "code": [], "links": { "Paper": "https://arxiv.org/abs/2508.14107" }, "resources": [], "modality": [ "Images", "Time series" ], "summary": "Curated SDO core dataset with application benchmarks on active region emergence, flares, magnetic field extrapolation, EUV irradiance and solar wind prediction." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "Mars-Bench", "title": "Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks", "venue": "NeurIPS 2025 (Datasets and Benchmarks)", "publication_type": "Conference", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.24010", "doi": "", "url": "https://arxiv.org/abs/2510.24010", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.24010" }, "resources": [], "modality": [ "Images" ], "summary": "20 orbital and rover image datasets for classification, segmentation and object detection used to compare natural-image, Earth observation and vision-language backbones." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "MMAE", "title": "Multi-Modal Masked Autoencoders for Learning Image-Spectrum Associations for Galaxy Evolution and Cosmology", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.22527", "doi": "", "url": "https://arxiv.org/abs/2510.22527", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.22527" }, "resources": [], "modality": [ "Images", "Spectra" ], "summary": "Paired dataset of 134,533 HSC galaxy images and DESI spectra with a masked autoencoder baseline for cross-modal reconstruction and redshift estimation." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "Moonstone", "title": "Moonstone: A Multimodal Foundation Model and Benchmark for Lunar Remote Sensing", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.03644", "doi": "", "url": "https://arxiv.org/abs/2607.03644", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.03644" }, "resources": [], "modality": [ "Images" ], "summary": "Lunar remote sensing foundation model released with a benchmark of six downstream tasks." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "NuBench", "title": "NuBench: An Open Benchmark for Deep Learning-Based Event Reconstruction in Neutrino Telescopes", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.13111", "doi": "", "url": "https://arxiv.org/abs/2511.13111", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.13111" }, "resources": [], "modality": [ "Point clouds" ], "summary": "Seven simulated neutrino telescope datasets used to compare ParticleNeT, DynEdge, GRIT and DeepIce on energy, direction, topology, vertex and inelasticity reconstruction." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "CraterBench-R", "title": "CraterBench-R: Instance-Level Crater Retrieval for Planetary Scale", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.06245", "doi": "", "url": "https://arxiv.org/abs/2604.06245", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.06245" }, "resources": [], "modality": [ "Images" ], "summary": "Instance retrieval benchmark of about 25,000 Mars CTX crater identities with verified multi-view queries, used to evaluate 30 vision backbones." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "JW-FD", "title": "JW-FD: A Long Horizon Multimodal Solar Flare Forecasting Dataset", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 8, "arxiv_id": "2608.19195", "doi": "", "url": "https://arxiv.org/abs/2608.19195", "code": [], "links": { "Paper": "https://arxiv.org/abs/2608.19195" }, "resources": [], "modality": [ "Images", "Tabular" ], "summary": "Fifteen-year flare forecasting dataset from 2011 to 2025 built from SDO/HMI magnetograms, NOAA region summaries and flare lists, with active region level splits and configurable horizons." }, { "section": "Benchmarks", "subsection": "Data and Modality Benchmarks", "name": "FAIR Universe WL", "title": "FAIR Universe Weak Lensing ML Uncertainty Challenge: Dataset and Cosmological Inference Competition", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.10228", "doi": "", "url": "https://arxiv.org/abs/2611.10228", "code": [ "https://github.com/FAIR-Universe/Cosmology_Challenge" ], "links": { "Paper": "https://arxiv.org/abs/2611.10228", "Data": "https://doi.org/10.5281/zenodo.20056065", "Code": "https://github.com/FAIR-Universe/Cosmology_Challenge" }, "resources": [ "code", "data" ], "modality": [ "Images" ], "summary": "Simulated HSC-like weak lensing convergence maps and a competition scoring cosmological parameter estimates together with their uncertainty calibration." }, { "section": "Benchmarks", "subsection": "Multimodal Model Evaluation", "name": "AstroChart", "title": "DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific Charts", "venue": "AAAI 2026", "publication_type": "Conference", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.19498", "doi": "", "url": "https://arxiv.org/abs/2503.19498", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.19498", "Data": "https://huggingface.co/datasets/yangjing0128/AstroChart" }, "resources": [ "data" ], "modality": [ "Images", "Text" ], "summary": "AstroChart provides 1,690 question-answer pairs over 482 astronomy charts and is used to evaluate 21 MLLMs on perception, numerical reasoning and domain knowledge." }, { "section": "Benchmarks", "subsection": "Multimodal Model Evaluation", "name": "AstroMMBench", "title": "AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.00063", "doi": "", "url": "https://arxiv.org/abs/2510.00063", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.00063" }, "resources": [], "modality": [ "Images", "Text" ], "summary": "621 expert-reviewed multiple-choice questions on astronomical images across six subfields, used to evaluate 25 MLLMs." }, { "section": "Benchmarks", "subsection": "Multimodal Model Evaluation", "name": "MarsRetrieval", "title": "MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 2, "arxiv_id": "2602.13961", "doi": "", "url": "https://arxiv.org/abs/2602.13961", "code": [], "links": { "Paper": "https://arxiv.org/abs/2602.13961" }, "resources": [], "modality": [ "Images", "Text" ], "summary": "Benchmark of vision-language models on retrieval over Mars orbital imagery at planetary scale." }, { "section": "Benchmarks", "subsection": "Multimodal Model Evaluation", "name": "AstroVLBench", "title": "A Systematic Evaluation of Vision-Language Models for Observational Astronomical Reasoning Tasks", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.24589", "doi": "", "url": "https://arxiv.org/abs/2604.24589", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.24589", "Data": "https://huggingface.co/datasets/XiaomanZhang/AstroVLBench" }, "resources": [ "data" ], "modality": [ "Images", "Spectra", "Time series", "Tabular", "Text" ], "summary": "More than 4,100 expert-verified instances over five tasks covering HSC imaging, FIRST and NVSS radio maps, AKARI photometry, PLAsTiCC light curves and optical spectra." }, { "section": "Benchmarks", "subsection": "Multimodal Model Evaluation", "name": "AstroAlertBench", "title": "AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 5, "arxiv_id": "2605.05573", "doi": "", "url": "https://arxiv.org/abs/2605.05573", "code": [ "https://github.com/LLM-for-Astronomy/AstroAlertBench" ], "links": { "Paper": "https://arxiv.org/abs/2605.05573", "Code": "https://github.com/LLM-for-Astronomy/AstroAlertBench" }, "resources": [ "code" ], "modality": [ "Images", "Tabular", "Text" ], "summary": "Evaluates 13 multimodal LLMs on transient alert review through metadata grounding, scientific reasoning and hierarchical classification over five classes." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "AstroMLab 1", "title": "AstroMLab 1: Who Wins Astronomy Jeopardy!?", "venue": "Astron. Comput. 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.11194", "doi": "", "url": "https://arxiv.org/abs/2407.11194", "code": [], "links": { "Paper": "https://arxiv.org/abs/2407.11194" }, "resources": [], "modality": [ "Text" ], "summary": "4,425 multiple-choice questions curated from the Annual Review of Astronomy and Astrophysics for evaluating LLM knowledge recall." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "AstroVisBench", "title": "AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy", "venue": "NeurIPS 2025 (Datasets and Benchmarks)", "publication_type": "Conference", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.20538", "doi": "", "url": "https://arxiv.org/abs/2505.20538", "code": [ "https://github.com/SebaJoe/AstroVisBench" ], "links": { "Paper": "https://arxiv.org/abs/2505.20538", "Code": "https://github.com/SebaJoe/AstroVisBench", "Project": "https://astrovisbench.github.io" }, "resources": [ "code" ], "modality": [ "Text" ], "summary": "864 processing and visualization tasks from 110 NOIRLab and STScI notebooks, scored by execution and a VLM judge." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "Astro-QA", "title": "An Astronomical Question Answering Dataset for Evaluating Large Language Models", "venue": "Scientific Data 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": null, "arxiv_id": "", "doi": "10.1038/s41597-025-04613-9", "url": "https://doi.org/10.1038/s41597-025-04613-9", "code": [], "links": { "Journal": "https://doi.org/10.1038/s41597-025-04613-9", "Data": "https://figshare.com/articles/dataset/Astro-QA/28235639" }, "resources": [ "data" ], "modality": [ "Text" ], "summary": "3,082 English and Chinese questions of six types across astrophysics, astrometry, celestial mechanics, history and techniques, evaluated on 27 LLMs." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "CosmoPaperQA", "title": "Evaluating Retrieval-Augmented Generation Agents for Autonomous Scientific Discovery in Astrophysics", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 7, "arxiv_id": "2507.07155", "doi": "", "url": "https://arxiv.org/abs/2507.07155", "code": [], "links": { "Paper": "https://arxiv.org/abs/2507.07155", "Data": "https://huggingface.co/datasets/ASTROANTS/CosmoPaperQA" }, "resources": [ "data" ], "modality": [ "Text" ], "summary": "105 expert-written question-answer pairs from cosmology papers for comparing retrieval-augmented generation agents against human evaluation." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "IOAA", "title": "Large Language Models Achieve Gold Medal Performance at the International Olympiad on Astronomy & Astrophysics (IOAA)", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.05016", "doi": "", "url": "https://arxiv.org/abs/2510.05016", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.05016" }, "resources": [], "modality": [ "Text" ], "summary": "Evaluates five LLMs on 49 theory and 8 data analysis problems from the 2022 to 2025 IOAA exams." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "ReplicationBench", "title": "ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.24591", "doi": "", "url": "https://arxiv.org/abs/2510.24591", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.24591" }, "resources": [], "modality": [ "Text" ], "summary": "111 tasks derived from 20 astrophysics papers that test whether agents can reproduce published results, with the best models scoring about 20 percent." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "ALeRCE Text-to-SQL", "title": "Querying an Astronomical Database Using Large Language Models: The ALeRCE Text-to-SQL System", "venue": "A&A 2026", "publication_type": "Journal", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.18108", "doi": "", "url": "https://arxiv.org/abs/2606.18108", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.18108" }, "resources": [], "modality": [ "Text" ], "summary": "Evaluates thirteen LLMs on translating natural-language requests into SQL queries over the ALeRCE alert broker database, comparing direct and step-by-step generation." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "Astro2Method", "title": "Astro2Method: Benchmarking LLMs on Machine Learning Method Selection in Astronomy", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 10, "arxiv_id": "2610.30282", "doi": "", "url": "https://arxiv.org/abs/2610.30282", "code": [], "links": { "Paper": "https://arxiv.org/abs/2610.30282", "Data": "https://huggingface.co/datasets/Xingzhongfan/Astro2Method" }, "resources": [ "data" ], "modality": [ "Text" ], "summary": "500 expert-reviewed binary questions from 346 astronomy papers asking which machine learning method performs better for a stated problem." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "", "title": "Reconstructing Implicit Scientific Knowledge: Evaluating LLM Agents through End-to-End Reproduction of Astronomy", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.35900", "doi": "", "url": "https://arxiv.org/abs/2609.35900", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.35900" }, "resources": [], "modality": [ "Text" ], "summary": "Reproduction framework that separates execution from verification, applied to one ApJ and thirteen Nature astronomy papers, eleven of which leave the reproduction path ambiguous." }, { "section": "Benchmarks", "subsection": "Text and Reasoning Evaluation", "name": "", "title": "AI Cosplaying as Astrophysicists: A Controlled Synthetic-Agent Study of AI-Assisted Astrophysical Research Workflows", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.29039", "doi": "", "url": "https://arxiv.org/abs/2603.29039", "code": [], "links": { "Paper": "https://arxiv.org/abs/2603.29039" }, "resources": [], "modality": [ "Text" ], "summary": "Controlled study of 144 synthetic researchers on 2,592 astrophysics assignments, comparing solo work with four styles of AI assistance over 12,960 scored episodes." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "GaMorNet", "title": "Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in ~100,000 SDSS and ~20,000 CANDELS Galaxies", "venue": "ApJ 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": 6, "arxiv_id": "2006.14639", "doi": "", "url": "https://arxiv.org/abs/2006.14639", "code": [ "https://github.com/aritraghsh09/GaMorNet" ], "links": { "Paper": "https://arxiv.org/abs/2006.14639", "Code": "https://github.com/aritraghsh09/GaMorNet" }, "resources": [ "code" ], "modality": [], "summary": "CNN pretrained on simulated galaxies and transferred to SDSS and CANDELS bulge-to-total classification." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "GZ DECaLS", "title": "Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies", "venue": "MNRAS 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 2, "arxiv_id": "2102.08414", "doi": "10.1093/mnras/stab2093", "url": "https://arxiv.org/abs/2102.08414", "code": [ "https://github.com/mwalmsley/zoobot" ], "links": { "Paper": "https://arxiv.org/abs/2102.08414", "Code": "https://github.com/mwalmsley/zoobot", "Data": "https://doi.org/10.5281/zenodo.4196266", "Journal": "https://doi.org/10.1093/mnras/stab2093" }, "resources": [ "code", "data" ], "modality": [], "summary": "7.5M volunteer classifications and Bayesian CNN posteriors for 314k DECaLS galaxies." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification", "venue": "ICECET 2021", "publication_type": "Conference", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.04353", "doi": "10.1109/ICECET52533.2021.9698414", "url": "https://arxiv.org/abs/2111.04353", "code": [], "links": { "Paper": "https://arxiv.org/abs/2111.04353", "Journal": "https://doi.org/10.1109/ICECET52533.2021.9698414" }, "resources": [], "modality": [], "summary": "Compares deep learning architectures for optical galaxy morphology classification using the Zoobot library." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "DeepAstroUDA", "title": "DeepAstroUDA: Semi-Supervised Universal Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection", "venue": "MLST 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 2, "arxiv_id": "2302.02005", "doi": "", "url": "https://arxiv.org/abs/2302.02005", "code": [ "https://github.com/deepskies/DeepAstroUDA" ], "links": { "Paper": "https://arxiv.org/abs/2302.02005", "Code": "https://github.com/deepskies/DeepAstroUDA" }, "resources": [ "code" ], "modality": [], "summary": "Universal domain adaptation between SDSS, DECaLS and LSST mock images that also clusters unknown classes." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Harnessing the Hubble Space Telescope Archives: A Catalog of 21,926 Interacting Galaxies", "venue": "ApJ 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 3, "arxiv_id": "2303.00366", "doi": "10.3847/1538-4357/acc0ff", "url": "https://arxiv.org/abs/2303.00366", "code": [], "links": { "Paper": "https://arxiv.org/abs/2303.00366", "Journal": "https://doi.org/10.3847/1538-4357/acc0ff" }, "resources": [], "modality": [], "summary": "Zoobot-based search of the HST archive for interacting galaxies." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "Astroformer", "title": "Astroformer: More Data Might Not be All You Need for Classification", "venue": "arXiv 2023", "publication_type": "Preprint", "note": "", "year": 2023, "month": 4, "arxiv_id": "2304.05350", "doi": "", "url": "https://arxiv.org/abs/2304.05350", "code": [ "https://github.com/Rishit-dagli/Astroformer" ], "links": { "Paper": "https://arxiv.org/abs/2304.05350", "Code": "https://github.com/Rishit-dagli/Astroformer" }, "resources": [ "code" ], "modality": [], "summary": "Hybrid transformer and convolutional classifier trained in the low-data regime on Galaxy10 DECals." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Transfer Learning for Galaxy Feature Detection: Finding Giant Star-forming Clumps in Low-redshift Galaxies Using Faster Region-based Convolutional Neural Network", "venue": "RASTI 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 12, "arxiv_id": "2312.03503", "doi": "10.1093/rasti/rzae013", "url": "https://arxiv.org/abs/2312.03503", "code": [], "links": { "Paper": "https://arxiv.org/abs/2312.03503", "Journal": "https://doi.org/10.1093/rasti/rzae013" }, "resources": [], "modality": [], "summary": "Object detection of star-forming clumps in galaxy images with transfer learning." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Euclid Preparation. Measuring Detailed Galaxy Morphologies for Euclid with Machine Learning", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 2, "arxiv_id": "2402.10187", "doi": "", "url": "https://arxiv.org/abs/2402.10187", "code": [], "links": { "Paper": "https://arxiv.org/abs/2402.10187" }, "resources": [], "modality": [], "summary": "Zoobot trained to predict detailed morphology for Euclid imaging." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Uncovering Tidal Treasures: Automated Classification of Faint Tidal Features in DECaLS Data", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 4, "arxiv_id": "2404.06487", "doi": "", "url": "https://arxiv.org/abs/2404.06487", "code": [], "links": { "Paper": "https://arxiv.org/abs/2404.06487" }, "resources": [], "modality": [], "summary": "Classification of faint tidal features in DECaLS images using pretrained morphology models." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Galaxy Zoo: Stronger Bars Facilitate Quenching in Star-forming Galaxies", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 5, "arxiv_id": "2405.05960", "doi": "", "url": "https://arxiv.org/abs/2405.05960", "code": [], "links": { "Paper": "https://arxiv.org/abs/2405.05960" }, "resources": [], "modality": [], "summary": "Uses deep learning bar classifications to study the link between bar strength and quenching." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Galaxy Zoo DESI: Large-scale Bars as a Secular Mechanism for Triggering AGN", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 6, "arxiv_id": "2406.20096", "doi": "", "url": "https://arxiv.org/abs/2406.20096", "code": [], "links": { "Paper": "https://arxiv.org/abs/2406.20096" }, "resources": [], "modality": [], "summary": "Uses Galaxy Zoo DESI deep learning morphologies to study bars and AGN." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Euclid Q1: Exploring Galaxy Morphology across Cosmic Time through Sersic Fits", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15309", "doi": "", "url": "https://arxiv.org/abs/2503.15309", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15309" }, "resources": [], "modality": [], "summary": "Euclid Q1 morphology study listed among Zoobot applications." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Euclid Q1: First Visual Morphology Catalogue", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15310", "doi": "", "url": "https://arxiv.org/abs/2503.15310", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15310" }, "resources": [], "modality": [], "summary": "First Euclid visual morphology catalogue produced with Galaxy Zoo volunteers and Zoobot." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Euclid Q1: A First Look at the Fraction of Bars in Massive Galaxies at z < 1", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15311", "doi": "", "url": "https://arxiv.org/abs/2503.15311", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15311" }, "resources": [], "modality": [], "summary": "Bar fraction measurement in Euclid Q1 using machine learning morphology." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "Euclid Q1: A Census of Dwarf Galaxies across a Range of Distances and Environments", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15335", "doi": "", "url": "https://arxiv.org/abs/2503.15335", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15335" }, "resources": [], "modality": [], "summary": "Dwarf galaxy census in Euclid Q1 listed among Zoobot applications." }, { "section": "Galaxies", "subsection": "Morphology and Catalogues", "name": "", "title": "A General-Purpose VLM Can Teach an Astronomy Foundation Model to Better Recognize Galaxy Morphology", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 8, "arxiv_id": "2608.02300", "doi": "", "url": "https://arxiv.org/abs/2608.02300", "code": [], "links": { "Paper": "https://arxiv.org/abs/2608.02300" }, "resources": [], "modality": [], "summary": "Distils a general-purpose VLM answering Galaxy Zoo decision tree questions into Zoobot through side tuning, with teacher uncertainty guiding which galaxies are sent for human labels." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "Weirdest Galaxies", "title": "The Weirdest SDSS Galaxies: Results from an Outlier Detection Algorithm", "venue": "MNRAS 2017", "publication_type": "Journal", "note": "", "year": 2016, "month": 11, "arxiv_id": "1611.07526", "doi": "10.1093/mnras/stw3021", "url": "https://arxiv.org/abs/1611.07526", "code": [ "https://github.com/dalya/WeirdestGalaxies" ], "links": { "Paper": "https://arxiv.org/abs/1611.07526", "Code": "https://github.com/dalya/WeirdestGalaxies", "Journal": "https://doi.org/10.1093/mnras/stw3021" }, "resources": [ "code" ], "modality": [], "summary": "Unsupervised random forest outlier scores for about two million SDSS galaxy spectra." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "Sequencer", "title": "Extracting the Main Trend in a Data Set: The Sequencer Algorithm", "venue": "ApJ 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 6, "arxiv_id": "2006.13948", "doi": "10.3847/1538-4357/abfc4d", "url": "https://arxiv.org/abs/2006.13948", "code": [ "https://github.com/dalya/Sequencer" ], "links": { "Paper": "https://arxiv.org/abs/2006.13948", "Journal": "https://doi.org/10.3847/1538-4357/abfc4d", "Code": "https://github.com/dalya/Sequencer" }, "resources": [ "code" ], "modality": [], "summary": "Unsupervised ordering algorithm that recovers one-dimensional trends in spectra and other datasets." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "Astronomaly", "title": "Astronomaly: Personalised Active Anomaly Detection in Astronomical Data", "venue": "Astron. Comput. 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.11202", "doi": "10.1016/j.ascom.2021.100481", "url": "https://arxiv.org/abs/2010.11202", "code": [ "https://github.com/MichelleLochner/astronomaly" ], "links": { "Paper": "https://arxiv.org/abs/2010.11202", "Journal": "https://doi.org/10.1016/j.ascom.2021.100481", "Protege": "https://arxiv.org/abs/2411.04188", "Code": "https://github.com/MichelleLochner/astronomaly" }, "resources": [ "code" ], "modality": [], "summary": "Active learning framework that combines anomaly scores with user feedback to rank interesting objects." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "HSC Anomalies", "title": "Anomaly Detection in Hyper Suprime-Cam Galaxy Images with Generative Adversarial Networks", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 5, "arxiv_id": "2105.02434", "doi": "", "url": "https://arxiv.org/abs/2105.02434", "code": [ "https://github.com/kstoreyf/anomalies-GAN-HSC" ], "links": { "Paper": "https://arxiv.org/abs/2105.02434", "Code": "https://github.com/kstoreyf/anomalies-GAN-HSC", "Workshop Version": "https://arxiv.org/abs/2012.08082" }, "resources": [ "code" ], "modality": [], "summary": "Wasserstein GAN anomaly scores for HSC galaxy images." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "DeepAdversaries", "title": "DeepAdversaries: Examining the Robustness of Deep Learning Models for Galaxy Morphology Classification", "venue": "MLST 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 12, "arxiv_id": "2112.14299", "doi": "10.1088/2632-2153/ac7f1a", "url": "https://arxiv.org/abs/2112.14299", "code": [ "https://github.com/AleksCipri/DeepAdversaries" ], "links": { "Paper": "https://arxiv.org/abs/2112.14299", "Journal": "https://doi.org/10.1088/2632-2153/ac7f1a", "Code": "https://github.com/AleksCipri/DeepAdversaries" }, "resources": [ "code" ], "modality": [], "summary": "Studies the robustness of galaxy morphology classifiers to image perturbations." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "", "title": "Astronomaly at Scale: Searching for Anomalies Amongst 4 Million Galaxies", "venue": "MNRAS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 9, "arxiv_id": "2309.08660", "doi": "10.1093/mnras/stae496", "url": "https://arxiv.org/abs/2309.08660", "code": [], "links": { "Paper": "https://arxiv.org/abs/2309.08660", "Journal": "https://doi.org/10.1093/mnras/stae496" }, "resources": [], "modality": [], "summary": "Applies Astronomaly to about 4M galaxies using pretrained Zoobot representations." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "", "title": "Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations", "venue": "MNRAS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 11, "arxiv_id": "2311.14157", "doi": "10.1093/mnras/stae926", "url": "https://arxiv.org/abs/2311.14157", "code": [], "links": { "Paper": "https://arxiv.org/abs/2311.14157", "Journal": "https://doi.org/10.1093/mnras/stae926" }, "resources": [], "modality": [], "summary": "Self-supervised features with clustering, artefact removal, anomaly detection and similarity search on survey images." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "AnomalyMatch", "title": "AnomalyMatch: Discovering Rare Objects of Interest with Semi-supervised and Active Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.03509", "doi": "", "url": "https://arxiv.org/abs/2505.03509", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.03509" }, "resources": [], "modality": [], "summary": "FixMatch with EfficientNet and a user-in-the-loop active learning interface, integrated into ESA Datalabs." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "AnomalyMatch HLA", "title": "Identifying Astrophysical Anomalies in 99.6 Million Source Cutouts from the Hubble Legacy Archive Using AnomalyMatch", "venue": "A&A 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.03508", "doi": "", "url": "https://arxiv.org/abs/2505.03508", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.03508" }, "resources": [], "modality": [], "summary": "Applies AnomalyMatch to the full Hubble Legacy Archive and reports 1,176 new anomalies across 19 classes." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "Coniferest", "title": "Coniferest: A Complete Active Anomaly Detection Framework", "venue": "Astron. Comput. 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": null, "arxiv_id": "", "doi": "10.1016/j.ascom.2025.100960", "url": "https://doi.org/10.1016/j.ascom.2025.100960", "code": [ "https://github.com/snad-space/coniferest" ], "links": { "Code": "https://github.com/snad-space/coniferest", "Journal": "https://doi.org/10.1016/j.ascom.2025.100960" }, "resources": [ "code" ], "modality": [], "summary": "Isolation-forest based active anomaly detection with expert feedback, used by the SNAD team on ZTF data." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "", "title": "Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.23749", "doi": "", "url": "https://arxiv.org/abs/2510.23749", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.23749" }, "resources": [], "modality": [], "summary": "Sparse autoencoders on Zoobot and masked-autoencoder embeddings of Euclid Q1 galaxies to surface interpretable features." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "astromorph", "title": "astromorph: Self-supervised Machine Learning Pipeline for Astronomical Morphology Analysis", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 2, "arxiv_id": "2602.09223", "doi": "", "url": "https://arxiv.org/abs/2602.09223", "code": [], "links": { "Paper": "https://arxiv.org/abs/2602.09223" }, "resources": [], "modality": [], "summary": "BYOL-based embedding pipeline applied to ALMA protoplanetary disks and infrared dark clouds." }, { "section": "Galaxies", "subsection": "Anomaly Detection", "name": "", "title": "Agentic Active Learning Meets Visual Embeddings: Finding Anomalies among 370 000 Variable Stars from ASAS-SN", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 8, "arxiv_id": "2608.23688", "doi": "", "url": "https://arxiv.org/abs/2608.23688", "code": [], "links": { "Paper": "https://arxiv.org/abs/2608.23688" }, "resources": [], "modality": [], "summary": "DINOv2 light-curve embeddings, isolation forests and multimodal LLM agents that vet anomaly candidates." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "ANNz2", "title": "ANNz2: Photometric Redshift and Probability Distribution Function Estimation Using Machine Learning", "venue": "PASP 2016", "publication_type": "Journal", "note": "", "year": 2015, "month": 7, "arxiv_id": "1507.00490", "doi": "", "url": "https://arxiv.org/abs/1507.00490", "code": [ "https://github.com/IftachSadeh/ANNZ" ], "links": { "Paper": "https://arxiv.org/abs/1507.00490", "Code": "https://github.com/IftachSadeh/ANNZ" }, "resources": [ "code" ], "modality": [], "summary": "Ensembles of neural networks and boosted decision trees for photometric redshift PDFs." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "Delight", "title": "Data-driven, Interpretable Photometric Redshifts Trained on Heterogeneous and Unrepresentative Data", "venue": "ApJ 2017", "publication_type": "Journal", "note": "", "year": 2016, "month": 12, "arxiv_id": "1612.00847", "doi": "", "url": "https://arxiv.org/abs/1612.00847", "code": [ "https://github.com/ixkael/Delight" ], "links": { "Paper": "https://arxiv.org/abs/1612.00847", "Code": "https://github.com/ixkael/Delight" }, "resources": [ "code" ], "modality": [], "summary": "Gaussian process photometric redshifts that combine templates with data-driven flux modeling." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "Pasquet Photo-z", "title": "Photometric Redshifts from SDSS Images Using a Convolutional Neural Network", "venue": "A&A 2019", "publication_type": "Journal", "note": "", "year": 2018, "month": 6, "arxiv_id": "1806.06607", "doi": "", "url": "https://arxiv.org/abs/1806.06607", "code": [ "https://github.com/jpasquet/photoz" ], "links": { "Paper": "https://arxiv.org/abs/1806.06607", "Code": "https://github.com/jpasquet/photoz" }, "resources": [ "code" ], "modality": [], "summary": "CNN that predicts redshift probability densities directly from multiband SDSS images." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "dense_basis", "title": "Nonparametric Star Formation History Reconstruction with Gaussian Processes. I. Counting Major Episodes of Star Formation", "venue": "ApJ 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": null, "arxiv_id": "", "doi": "10.3847/1538-4357/ab2052", "url": "https://doi.org/10.3847/1538-4357/ab2052", "code": [ "https://github.com/kartheikiyer/dense_basis" ], "links": { "Journal": "https://doi.org/10.3847/1538-4357/ab2052", "Code": "https://github.com/kartheikiyer/dense_basis" }, "resources": [ "code" ], "modality": [], "summary": "Gaussian process representation of galaxy star formation histories for SED fitting." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "speculator", "title": "SPECULATOR: Emulating Stellar Population Synthesis for Fast and Accurate Galaxy Spectra and Photometry", "venue": "ApJS 2020", "publication_type": "Journal", "note": "", "year": 2019, "month": 11, "arxiv_id": "1911.11778", "doi": "10.3847/1538-4365/ab917f", "url": "https://arxiv.org/abs/1911.11778", "code": [ "https://github.com/justinalsing/speculator" ], "links": { "Paper": "https://arxiv.org/abs/1911.11778", "Code": "https://github.com/justinalsing/speculator", "Journal": "https://doi.org/10.3847/1538-4365/ab917f" }, "resources": [ "code" ], "modality": [], "summary": "Neural network emulator of stellar population synthesis for fast SED fitting." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "PROVABGS", "title": "The DESI PRObabilistic Value-Added Bright Galaxy Survey (PROVABGS) Mock Challenge", "venue": "ApJ 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 2, "arxiv_id": "2202.01809", "doi": "10.3847/1538-4357/ac8983", "url": "https://arxiv.org/abs/2202.01809", "code": [ "https://github.com/changhoonhahn/provabgs" ], "links": { "Paper": "https://arxiv.org/abs/2202.01809", "Journal": "https://doi.org/10.3847/1538-4357/ac8983", "Code": "https://github.com/changhoonhahn/provabgs" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian SED modeling pipeline for DESI BGS that uses neural emulators for speed." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "SEDflow", "title": "Accelerated Bayesian SED Modeling Using Amortized Neural Posterior Estimation", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 3, "arxiv_id": "2203.07391", "doi": "10.3847/1538-4357/ac7b84", "url": "https://arxiv.org/abs/2203.07391", "code": [ "https://github.com/changhoonhahn/SEDflow" ], "links": { "Paper": "https://arxiv.org/abs/2203.07391", "Code": "https://github.com/changhoonhahn/SEDflow", "Journal": "https://doi.org/10.3847/1538-4357/ac7b84" }, "resources": [ "code" ], "modality": [], "summary": "Amortized neural posterior estimation of 12 SED parameters in about one second per galaxy." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "GaMPEN", "title": "GaMPEN: A Machine-learning Framework for Estimating Bayesian Posteriors of Galaxy Morphological Parameters", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 7, "arxiv_id": "2207.05107", "doi": "", "url": "https://arxiv.org/abs/2207.05107", "code": [ "https://github.com/aritraghsh09/GaMPEN" ], "links": { "Paper": "https://arxiv.org/abs/2207.05107", "Code": "https://github.com/aritraghsh09/GaMPEN" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian CNN that predicts posteriors of bulge-to-total ratio, effective radius and flux." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "Mangrove", "title": "Mangrove: Learning Galaxy Properties from Merger Trees", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 10, "arxiv_id": "2210.13473", "doi": "", "url": "https://arxiv.org/abs/2210.13473", "code": [ "https://github.com/astrockragh/Mangrove" ], "links": { "Paper": "https://arxiv.org/abs/2210.13473", "Code": "https://github.com/astrockragh/Mangrove" }, "resources": [ "code" ], "modality": [], "summary": "Graph neural networks on dark matter merger trees that emulate semi-analytic galaxy properties." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "SBI++", "title": "SBI++: Flexible, Ultra-fast Likelihood-free Inference Customized for Astronomical Applications", "venue": "ApJL 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 4, "arxiv_id": "2304.05281", "doi": "", "url": "https://arxiv.org/abs/2304.05281", "code": [ "https://github.com/wangbingjie/sbi_pp" ], "links": { "Paper": "https://arxiv.org/abs/2304.05281", "Code": "https://github.com/wangbingjie/sbi_pp" }, "resources": [ "code" ], "modality": [], "summary": "Neural posterior estimation for galaxy SED fitting that handles missing data and out-of-distribution noise." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "pzflow", "title": "Probabilistic Forward Modeling of Galaxy Catalogs with Normalizing Flows", "venue": "AJ 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": 5, "arxiv_id": "2405.04740", "doi": "", "url": "https://arxiv.org/abs/2405.04740", "code": [ "https://github.com/jfcrenshaw/pzflow" ], "links": { "Paper": "https://arxiv.org/abs/2405.04740", "Code": "https://github.com/jfcrenshaw/pzflow" }, "resources": [ "code" ], "modality": [], "summary": "Normalizing flows for modeling galaxy catalogs and photometric redshift posteriors." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "", "title": "Galaxy Spectroscopy without Spectra: Galaxy Properties from Photometric Images with Conditional Diffusion Models", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 6, "arxiv_id": "2406.18175", "doi": "", "url": "https://arxiv.org/abs/2406.18175", "code": [], "links": { "Paper": "https://arxiv.org/abs/2406.18175" }, "resources": [], "modality": [], "summary": "Diffusion model with contrastive networks that predicts optical spectra and photometric redshifts from SDSS images." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "CLAP", "title": "CLAP. I. Resolving Miscalibration for Deep Learning-based Galaxy Photometric Redshift Estimation", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 10, "arxiv_id": "2410.19390", "doi": "", "url": "https://arxiv.org/abs/2410.19390", "code": [], "links": { "Paper": "https://arxiv.org/abs/2410.19390" }, "resources": [], "modality": [], "summary": "Supervised contrastive learning with adaptive KNN to calibrate photometric redshift probability densities." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "Hybrid-z", "title": "Hybrid-z: Enhancing the Kilo-Degree Survey Bright Galaxy Sample Photometric Redshifts with Deep Learning", "venue": "A&A 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": 1, "arxiv_id": "2501.01942", "doi": "", "url": "https://arxiv.org/abs/2501.01942", "code": [], "links": { "Paper": "https://arxiv.org/abs/2501.01942" }, "resources": [], "modality": [], "summary": "Inception CNN on four-band images combined with an MLP on nine-band magnitudes for 1.2 million KiDS-Bright galaxies." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "RAIL", "title": "Redshift Assessment Infrastructure Layers (RAIL): Rubin-era Photometric Redshift Stress-testing and At-scale Production", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.02928", "doi": "", "url": "https://arxiv.org/abs/2505.02928", "code": [ "https://github.com/LSSTDESC/rail" ], "links": { "Paper": "https://arxiv.org/abs/2505.02928", "Code": "https://github.com/LSSTDESC/rail" }, "resources": [ "code" ], "modality": [], "summary": "LSST DESC framework for training, evaluating and running photometric redshift estimators." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "", "title": "Template-Fitting Meets Deep Learning: Redshift Estimation Using Physics-Guided Neural Networks", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 7, "arxiv_id": "2507.00866", "doi": "", "url": "https://arxiv.org/abs/2507.00866", "code": [], "links": { "Paper": "https://arxiv.org/abs/2507.00866" }, "resources": [], "modality": [], "summary": "Multimodal network with cross-attention and Bayesian layers that integrates SED templates on HSC PDR3 data." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "", "title": "Deep Learning Improves Photometric Redshifts in All Regions of Color Space", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 7, "arxiv_id": "2507.06299", "doi": "", "url": "https://arxiv.org/abs/2507.06299", "code": [], "links": { "Paper": "https://arxiv.org/abs/2507.06299" }, "resources": [], "modality": [], "summary": "Self-organizing map analysis showing lower scatter and attenuation bias for image-based photo-z on SDSS." }, { "section": "Galaxies", "subsection": "Physical Properties and Photometric Redshifts", "name": "PITA", "title": "Optimizing Deep Learning Photometric Redshifts for the Roman Space Telescope with HST/CANDELS", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 2, "arxiv_id": "2602.10207", "doi": "", "url": "https://arxiv.org/abs/2602.10207", "code": [], "links": { "Paper": "https://arxiv.org/abs/2602.10207" }, "resources": [], "modality": [], "summary": "Semi-supervised network that combines contrastive, color and redshift losses on CANDELS images." }, { "section": "Gravitational Lensing", "subsection": "", "name": "SHINE", "title": "SHINE: Shear inference environment - Generative forward modelling for radio weak gravitational lensing", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.14301", "doi": "", "url": "https://arxiv.org/abs/2611.14301", "code": [ "https://github.com/CentofantiEze/Radio_WL_Generative_Forward_Model" ], "links": { "Paper": "https://arxiv.org/abs/2611.14301", "Code": "https://github.com/CentofantiEze/Radio_WL_Generative_Forward_Model", "Model": "https://zenodo.org/records/21131669" }, "resources": [ "code", "model", "data" ], "modality": [], "summary": "A convolutional autoencoder trained on HST COSMOS galaxy images supplies morphologies for shear inference on 10,000 simulated radio interferometric visibilities." }, { "section": "Gravitational Lensing", "subsection": "", "name": "CMU DeepLens", "title": "CMU DeepLens: Deep Learning for Automatic Image-based Galaxy-Galaxy Strong Lens Finding", "venue": "MNRAS 2018", "publication_type": "Journal", "note": "", "year": 2017, "month": 3, "arxiv_id": "1703.02642", "doi": "", "url": "https://arxiv.org/abs/1703.02642", "code": [ "https://github.com/McWilliamsCenter/CMUDeepLens" ], "links": { "Paper": "https://arxiv.org/abs/1703.02642", "Code": "https://github.com/McWilliamsCenter/CMUDeepLens" }, "resources": [ "code" ], "modality": [], "summary": "Residual network strong lens finder." }, { "section": "Gravitational Lensing", "subsection": "", "name": "DeepMass", "title": "Deep Learning Dark Matter Map Reconstructions from DES SV Weak Lensing Data", "venue": "MNRAS 2020", "publication_type": "Journal", "note": "", "year": 2019, "month": 8, "arxiv_id": "1908.00543", "doi": "", "url": "https://arxiv.org/abs/1908.00543", "code": [ "https://github.com/NiallJeffrey/DeepMass" ], "links": { "Paper": "https://arxiv.org/abs/1908.00543", "Code": "https://github.com/NiallJeffrey/DeepMass" }, "resources": [ "code" ], "modality": [], "summary": "U-Net mass mapping of Dark Energy Survey Science Verification weak lensing data." }, { "section": "Gravitational Lensing", "subsection": "", "name": "Substructure Mining", "title": "Mining for Dark Matter Substructure: Inferring Subhalo Population Properties from Strong Lenses with Machine Learning", "venue": "ApJ 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 9, "arxiv_id": "1909.02005", "doi": "10.3847/1538-4357/ab4c41", "url": "https://arxiv.org/abs/1909.02005", "code": [ "https://github.com/smsharma/mining-for-substructure-lens" ], "links": { "Paper": "https://arxiv.org/abs/1909.02005", "Journal": "https://doi.org/10.3847/1538-4357/ab4c41", "Code": "https://github.com/smsharma/mining-for-substructure-lens" }, "resources": [ "code" ], "modality": [], "summary": "Likelihood-ratio estimation with neural networks for subhalo population inference from lensed images." }, { "section": "Gravitational Lensing", "subsection": "", "name": "DeepLense", "title": "Deep Learning the Morphology of Dark Matter Substructure", "venue": "ApJ 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": null, "arxiv_id": "", "doi": "10.3847/1538-4357/ab7925", "url": "https://doi.org/10.3847/1538-4357/ab7925", "code": [ "https://github.com/ML4SCI/DeepLense" ], "links": { "Journal": "https://doi.org/10.3847/1538-4357/ab7925", "Code": "https://github.com/ML4SCI/DeepLense" }, "resources": [ "code" ], "modality": [], "summary": "Classifies strong lensing images by dark matter substructure type with deep learning." }, { "section": "Gravitational Lensing", "subsection": "", "name": "ovejero", "title": "Hierarchical Inference with Bayesian Neural Networks: An Application to Strong Gravitational Lensing", "venue": "ApJ 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.13787", "doi": "", "url": "https://arxiv.org/abs/2010.13787", "code": [ "https://github.com/swagnercarena/ovejero" ], "links": { "Paper": "https://arxiv.org/abs/2010.13787", "Code": "https://github.com/swagnercarena/ovejero" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian neural networks for population-level lens parameter inference." }, { "section": "Gravitational Lensing", "subsection": "", "name": "h0rton", "title": "Large-scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant", "venue": "ApJ 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 12, "arxiv_id": "2012.00042", "doi": "", "url": "https://arxiv.org/abs/2012.00042", "code": [ "https://github.com/jiwoncpark/h0rton" ], "links": { "Paper": "https://arxiv.org/abs/2012.00042", "Code": "https://github.com/jiwoncpark/h0rton" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian neural network lens modeling for time-delay cosmography." }, { "section": "Gravitational Lensing", "subsection": "", "name": "deeplenstronomy", "title": "deeplenstronomy: A Dataset Simulation Package for Strong Gravitational Lensing", "venue": "JOSS 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 2, "arxiv_id": "2102.02830", "doi": "10.21105/joss.02854", "url": "https://arxiv.org/abs/2102.02830", "code": [ "https://github.com/deepskies/deeplenstronomy" ], "links": { "Paper": "https://arxiv.org/abs/2102.02830", "Code": "https://github.com/deepskies/deeplenstronomy", "Journal": "https://doi.org/10.21105/joss.02854" }, "resources": [ "code" ], "modality": [], "summary": "Configuration-driven simulation of strong lensing training sets for deep learning." }, { "section": "Gravitational Lensing", "subsection": "", "name": "Lens Mining", "title": "Mining for Strong Gravitational Lenses with Self-supervised Learning", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 10, "arxiv_id": "2110.00023", "doi": "10.3847/1538-4357/ac6d63", "url": "https://arxiv.org/abs/2110.00023", "code": [ "https://github.com/georgestein/ssl-legacysurvey" ], "links": { "Paper": "https://arxiv.org/abs/2110.00023", "Journal": "https://doi.org/10.3847/1538-4357/ac6d63", "Code": "https://github.com/georgestein/ssl-legacysurvey" }, "resources": [ "code" ], "modality": [], "summary": "Self-supervised representations of DESI Legacy Survey images used to find new strong lens candidates." }, { "section": "Gravitational Lensing", "subsection": "", "name": "GIGA-Lens", "title": "GIGA-Lens: Fast Bayesian Inference for Strong Gravitational Lens Modeling", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 2, "arxiv_id": "2202.07663", "doi": "", "url": "https://arxiv.org/abs/2202.07663", "code": [ "https://github.com/giga-lens/gigalens" ], "links": { "Paper": "https://arxiv.org/abs/2202.07663", "Code": "https://github.com/giga-lens/gigalens" }, "resources": [ "code" ], "modality": [], "summary": "GPU-accelerated lens modeling with gradient-based optimization, variational inference and HMC." }, { "section": "Gravitational Lensing", "subsection": "", "name": "paltas", "title": "From Images to Dark Matter: End-to-end Inference of Substructure from Hundreds of Strong Gravitational Lenses", "venue": "ApJ 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 3, "arxiv_id": "2203.00690", "doi": "", "url": "https://arxiv.org/abs/2203.00690", "code": [ "https://github.com/swagnercarena/paltas" ], "links": { "Paper": "https://arxiv.org/abs/2203.00690", "Code": "https://github.com/swagnercarena/paltas" }, "resources": [ "code" ], "modality": [], "summary": "Simulation-based inference of subhalo mass function parameters from many lenses." }, { "section": "Gravitational Lensing", "subsection": "", "name": "Score Lensing", "title": "Posterior Samples of Source Galaxies in Strong Gravitational Lenses with Score-Based Priors", "venue": "arXiv 2022", "publication_type": "Preprint", "note": "", "year": 2022, "month": 11, "arxiv_id": "2211.03812", "doi": "", "url": "https://arxiv.org/abs/2211.03812", "code": [ "https://github.com/AlexandreAdam/score_models" ], "links": { "Paper": "https://arxiv.org/abs/2211.03812", "Code": "https://github.com/AlexandreAdam/score_models" }, "resources": [ "code" ], "modality": [], "summary": "Score-based generative priors for lensed source reconstruction." }, { "section": "Gravitational Lensing", "subsection": "", "name": "caustics", "title": "Caustics: A Python Package for Accelerated Strong Gravitational Lensing Simulations", "venue": "JOSS 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": 6, "arxiv_id": "2406.15542", "doi": "", "url": "https://arxiv.org/abs/2406.15542", "code": [ "https://github.com/Ciela-Institute/caustics" ], "links": { "Paper": "https://arxiv.org/abs/2406.15542", "Code": "https://github.com/Ciela-Institute/caustics" }, "resources": [ "code" ], "modality": [], "summary": "Differentiable, GPU-accelerated lensing simulator for machine learning workflows." }, { "section": "Gravitational Lensing", "subsection": "", "name": "", "title": "Euclid: Finding Strong Gravitational Lenses in the Early Release Observations Using Convolutional Neural Networks", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 2, "arxiv_id": "2502.09802", "doi": "", "url": "https://arxiv.org/abs/2502.09802", "code": [], "links": { "Paper": "https://arxiv.org/abs/2502.09802" }, "resources": [], "modality": [], "summary": "Five CNN lens finders applied to 13 Euclid ERO fields, followed by visual inspection and spectroscopic confirmation." }, { "section": "Gravitational Lensing", "subsection": "", "name": "", "title": "Euclid Q1: The Strong Lensing Discovery Engine A, System Overview and Lens Catalogue", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15324", "doi": "", "url": "https://arxiv.org/abs/2503.15324", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15324" }, "resources": [], "modality": [], "summary": "Overview of the Euclid Q1 strong lens search combining volunteers and machine learning." }, { "section": "Gravitational Lensing", "subsection": "", "name": "", "title": "Euclid Q1: The Strong Lensing Discovery Engine C, Finding Lenses with Machine Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15326", "doi": "", "url": "https://arxiv.org/abs/2503.15326", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15326" }, "resources": [], "modality": [], "summary": "Machine learning lens finders applied to Euclid Q1." }, { "section": "Gravitational Lensing", "subsection": "", "name": "", "title": "Euclid Q1: The Strong Lensing Discovery Engine D, Double-Source-Plane Lens Candidates", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15327", "doi": "", "url": "https://arxiv.org/abs/2503.15327", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15327" }, "resources": [], "modality": [], "summary": "Double-source-plane lens candidates from the Euclid Q1 search." }, { "section": "Gravitational Lensing", "subsection": "", "name": "", "title": "Euclid Q1: The Strong Lensing Discovery Engine E, Ensemble Classification of Strong Gravitational Lenses", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15328", "doi": "", "url": "https://arxiv.org/abs/2503.15328", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15328" }, "resources": [], "modality": [], "summary": "Ensemble classification of lens candidates and lessons for Euclid DR1." }, { "section": "Gravitational Lensing", "subsection": "", "name": "LEMON", "title": "Euclid Quick Data Release (Q1). LEMON -- Lens Modelling with Neural Networks. Automated and Fast Modelling of Euclid Gravitational Lenses with a Singular Isothermal Ellipsoid Mass Profile", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.15329", "doi": "", "url": "https://arxiv.org/abs/2503.15329", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.15329" }, "resources": [], "modality": [], "summary": "Bayesian neural network that predicts lens mass and light parameters and initialises classical lens modelling." }, { "section": "Gravitational Lensing", "subsection": "", "name": "GLUE I", "title": "Gravitational Lenses in UNIONS and Euclid (GLUE) I: A Search for Strong Gravitational Lenses in UNIONS with Subaru, CFHT, and Pan-STARRS Data", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.05032", "doi": "", "url": "https://arxiv.org/abs/2505.05032", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.05032" }, "resources": [], "modality": [], "summary": "ResNet lens finder based on CMU-DeepLens applied to 8 million UNIONS galaxies." }, { "section": "Gravitational Lensing", "subsection": "", "name": "", "title": "Euclid Quick Data Release (Q1). Searching for Giant Gravitational Arcs in Galaxy Clusters with Mask Region-based Convolutional Neural Networks", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.03064", "doi": "", "url": "https://arxiv.org/abs/2511.03064", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.03064" }, "resources": [], "modality": [], "summary": "Mask R-CNN instance segmentation of cluster-scale lensed arcs trained on Euclidised HST simulations." }, { "section": "Gravitational Lensing", "subsection": "", "name": "AgileLens", "title": "Euclid Quick Data Release (Q1). AgileLens: A Scalable CNN-Based Pipeline for Strong Gravitational Lens Identification", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.06648", "doi": "", "url": "https://arxiv.org/abs/2604.06648", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.06648" }, "resources": [], "modality": [], "summary": "Iterative fine-tuning of a modified VGG16 from 27 seed lenses to 30,686 training images, yielding 441 grade A or B candidates in Euclid Q1, 130 of them new." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "scarlet", "title": "scarlet: Source Separation in Multi-band Images by Constrained Matrix Factorization", "venue": "Astron. Comput. 2018", "publication_type": "Journal", "note": "", "year": 2018, "month": 2, "arxiv_id": "1802.10157", "doi": "10.1016/j.ascom.2018.07.001", "url": "https://arxiv.org/abs/1802.10157", "code": [ "https://github.com/pmelchior/scarlet" ], "links": { "Paper": "https://arxiv.org/abs/1802.10157", "Code": "https://github.com/pmelchior/scarlet", "Journal": "https://doi.org/10.1016/j.ascom.2018.07.001" }, "resources": [ "code" ], "modality": [], "summary": "Constrained matrix factorization deblender for multiband survey images." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "Astro R-CNN", "title": "Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning", "venue": "MNRAS 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": null, "arxiv_id": "", "doi": "10.1093/mnras/stz2845", "url": "https://doi.org/10.1093/mnras/stz2845", "code": [ "https://github.com/burke86/astro_rcnn" ], "links": { "Journal": "https://doi.org/10.1093/mnras/stz2845", "Code": "https://github.com/burke86/astro_rcnn" }, "resources": [ "code" ], "modality": [], "summary": "Instance segmentation for joint detection, deblending and star-galaxy classification." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "DeblenderVAE", "title": "Deblending Galaxies with Variational Autoencoders: A Joint Multi-band, Multi-instrument Approach", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 5, "arxiv_id": "2005.12039", "doi": "10.1093/mnras/staa3062", "url": "https://arxiv.org/abs/2005.12039", "code": [ "https://github.com/LSSTDESC/DeblenderVAE", "https://github.com/astrodeepnet/debvader" ], "links": { "Paper": "https://arxiv.org/abs/2005.12039", "Journal": "https://doi.org/10.1093/mnras/staa3062", "Code": "https://github.com/LSSTDESC/DeblenderVAE", "Updated Code": "https://github.com/astrodeepnet/debvader" }, "resources": [ "code" ], "modality": [], "summary": "VAE-based deblender trained jointly on ground and space-based simulated images." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "galsim-hub", "title": "Deep Generative Models for Galaxy Image Simulations", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 8, "arxiv_id": "2008.03833", "doi": "", "url": "https://arxiv.org/abs/2008.03833", "code": [ "https://github.com/McWilliamsCenter/galsim_hub" ], "links": { "Paper": "https://arxiv.org/abs/2008.03833", "Code": "https://github.com/McWilliamsCenter/galsim_hub" }, "resources": [ "code" ], "modality": [], "summary": "Conditional generative models of galaxy light profiles integrated with GalSim." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "MuyGPs Star-Galaxy", "title": "Star-Galaxy Separation via Gaussian Processes with Model Reduction", "venue": "arXiv 2020", "publication_type": "Preprint", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.06094", "doi": "", "url": "https://arxiv.org/abs/2010.06094", "code": [ "https://github.com/LLNL/MuyGPyS" ], "links": { "Paper": "https://arxiv.org/abs/2010.06094", "Code": "https://github.com/LLNL/MuyGPyS" }, "resources": [ "code" ], "modality": [], "summary": "Gaussian process classification of stars and galaxies with dimensionality reduction." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "PS1 Point Source Catalog II", "title": "A Morphological Classification Model to Identify Unresolved PanSTARRS1 Sources II: Update to the PS1 Point Source Catalog", "venue": "PASP 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 12, "arxiv_id": "2012.01544", "doi": "", "url": "https://arxiv.org/abs/2012.01544", "code": [ "https://github.com/adamamiller/PS1_star_galaxy" ], "links": { "Paper": "https://arxiv.org/abs/2012.01544", "Code": "https://github.com/adamamiller/PS1_star_galaxy" }, "resources": [ "code" ], "modality": [], "summary": "Random forest star and galaxy separation for Pan-STARRS1 sources." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "MuyGPs Star-Galaxy Images", "title": "Star-Galaxy Image Separation with Computationally Efficient Gaussian Process Classification", "venue": "AJ 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 5, "arxiv_id": "2105.01106", "doi": "10.3847/1538-3881/ac4e93", "url": "https://arxiv.org/abs/2105.01106", "code": [ "https://github.com/LLNL/MuyGPyS" ], "links": { "Paper": "https://arxiv.org/abs/2105.01106", "Journal": "https://doi.org/10.3847/1538-3881/ac4e93", "Code": "https://github.com/LLNL/MuyGPyS" }, "resources": [ "code" ], "modality": [], "summary": "Scalable local Gaussian process classification of star and galaxy image cutouts." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "MuyGPs Blends", "title": "Gaussian Process Classification for Galaxy Blend Identification in LSST", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 7, "arxiv_id": "2107.09246", "doi": "10.3847/1538-4357/ac35ca", "url": "https://arxiv.org/abs/2107.09246", "code": [ "https://github.com/LLNL/MuyGPyS" ], "links": { "Paper": "https://arxiv.org/abs/2107.09246", "Journal": "https://doi.org/10.3847/1538-4357/ac35ca", "Code": "https://github.com/LLNL/MuyGPyS" }, "resources": [ "code" ], "modality": [], "summary": "Gaussian process classifiers that flag blended galaxies in simulated LSST images." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "astroddpm", "title": "Realistic Galaxy Image Simulation via Score-Based Generative Models", "venue": "MNRAS 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.01713", "doi": "", "url": "https://arxiv.org/abs/2111.01713", "code": [ "https://github.com/Smith42/astroddpm" ], "links": { "Paper": "https://arxiv.org/abs/2111.01713", "Code": "https://github.com/Smith42/astroddpm" }, "resources": [ "code" ], "modality": [], "summary": "Denoising diffusion models that generate realistic galaxy images." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "WaveDiff", "title": "Rethinking Data-driven Point Spread Function Modeling with a Differentiable Optical Model", "venue": "Inverse Problems 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 3, "arxiv_id": "2203.04908", "doi": "", "url": "https://arxiv.org/abs/2203.04908", "code": [ "https://github.com/CosmoStat/wf-psf" ], "links": { "Paper": "https://arxiv.org/abs/2203.04908", "Code": "https://github.com/CosmoStat/wf-psf" }, "resources": [ "code" ], "modality": [], "summary": "Differentiable wavefront-based PSF model that captures chromatic variations for Euclid-like telescopes." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "MuyGPs Stellar Blends", "title": "Stellar Blend Image Classification Using Computationally Efficient Gaussian Processes", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.19297", "doi": "", "url": "https://arxiv.org/abs/2407.19297", "code": [ "https://github.com/LLNL/MuyGPyS" ], "links": { "Paper": "https://arxiv.org/abs/2407.19297", "Code": "https://github.com/LLNL/MuyGPyS" }, "resources": [ "code" ], "modality": [], "summary": "Scalable Gaussian process classification of blended stellar images." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "", "title": "Denoising Diffusion Probabilistic Model for Realistic and Fast Generated Euclid-like Data for Weak Lensing Analysis", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 4, "arxiv_id": "2504.07183", "doi": "", "url": "https://arxiv.org/abs/2504.07183", "code": [], "links": { "Paper": "https://arxiv.org/abs/2504.07183" }, "resources": [], "modality": [], "summary": "DDPM trained on CANDELS images that generates Euclid-like galaxies for shear calibration." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "BTK", "title": "The Blending ToolKit: A Simulation Framework for Evaluation of Galaxy Detection and Deblending", "venue": "OJAp 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": null, "arxiv_id": "", "doi": "10.33232/001c.129699", "url": "https://doi.org/10.33232/001c.129699", "code": [ "https://github.com/LSSTDESC/BlendingToolKit" ], "links": { "Journal": "https://doi.org/10.33232/001c.129699", "Code": "https://github.com/LSSTDESC/BlendingToolKit" }, "resources": [ "code" ], "modality": [], "summary": "Simulation and metrics framework for benchmarking detection and deblending algorithms." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "GalaxySD", "title": "Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 6, "arxiv_id": "2506.16233", "doi": "", "url": "https://arxiv.org/abs/2506.16233", "code": [], "links": { "Paper": "https://arxiv.org/abs/2506.16233" }, "resources": [], "modality": [], "summary": "Stable Diffusion fine-tuned on Galaxy Zoo 2 morphology prompts to augment classifiers and find rare dusty early-type galaxies." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "GalCatDiff", "title": "Category-based Galaxy Image Generation via Diffusion Models", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 6, "arxiv_id": "2506.16255", "doi": "", "url": "https://arxiv.org/abs/2506.16255", "code": [], "links": { "Paper": "https://arxiv.org/abs/2506.16255" }, "resources": [], "modality": [], "summary": "Class-conditioned diffusion model with residual attention blocks trained on Galaxy10 DECaLS categories." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "", "title": "Diffusion-based Galaxy Simulations for the Roman High Latitude Survey", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.22917", "doi": "", "url": "https://arxiv.org/abs/2604.22917", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.22917" }, "resources": [], "modality": [], "summary": "DDPM trained on JWST JADES imaging to generate Roman-like multi-band galaxy stamps for weak lensing." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "scarlet2", "title": "scarlet2: Astronomical Scene Modeling in JAX", "venue": "JOSS 2026", "publication_type": "Journal", "note": "", "year": 2026, "month": null, "arxiv_id": "", "doi": "10.21105/joss.09646", "url": "https://doi.org/10.21105/joss.09646", "code": [ "https://github.com/pmelchior/scarlet2" ], "links": { "Code": "https://github.com/pmelchior/scarlet2", "Journal": "https://doi.org/10.21105/joss.09646" }, "resources": [ "code" ], "modality": [], "summary": "JAX scene modeling for multi-band, multi-epoch and multi-instrument data with neural network priors." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "FluxFlow", "title": "FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolution", "venue": "NeurIPS 2026", "publication_type": "Conference", "note": "", "year": 2026, "month": 5, "arxiv_id": "2605.03749", "doi": "", "url": "https://arxiv.org/abs/2605.03749", "code": [ "https://github.com/I2WM/FluxFlow" ], "links": { "Paper": "https://arxiv.org/abs/2605.03749", "Code": "https://github.com/I2WM/FluxFlow" }, "resources": [ "code" ], "modality": [], "summary": "Pixel-space flow matching for super-resolution that weights training by observational uncertainty and source regions, with a training-free Wiener-regularised correction against spurious sources; introduces 19,500 co-registered DESI to HST image pairs." }, { "section": "Source Detection, Deblending and Image Simulation", "subsection": "", "name": "", "title": "Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging", "venue": "ECCV 2026", "publication_type": "Conference", "note": "", "year": 2026, "month": 1, "arxiv_id": "2601.23276", "doi": "", "url": "https://arxiv.org/abs/2601.23276", "code": [ "https://github.com/ShuhongLL/Denoising-Deep-Sky" ], "links": { "Paper": "https://arxiv.org/abs/2601.23276", "Code": "https://github.com/ShuhongLL/Denoising-Deep-Sky", "Data": "https://huggingface.co/datasets/ToferFish/MuSCAT-RawImage" }, "resources": [ "code", "data" ], "modality": [], "summary": "Synthesises paired training data from a CCD noise model covering shot noise, response non-uniformity, dark current, readout effects, cosmic rays and hot pixels on stacked high-SNR bases; releases multi-band raw frames from two twin ground-based telescopes." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "astroNN", "title": "Deep Learning of Multi-element Abundances from High-resolution Spectroscopic Data", "venue": "MNRAS 2019", "publication_type": "Journal", "note": "", "year": 2018, "month": 8, "arxiv_id": "1808.04428", "doi": "10.1093/mnras/sty3217", "url": "https://arxiv.org/abs/1808.04428", "code": [ "https://github.com/henrysky/astroNN" ], "links": { "Paper": "https://arxiv.org/abs/1808.04428", "Code": "https://github.com/henrysky/astroNN", "Journal": "https://doi.org/10.1093/mnras/sty3217" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian neural networks for stellar parameters and abundances from APOGEE spectra." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "Blancato CNN", "title": "Data-driven Derivation of Stellar Properties from Photometric Time Series Data Using Convolutional Neural Networks", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2020, "month": 5, "arxiv_id": "2005.09682", "doi": "", "url": "https://arxiv.org/abs/2005.09682", "code": [ "https://github.com/kblancato/theia-net" ], "links": { "Paper": "https://arxiv.org/abs/2005.09682", "Code": "https://github.com/kblancato/theia-net" }, "resources": [ "code" ], "modality": [], "summary": "CNNs that infer stellar rotation and surface gravity from Kepler light curves." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "stella", "title": "stella: Convolutional Neural Networks for Flare Identification in TESS", "venue": "JOSS 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": null, "arxiv_id": "", "doi": "10.21105/joss.02347", "url": "https://doi.org/10.21105/joss.02347", "code": [ "https://github.com/afeinstein20/stella" ], "links": { "Journal": "https://doi.org/10.21105/joss.02347", "Code": "https://github.com/afeinstein20/stella" }, "resources": [ "code" ], "modality": [], "summary": "CNN flare detection in TESS two-minute light curves." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "LightPred", "title": "Accurate and Robust Stellar Rotation Periods Catalog for 82771 Kepler Stars Using Deep Learning", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.06858", "doi": "", "url": "https://arxiv.org/abs/2407.06858", "code": [], "links": { "Paper": "https://arxiv.org/abs/2407.06858" }, "resources": [], "modality": [], "summary": "LSTM and transformer model pretrained contrastively on Kepler light curves and trained on spot-model simulations." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "Predicting Metallicities and Carbon Abundances from Gaia XP Spectra for (Carbon-enhanced) Metal-poor Stars", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 10, "arxiv_id": "2410.11077", "doi": "", "url": "https://arxiv.org/abs/2410.11077", "code": [], "links": { "Paper": "https://arxiv.org/abs/2410.11077" }, "resources": [], "modality": [], "summary": "Heteroscedastic neural network ensemble that predicts [Fe/H] and [C/Fe] for more than 10 million XP stars." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "Mapping the Milky Way with Gaia Bp/Rp Spectra I: Systematic Flux Corrections and Atmospheric Parameters for 68 Million Stars", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 11, "arxiv_id": "2411.19105", "doi": "", "url": "https://arxiv.org/abs/2411.19105", "code": [], "links": { "Paper": "https://arxiv.org/abs/2411.19105" }, "resources": [], "modality": [], "summary": "APOGEE-trained network that corrects XP flux systematics before model-atmosphere fitting." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "UA-CSNet", "title": "Metallicities of 20 Million Giant Stars Based on Gaia XP Spectra", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.05281", "doi": "", "url": "https://arxiv.org/abs/2505.05281", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.05281" }, "resources": [], "modality": [], "summary": "Uncertainty-aware cost-sensitive network that estimates metallicities down to [Fe/H] about -4 for giants." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "Millions of Main-Sequence Binary Stars from Gaia BP/RP Spectra", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 7, "arxiv_id": "2507.09622", "doi": "", "url": "https://arxiv.org/abs/2507.09622", "code": [], "links": { "Paper": "https://arxiv.org/abs/2507.09622" }, "resources": [], "modality": [], "summary": "Neural spectral emulator of single stars used to identify more than 14 million binary candidates from XP spectra." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "The Use of Conditional Variational Autoencoders in Generating Stellar Spectra", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.17059", "doi": "", "url": "https://arxiv.org/abs/2508.17059", "code": [], "links": { "Paper": "https://arxiv.org/abs/2508.17059" }, "resources": [], "modality": [], "summary": "CVAE that generates stellar spectra over a grid of atmospheric parameters, rotation and instrumental resolution." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "EBOP MAVEN", "title": "EBOP MAVEN: A Machine Learning Model to Estimate the Input Parameters for Analytic Fitting of Detached Eclipsing Binary Light Curves", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.21465", "doi": "", "url": "https://arxiv.org/abs/2510.21465", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.21465" }, "resources": [], "modality": [], "summary": "CNN that predicts detached eclipsing binary parameters from phase-folded TESS light curves to initialise JKTEBOP fits." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "A Generalist Model Including Evolved Star Mass and Age", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.03732", "doi": "", "url": "https://arxiv.org/abs/2603.03732", "code": [], "links": { "Paper": "https://arxiv.org/abs/2603.03732" }, "resources": [], "modality": [], "summary": "Extends a transformer stellar foundation model to infer mass and age of giants from Gaia XP spectra." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "ASTRAFier", "title": "ASTRAFier: A Novel and Scalable Transformer-based Stellar Variability Classifier", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.07437", "doi": "", "url": "https://arxiv.org/abs/2604.07437", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.07437" }, "resources": [], "modality": [], "summary": "BiLSTM, attention and CNN classifier applied to about 2.8 million TESS light curves." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "Homogeneous Stellar Parameters from Heterogeneous Spectra with Deep Learning", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.25786", "doi": "", "url": "https://arxiv.org/abs/2604.25786", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.25786" }, "resources": [], "modality": [], "summary": "Single transformer trained across APOGEE, GALAH, DESI and Gaia RVS that outputs atmospheric parameters, 20 abundances, distances and ages on one consistent scale." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "Potential of Gaia XP Spectra in Red Giant Star Asteroseismology: A Deep-Learning Approach", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.17045", "doi": "", "url": "https://arxiv.org/abs/2604.17045", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.17045" }, "resources": [], "modality": [], "summary": "CNN-LSTM models trained on Kepler red giants recover delta nu, nu max and period spacing from Gaia XP spectra and provide predictions for more than 2.5 million giants." }, { "section": "Stars and Stellar Spectroscopy", "subsection": "", "name": "", "title": "Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 5, "arxiv_id": "2605.22162", "doi": "", "url": "https://arxiv.org/abs/2605.22162", "code": [], "links": { "Paper": "https://arxiv.org/abs/2605.22162" }, "resources": [], "modality": [], "summary": "Fine-tunes a large language model on LAMOST low-resolution spectra in two stages to infer stellar parameters and elemental abundances, validated against Gaia-ESO and GALAH DR4." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "DeepAP", "title": "DeepAP: Deep Learning-based Aperture Photometry Feasibility Assessment and Aperture Size Prediction", "venue": "RAA 2025", "publication_type": "Journal", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.03400", "doi": "10.1088/1674-4527/adf716", "url": "https://arxiv.org/abs/2508.03400", "code": [ "https://github.com/ruiyicheng/DeepAP" ], "links": { "Paper": "https://arxiv.org/abs/2508.03400", "Code": "https://github.com/ruiyicheng/DeepAP", "Journal": "https://doi.org/10.1088/1674-4527/adf716" }, "resources": [ "code" ], "modality": [ "Images" ], "summary": "Two-stage framework uses a Vision Transformer to assess aperture-photometry feasibility and a ResNet to predict aperture size for optical survey photometry, achieving a test ROC AUC of 0.96 for feasibility assessment." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "snmachine", "title": "Photometric Supernova Classification with Machine Learning", "venue": "ApJS 2016", "publication_type": "Journal", "note": "", "year": 2016, "month": 3, "arxiv_id": "1603.00882", "doi": "", "url": "https://arxiv.org/abs/1603.00882", "code": [ "https://github.com/LSSTDESC/snmachine" ], "links": { "Paper": "https://arxiv.org/abs/1603.00882", "Rubin Study": "https://arxiv.org/abs/2107.07531", "Code": "https://github.com/LSSTDESC/snmachine" }, "resources": [ "code" ], "modality": [], "summary": "Feature extraction and classifier pipeline for photometric supernova typing." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "SuperNNova", "title": "SuperNNova: An Open-Source Framework for Bayesian, Neural Network Based Supernova Classification", "venue": "MNRAS 2020", "publication_type": "Journal", "note": "", "year": 2019, "month": 1, "arxiv_id": "1901.06384", "doi": "10.1093/mnras/stz3312", "url": "https://arxiv.org/abs/1901.06384", "code": [ "https://github.com/supernnova/SuperNNova" ], "links": { "Paper": "https://arxiv.org/abs/1901.06384", "Code": "https://github.com/supernnova/SuperNNova", "Journal": "https://doi.org/10.1093/mnras/stz3312" }, "resources": [ "code" ], "modality": [], "summary": "Recurrent and Bayesian neural networks for light-curve classification." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "DeepStreaks", "title": "DeepStreaks: Identifying Fast-moving Objects in the Zwicky Transient Facility Data with Deep Learning", "venue": "MNRAS 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 4, "arxiv_id": "1904.05920", "doi": "", "url": "https://arxiv.org/abs/1904.05920", "code": [ "https://github.com/dmitryduev/DeepStreaks" ], "links": { "Paper": "https://arxiv.org/abs/1904.05920", "Code": "https://github.com/dmitryduev/DeepStreaks" }, "resources": [ "code" ], "modality": [], "summary": "CNN ensemble that identifies streaks from fast-moving near-Earth objects in ZTF images." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "braai", "title": "Real-bogus Classification for the Zwicky Transient Facility Using Deep Learning", "venue": "MNRAS 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 7, "arxiv_id": "1907.11259", "doi": "", "url": "https://arxiv.org/abs/1907.11259", "code": [ "https://github.com/dmitryduev/braai" ], "links": { "Paper": "https://arxiv.org/abs/1907.11259", "Code": "https://github.com/dmitryduev/braai" }, "resources": [ "code" ], "modality": [], "summary": "CNN real-bogus classifier deployed in the ZTF alert pipeline." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "Cyclic-Permutation Networks", "title": "Classification of Periodic Variable Stars with Novel Cyclic-permutation Invariant Neural Networks", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 11, "arxiv_id": "2011.01243", "doi": "", "url": "https://arxiv.org/abs/2011.01243", "code": [ "https://github.com/kmzzhang/periodicnetwork" ], "links": { "Paper": "https://arxiv.org/abs/2011.01243", "Code": "https://github.com/kmzzhang/periodicnetwork" }, "resources": [ "code" ], "modality": [], "summary": "Phase-folded light-curve classifiers that are invariant to cyclic permutations." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "SCoPe", "title": "The ZTF Source Classification Project: I. Methods and Infrastructure", "venue": "AJ 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 2, "arxiv_id": "2102.11304", "doi": "10.3847/1538-3881/abe853", "url": "https://arxiv.org/abs/2102.11304", "code": [ "https://github.com/ZwickyTransientFacility/scope" ], "links": { "Paper": "https://arxiv.org/abs/2102.11304", "Code": "https://github.com/ZwickyTransientFacility/scope", "Journal": "https://doi.org/10.3847/1538-3881/abe853" }, "resources": [ "code" ], "modality": [], "summary": "Modular machine learning framework for classifying variable sources in ZTF light curves." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "Time-Series Transformer", "title": "Paying Attention to Astronomical Transients: Introducing the Time-series Transformer for Photometric Classification", "venue": "RASTI 2024", "publication_type": "Journal", "note": "", "year": 2021, "month": 5, "arxiv_id": "2105.06178", "doi": "", "url": "https://arxiv.org/abs/2105.06178", "code": [ "https://github.com/tallamjr/astronet" ], "links": { "Paper": "https://arxiv.org/abs/2105.06178", "Code": "https://github.com/tallamjr/astronet" }, "resources": [ "code" ], "modality": [], "summary": "Transformer classifier for multiband transient light curves evaluated on PLAsTiCC." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "SCONE", "title": "SCONE: Supernova Classification with a Convolutional Neural Network", "venue": "AJ 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 6, "arxiv_id": "2106.04370", "doi": "", "url": "https://arxiv.org/abs/2106.04370", "code": [ "https://github.com/helenqu/scone" ], "links": { "Paper": "https://arxiv.org/abs/2106.04370", "Code": "https://github.com/helenqu/scone", "Early-time Paper": "https://arxiv.org/abs/2111.05539" }, "resources": [ "code" ], "modality": [], "summary": "CNN on wavelength-time heatmaps of supernova light curves." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "Roman Microlensing NPE", "title": "Real-time Likelihood-free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation", "venue": "AJ 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": null, "arxiv_id": "", "doi": "10.3847/1538-3881/abf42e", "url": "https://doi.org/10.3847/1538-3881/abf42e", "code": [ "https://github.com/kmzzhang/nbi" ], "links": { "Code": "https://github.com/kmzzhang/nbi", "Journal": "https://doi.org/10.3847/1538-3881/abf42e" }, "resources": [ "code" ], "modality": [], "summary": "ResNet-GRU featurizer and normalizing flow that infer binary microlensing parameters in real time." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "ACAI", "title": "Phenomenological Classification of the Zwicky Transient Facility Astronomical Event Alerts", "venue": "arXiv 2021", "publication_type": "Preprint", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.12142", "doi": "", "url": "https://arxiv.org/abs/2111.12142", "code": [ "https://github.com/dmitryduev/acai" ], "links": { "Paper": "https://arxiv.org/abs/2111.12142", "Code": "https://github.com/dmitryduev/acai" }, "resources": [ "code" ], "modality": [], "summary": "Multi-label deep learning classifiers for ZTF alert phenomenology." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "MuyGPs Light Curves", "title": "Light Curve Completion and Forecasting Using Fast and Scalable Gaussian Processes (MuyGPs)", "venue": "arXiv 2022", "publication_type": "Preprint", "note": "", "year": 2022, "month": 8, "arxiv_id": "2208.14592", "doi": "", "url": "https://arxiv.org/abs/2208.14592", "code": [ "https://github.com/LLNL/MuyGPyS" ], "links": { "Paper": "https://arxiv.org/abs/2208.14592", "Code": "https://github.com/LLNL/MuyGPyS" }, "resources": [ "code" ], "modality": [], "summary": "Scalable Gaussian processes for filling gaps in and forecasting light curves." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "", "title": "Identifying Light-curve Signals with a Deep-learning-based Object Detection Algorithm. II. A General Light-curve Classification Framework", "venue": "ApJS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 11, "arxiv_id": "2311.08080", "doi": "10.3847/1538-4365/ad62fd", "url": "https://arxiv.org/abs/2311.08080", "code": [], "links": { "Paper": "https://arxiv.org/abs/2311.08080", "Journal": "https://doi.org/10.3847/1538-4365/ad62fd" }, "resources": [], "modality": [], "summary": "Object-detection based classifier on light curves and power spectra from Kepler, TESS and ZTF." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "BTSbot", "title": "The Zwicky Transient Facility Bright Transient Survey. III. BTSbot: Automated Identification and Follow-up of Bright Transients with Deep Learning", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 1, "arxiv_id": "2401.15167", "doi": "", "url": "https://arxiv.org/abs/2401.15167", "code": [ "https://github.com/nabeelre/BTSbot" ], "links": { "Paper": "https://arxiv.org/abs/2401.15167", "Follow-up": "https://arxiv.org/abs/2512.11957", "Code": "https://github.com/nabeelre/BTSbot" }, "resources": [ "code" ], "modality": [], "summary": "Multimodal CNN that selects bright transients for automated spectroscopic follow-up." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "CATS", "title": "Transient Classifiers for Fink", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 4, "arxiv_id": "2404.08798", "doi": "", "url": "https://arxiv.org/abs/2404.08798", "code": [], "links": { "Paper": "https://arxiv.org/abs/2404.08798" }, "resources": [], "modality": [], "summary": "Tree-based and deep learning classifiers in the Fink broker evaluated on ELAsTiCC, including the CATS architecture." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "ORACLE", "title": "ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 1, "arxiv_id": "2501.01496", "doi": "", "url": "https://arxiv.org/abs/2501.01496", "code": [ "https://github.com/uiucsn/ORACLE" ], "links": { "Paper": "https://arxiv.org/abs/2501.01496", "Code": "https://github.com/uiucsn/ORACLE" }, "resources": [ "code" ], "modality": [], "summary": "Hierarchical recurrent classifier for real-time LSST alert streams." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "AMPEL", "title": "AMPEL Workflows for LSST: Modular and Reproducible Real-time Photometric Classification", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 1, "arxiv_id": "2501.16511", "doi": "", "url": "https://arxiv.org/abs/2501.16511", "code": [], "links": { "Paper": "https://arxiv.org/abs/2501.16511" }, "resources": [], "modality": [], "summary": "SNGuess, FollowMe and FinalBet classification channels for ELAsTiCC alerts." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "", "title": "Real-Time Active Learning for Optimised Spectroscopic Follow-up: Enhancing Early SN Ia Classification with the Fink Broker", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 2, "arxiv_id": "2502.19555", "doi": "", "url": "https://arxiv.org/abs/2502.19555", "code": [], "links": { "Paper": "https://arxiv.org/abs/2502.19555" }, "resources": [], "modality": [], "summary": "Active learning loop on the Fink stream that selects spectroscopic targets to improve early SN Ia classifiers." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "PIE-ADA", "title": "PIE-ADA: Physics-Informed Ensemble with Adaptive Data Augmentation for Photometric Transient Classification", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.29367", "doi": "", "url": "https://arxiv.org/abs/2606.29367", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.29367" }, "resources": [], "modality": [], "summary": "Physics-motivated light-curve augmentation for rare classes combined with gradient boosted ensembles." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "NAPTIME", "title": "NAPTIME: A Neural-Process Framework for Rubin Alert Classification", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.19236", "doi": "", "url": "https://arxiv.org/abs/2607.19236", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.19236" }, "resources": [], "modality": [], "summary": "Neural process that jointly reconstructs and classifies sparse multiband light curves on ELAsTiCC2 and MALLORN." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "", "title": "Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 2, "arxiv_id": "2502.18558", "doi": "", "url": "https://arxiv.org/abs/2502.18558", "code": [], "links": { "Paper": "https://arxiv.org/abs/2502.18558" }, "resources": [], "modality": [], "summary": "Shows that transient classifiers pretrained on simulations or ZTF light curves can be adapted to real data and to LSST with small labelled samples." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "FCN4Flare", "title": "FCN4Flare: Fully Convolution Neural Networks for Flare Detection", "venue": "MNRAS 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.21240", "doi": "10.1093/mnras/stae2789", "url": "https://arxiv.org/abs/2407.21240", "code": [ "https://github.com/NAOC-LAMOST/fcn4flare" ], "links": { "Paper": "https://arxiv.org/abs/2407.21240", "Journal": "https://doi.org/10.1093/mnras/stae2789", "Code": "https://github.com/NAOC-LAMOST/fcn4flare" }, "resources": [ "code" ], "modality": [], "summary": "Fully convolutional networks with a NaN mask and masked Dice loss detect stellar flares point by point in variable-length Kepler light curves, yielding a catalogue of 30,285 flares on 1,426 stars." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "FLARE", "title": "FLARE: A Framework for Stellar Flare Forecasting Using Stellar Physical Properties and Historical Records", "venue": "IJCAI 2025", "publication_type": "Conference", "note": "", "year": 2025, "month": 2, "arxiv_id": "2502.18218", "doi": "10.24963/ijcai.2025/1056", "url": "https://arxiv.org/abs/2502.18218", "code": [], "links": { "Paper": "https://arxiv.org/abs/2502.18218", "Journal": "https://doi.org/10.24963/ijcai.2025/1056" }, "resources": [], "modality": [], "summary": "Forecasts stellar flares from Kepler light curves by combining stellar physical properties and historical flare records through a soft prompt module and a residual record fusion module." }, { "section": "Time-Domain Astronomy and Transients", "subsection": "", "name": "StarWhisper LC", "title": "Deep Learning and Methods Based on Large Language Models Applied to Stellar Light Curve Classification", "venue": "Intell. Comput. 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 4, "arxiv_id": "2404.10757", "doi": "10.34133/icomputing.0110", "url": "https://arxiv.org/abs/2404.10757", "code": [ "https://github.com/Yu-Yang-Li/StarWhisper/tree/main/projects/light-curves" ], "links": { "Paper": "https://arxiv.org/abs/2404.10757", "Code": "https://github.com/Yu-Yang-Li/StarWhisper/tree/main/projects/light-curves", "Journal": "https://doi.org/10.34133/icomputing.0110" }, "resources": [ "code" ], "modality": [], "summary": "Compares Conv1D-BiLSTM and Swin Transformer classifiers with fine-tuned LLM, multimodal LLM and audio LLM models on Kepler and K2 variable-star light curves; the Swin Transformer reaches 99% accuracy and the LLM-based models about 90%." }, { "section": "Exoplanets", "subsection": "", "name": "", "title": "Learning a model of non-stationary nuisances with non-local correlations for object detection", "venue": "EUSIPCO 2026", "publication_type": "Conference", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.14479", "doi": "", "url": "https://arxiv.org/abs/2611.14479", "code": [], "links": { "Paper": "https://arxiv.org/abs/2611.14479" }, "resources": [], "modality": [], "summary": "Learns a sparse precision matrix for correlated stellar residuals and tests likelihood-ratio exoplanet detection on 13 VLT/SPHERE datasets." }, { "section": "Exoplanets", "subsection": "", "name": "Pearson Exoplanet AI", "title": "Searching for Exoplanets Using Artificial Intelligence", "venue": "MNRAS 2018", "publication_type": "Journal", "note": "", "year": 2017, "month": 6, "arxiv_id": "1706.04319", "doi": "", "url": "https://arxiv.org/abs/1706.04319", "code": [ "https://github.com/pearsonkyle/Exoplanet-Artificial-Intelligence" ], "links": { "Paper": "https://arxiv.org/abs/1706.04319", "Code": "https://github.com/pearsonkyle/Exoplanet-Artificial-Intelligence" }, "resources": [ "code" ], "modality": [], "summary": "Neural networks that detect transit signals in simulated and Kepler light curves." }, { "section": "Exoplanets", "subsection": "", "name": "AstroNet", "title": "Identifying Exoplanets with Deep Learning: A Five-planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90", "venue": "AJ 2018", "publication_type": "Journal", "note": "", "year": 2018, "month": null, "arxiv_id": "", "doi": "10.3847/1538-3881/aa9e09", "url": "https://doi.org/10.3847/1538-3881/aa9e09", "code": [ "https://github.com/google-research/exoplanet-ml" ], "links": { "Journal": "https://doi.org/10.3847/1538-3881/aa9e09", "Code": "https://github.com/google-research/exoplanet-ml" }, "resources": [ "code" ], "modality": [], "summary": "CNN transit classifier for Kepler threshold crossing events." }, { "section": "Exoplanets", "subsection": "", "name": "HELA", "title": "Supervised Machine Learning for Analysing Spectra of Exoplanetary Atmospheres", "venue": "Nature Astronomy 2018", "publication_type": "Journal", "note": "", "year": 2018, "month": 6, "arxiv_id": "1806.03944", "doi": "", "url": "https://arxiv.org/abs/1806.03944", "code": [ "https://github.com/exoclime/HELA" ], "links": { "Paper": "https://arxiv.org/abs/1806.03944", "Code": "https://github.com/exoclime/HELA" }, "resources": [ "code" ], "modality": [], "summary": "Random forest atmospheric retrieval for exoplanet transmission spectra." }, { "section": "Exoplanets", "subsection": "", "name": "ExoGAN", "title": "ExoGAN: Retrieving Exoplanetary Atmospheres Using Deep Convolutional Generative Adversarial Networks", "venue": "AJ 2018", "publication_type": "Journal", "note": "", "year": 2018, "month": 6, "arxiv_id": "1806.02906", "doi": "", "url": "https://arxiv.org/abs/1806.02906", "code": [ "https://github.com/ucl-exoplanets/ExoGAN_public" ], "links": { "Paper": "https://arxiv.org/abs/1806.02906", "Code": "https://github.com/ucl-exoplanets/ExoGAN_public" }, "resources": [ "code" ], "modality": [], "summary": "Generative adversarial network for atmospheric retrieval." }, { "section": "Exoplanets", "subsection": "", "name": "AstroNet-K2", "title": "Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data", "venue": "AJ 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 3, "arxiv_id": "1903.10507", "doi": "", "url": "https://arxiv.org/abs/1903.10507", "code": [ "https://github.com/aedattilo/models_K2" ], "links": { "Paper": "https://arxiv.org/abs/1903.10507", "Code": "https://github.com/aedattilo/models_K2" }, "resources": [ "code" ], "modality": [], "summary": "AstroNet adapted to K2 light curves." }, { "section": "Exoplanets", "subsection": "", "name": "Astronet-Triage", "title": "Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates", "venue": "AJ 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 4, "arxiv_id": "1904.02726", "doi": "10.3847/1538-3881/ab21d6", "url": "https://arxiv.org/abs/1904.02726", "code": [ "https://github.com/yuliang419/Astronet-Triage" ], "links": { "Paper": "https://arxiv.org/abs/1904.02726", "Code": "https://github.com/yuliang419/Astronet-Triage", "Journal": "https://doi.org/10.3847/1538-3881/ab21d6" }, "resources": [ "code" ], "modality": [], "summary": "Neural networks for triage and vetting of TESS transit signals." }, { "section": "Exoplanets", "subsection": "", "name": "SPOCK", "title": "Predicting the Long-term Stability of Compact Multiplanet Systems", "venue": "PNAS 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": 7, "arxiv_id": "2007.06521", "doi": "", "url": "https://arxiv.org/abs/2007.06521", "code": [ "https://github.com/dtamayo/spock" ], "links": { "Paper": "https://arxiv.org/abs/2007.06521", "Follow-up": "https://arxiv.org/abs/2408.08873", "Code": "https://github.com/dtamayo/spock" }, "resources": [ "code" ], "modality": [], "summary": "Gradient boosted classifier on short N-body integrations that predicts multiplanet stability." }, { "section": "Exoplanets", "subsection": "", "name": "BNN Chaos", "title": "A Bayesian Neural Network Predicts the Dissolution of Compact Planetary Systems", "venue": "PNAS 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 1, "arxiv_id": "2101.04117", "doi": "", "url": "https://arxiv.org/abs/2101.04117", "code": [ "https://github.com/MilesCranmer/bnn_chaos_model" ], "links": { "Paper": "https://arxiv.org/abs/2101.04117", "Code": "https://github.com/MilesCranmer/bnn_chaos_model" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian neural network that predicts instability times of compact planetary systems." }, { "section": "Exoplanets", "subsection": "", "name": "MARGE", "title": "Accurate Machine-learning Atmospheric Retrieval via a Neural-network Surrogate Model for Radiative Transfer", "venue": "PSJ 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": null, "arxiv_id": "", "doi": "10.3847/PSJ/abe3fd", "url": "https://doi.org/10.3847/PSJ/abe3fd", "code": [ "https://github.com/exosports/MARGE" ], "links": { "Code": "https://github.com/exosports/MARGE", "Journal": "https://doi.org/10.3847/PSJ/abe3fd" }, "resources": [ "code" ], "modality": [], "summary": "Neural surrogate for radiative transfer that accelerates exoplanet atmospheric retrieval." }, { "section": "Exoplanets", "subsection": "", "name": "ExoMiner", "title": "ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.10009", "doi": "10.3847/1538-4357/ac4399", "url": "https://arxiv.org/abs/2111.10009", "code": [ "https://github.com/nasa/ExoMiner" ], "links": { "Paper": "https://arxiv.org/abs/2111.10009", "Code": "https://github.com/nasa/ExoMiner", "Journal": "https://doi.org/10.3847/1538-4357/ac4399" }, "resources": [ "code" ], "modality": [], "summary": "Multi-branch network that mimics expert vetting diagnostics and validates 301 Kepler planets." }, { "section": "Exoplanets", "subsection": "", "name": "HSR4HCI", "title": "Half-sibling Regression Meets Exoplanet Imaging: PSF Modeling and Subtraction Using a Flexible, Domain Knowledge-driven, Causal Framework", "venue": "A&A 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 4, "arxiv_id": "2204.03439", "doi": "", "url": "https://arxiv.org/abs/2204.03439", "code": [ "https://github.com/timothygebhard/hsr4hci" ], "links": { "Paper": "https://arxiv.org/abs/2204.03439", "Code": "https://github.com/timothygebhard/hsr4hci" }, "resources": [ "code" ], "modality": [], "summary": "Data-driven PSF subtraction for high-contrast imaging based on half-sibling regression." }, { "section": "Exoplanets", "subsection": "", "name": "SBI-EAR", "title": "Neural Posterior Estimation for Exoplanetary Atmospheric Retrieval", "venue": "A&A 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 1, "arxiv_id": "2301.06575", "doi": "", "url": "https://arxiv.org/abs/2301.06575", "code": [ "https://github.com/MalAstronomy/sbi-ear" ], "links": { "Paper": "https://arxiv.org/abs/2301.06575", "Code": "https://github.com/MalAstronomy/sbi-ear" }, "resources": [ "code" ], "modality": [], "summary": "Normalizing-flow posterior estimation for exoplanet atmospheric retrieval." }, { "section": "Exoplanets", "subsection": "", "name": "AESTRA", "title": "AESTRA: Deep Learning for Precise Radial Velocity Estimation in the Presence of Stellar Activity", "venue": "AJ 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 11, "arxiv_id": "2311.18326", "doi": "10.3847/1538-3881/ad0e01", "url": "https://arxiv.org/abs/2311.18326", "code": [ "https://github.com/yanliang-astro/aestra" ], "links": { "Paper": "https://arxiv.org/abs/2311.18326", "Code": "https://github.com/yanliang-astro/aestra", "Journal": "https://doi.org/10.3847/1538-3881/ad0e01", "Paper II": "https://arxiv.org/abs/2606.13574" }, "resources": [ "code" ], "modality": [], "summary": "Self-supervised spectrum autoencoder and RV estimator that separate Doppler shifts from activity-induced line-profile changes." }, { "section": "Exoplanets", "subsection": "", "name": "FlopPITy", "title": "FlopPITy: Enabling Self-consistent Exoplanet Atmospheric Retrievals with Machine Learning", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 1, "arxiv_id": "2401.04168", "doi": "", "url": "https://arxiv.org/abs/2401.04168", "code": [], "links": { "Paper": "https://arxiv.org/abs/2401.04168" }, "resources": [], "modality": [], "summary": "Sequential neural posterior estimation with neural spline flows for self-consistent atmospheric retrievals." }, { "section": "Exoplanets", "subsection": "", "name": "FMPE Retrieval", "title": "Flow Matching for Atmospheric Retrieval of Exoplanets: Where Reliability Meets Adaptive Noise Levels", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 10, "arxiv_id": "2410.21477", "doi": "", "url": "https://arxiv.org/abs/2410.21477", "code": [], "links": { "Paper": "https://arxiv.org/abs/2410.21477" }, "resources": [], "modality": [], "summary": "Flow matching posterior estimation with importance sampling to verify retrievals and estimate the evidence." }, { "section": "Exoplanets", "subsection": "", "name": "FASTER", "title": "Near-instantaneous Atmospheric Retrievals and Model Comparison with FASTER", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 2, "arxiv_id": "2502.18045", "doi": "", "url": "https://arxiv.org/abs/2502.18045", "code": [], "links": { "Paper": "https://arxiv.org/abs/2502.18045" }, "resources": [], "modality": [], "summary": "Neural ratio estimation for marginal posteriors and amortized Bayesian model comparison, applied to WASP-39b." }, { "section": "Exoplanets", "subsection": "", "name": "", "title": "Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 2, "arxiv_id": "2502.07542", "doi": "", "url": "https://arxiv.org/abs/2502.07542", "code": [], "links": { "Paper": "https://arxiv.org/abs/2502.07542" }, "resources": [], "modality": [], "summary": "Convolutional embeddings and transformer encoder applied to flux, centroid and background series of 4.1 million light curves." }, { "section": "Exoplanets", "subsection": "", "name": "DART-Vetter", "title": "DART-Vetter: A Deep LeARning Tool for Automatic Triage of Exoplanet Candidates", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 6, "arxiv_id": "2506.05556", "doi": "", "url": "https://arxiv.org/abs/2506.05556", "code": [], "links": { "Paper": "https://arxiv.org/abs/2506.05556" }, "resources": [], "modality": [], "summary": "Compact CNN on phase-folded light curves that triages TESS and Kepler threshold crossing events." }, { "section": "Exoplanets", "subsection": "", "name": "", "title": "Towards the Habitable Worlds Observatory: Retrieval of Reflection Spectra from Evolving Earth Analogues Using 1D CNNs", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.00076", "doi": "", "url": "https://arxiv.org/abs/2508.00076", "code": [], "links": { "Paper": "https://arxiv.org/abs/2508.00076" }, "resources": [], "modality": [], "summary": "1D CNN retrieval of composition and planetary properties from HWO-like reflected-light spectra." }, { "section": "Exoplanets", "subsection": "", "name": "", "title": "Supervised Machine Learning Methods with Uncertainty Quantification for Exoplanet Atmospheric Retrievals from Transmission Spectroscopy", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.04982", "doi": "", "url": "https://arxiv.org/abs/2508.04982", "code": [], "links": { "Paper": "https://arxiv.org/abs/2508.04982" }, "resources": [], "modality": [], "summary": "Benchmark of PLS, SVM, KNN, tree ensembles and XGBoost on Ariel-like transmission spectra." }, { "section": "Exoplanets", "subsection": "", "name": "", "title": "Exoplanetary Atmospheres Retrieval via a Quantum Extreme Learning Machine", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.03617", "doi": "", "url": "https://arxiv.org/abs/2509.03617", "code": [], "links": { "Paper": "https://arxiv.org/abs/2509.03617" }, "resources": [], "modality": [], "summary": "Quantum extreme learning machine retrieval executed on IBM quantum hardware." }, { "section": "Exoplanets", "subsection": "", "name": "", "title": "Identifying Exoplanets with Deep Learning: A CNN and RNN Classifier for Kepler DR25 and Candidate Vetting", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.04793", "doi": "", "url": "https://arxiv.org/abs/2509.04793", "code": [], "links": { "Paper": "https://arxiv.org/abs/2509.04793" }, "resources": [], "modality": [], "summary": "CNN, bidirectional LSTM and attention classifier for Kepler DR25 transit signals." }, { "section": "Exoplanets", "subsection": "", "name": "WATSON-Net", "title": "WATSON-Net: Vetting, Validation, and Analysis of Transits from Space Observations with Neural Networks", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.08768", "doi": "", "url": "https://arxiv.org/abs/2511.08768", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.08768" }, "resources": [], "modality": [], "summary": "Multi-branch network for transit vetting integrated into the SHERLOCK pipeline." }, { "section": "Exoplanets", "subsection": "", "name": "RAVEN", "title": "Automatic Search for Transiting Planets in TESS-SPOC FFIs with RAVEN: Over 100 Newly Validated Planets and Over 2000 Vetted Candidates", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.22597", "doi": "", "url": "https://arxiv.org/abs/2603.22597", "code": [], "links": { "Paper": "https://arxiv.org/abs/2603.22597" }, "resources": [], "modality": [], "summary": "Machine learning classifiers trained on injected simulations combined with statistical validation for TESS FFI candidates." }, { "section": "Exoplanets", "subsection": "", "name": "ExoNet", "title": "ExoNet: Calibrated Multimodal Deep Learning for TESS Exoplanet Candidate Vetting Using Phase-Folded Light Curves, Stellar Parameters, and Multi-Head Attention", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.15560", "doi": "", "url": "https://arxiv.org/abs/2604.15560", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.15560" }, "resources": [], "modality": [], "summary": "Late fusion of light-curve CNN features with attention and stellar parameters, calibrated by temperature scaling." }, { "section": "Exoplanets", "subsection": "", "name": "ExoVeil", "title": "One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with ExoVeil", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.02778", "doi": "", "url": "https://arxiv.org/abs/2606.02778", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.02778" }, "resources": [], "modality": [], "summary": "Transformer world model trained on 16,499 Kepler light curves predicts stellar flux, with matched filtering on residuals reaching AUC 0.938 on DR25 and recovering 47 TESS planets zero-shot." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Self-Interacting Neutrinos in NEDE and DRMD Cosmologies: Posteriors, profiles and evidence using CLiENT", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.13756", "doi": "", "url": "https://arxiv.org/abs/2611.13756", "code": [ "https://github.com/AarhusCosmology/client-f/tree/papers/2026-sidr-drmd" ], "links": { "Paper": "https://arxiv.org/abs/2611.13756", "Code": "https://github.com/AarhusCosmology/client-f/tree/papers/2026-sidr-drmd" }, "resources": [ "code" ], "modality": [], "summary": "An actively trained neural emulator approximates the joint cosmological and nuisance-parameter log posterior using roughly 300,000 likelihood evaluations per dataset." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "CosmoGAN", "title": "CosmoGAN: Creating High-fidelity Weak Lensing Convergence Maps Using Generative Adversarial Networks", "venue": "Comput. Astrophys. Cosmol. 2019", "publication_type": "Journal", "note": "", "year": 2017, "month": 6, "arxiv_id": "1706.02390", "doi": "10.1186/s40668-019-0029-9", "url": "https://arxiv.org/abs/1706.02390", "code": [ "https://github.com/MustafaMustafa/cosmoGAN" ], "links": { "Paper": "https://arxiv.org/abs/1706.02390", "Journal": "https://doi.org/10.1186/s40668-019-0029-9", "Code": "https://github.com/MustafaMustafa/cosmoGAN" }, "resources": [ "code" ], "modality": [], "summary": "GAN that generates weak lensing convergence maps." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "IMNN", "title": "Automatic Physical Inference with Information Maximizing Neural Networks", "venue": "PRD 2018", "publication_type": "Journal", "note": "", "year": 2018, "month": null, "arxiv_id": "", "doi": "10.1103/PhysRevD.97.083004", "url": "https://doi.org/10.1103/PhysRevD.97.083004", "code": [ "https://github.com/tomcharnock/IMNN" ], "links": { "Journal": "https://doi.org/10.1103/PhysRevD.97.083004", "Code": "https://github.com/tomcharnock/IMNN" }, "resources": [ "code" ], "modality": [], "summary": "Neural compression that maximises Fisher information for downstream inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "NNhealpix", "title": "Convolutional Neural Networks on the HEALPix Sphere: A Pixel-based Algorithm and Its Application to CMB Data Analysis", "venue": "A&A 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": null, "arxiv_id": "", "doi": "10.1051/0004-6361/201935211", "url": "https://doi.org/10.1051/0004-6361/201935211", "code": [ "https://github.com/ai4cmb/NNhealpix" ], "links": { "Journal": "https://doi.org/10.1051/0004-6361/201935211", "Code": "https://github.com/ai4cmb/NNhealpix" }, "resources": [ "code" ], "modality": [], "summary": "Pixel-based convolutions on HEALPix maps applied to CMB analysis." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "3DcosmoGAN", "title": "Cosmological N-body Simulations: A Challenge for Scalable Generative Models", "venue": "Comput. Astrophys. Cosmol. 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 8, "arxiv_id": "1908.05519", "doi": "10.1186/s40668-019-0032-1", "url": "https://arxiv.org/abs/1908.05519", "code": [ "https://github.com/nperraud/3DcosmoGAN" ], "links": { "Paper": "https://arxiv.org/abs/1908.05519", "Journal": "https://doi.org/10.1186/s40668-019-0032-1", "Code": "https://github.com/nperraud/3DcosmoGAN" }, "resources": [ "code" ], "modality": [], "summary": "Scalable 3D GAN for N-body density fields." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "Symbolic DL", "title": "Discovering Symbolic Models from Deep Learning with Inductive Biases", "venue": "NeurIPS 2020", "publication_type": "Conference", "note": "", "year": 2020, "month": 6, "arxiv_id": "2006.11287", "doi": "", "url": "https://arxiv.org/abs/2006.11287", "code": [ "https://github.com/MilesCranmer/symbolic_deep_learning" ], "links": { "Paper": "https://arxiv.org/abs/2006.11287", "Code": "https://github.com/MilesCranmer/symbolic_deep_learning" }, "resources": [ "code" ], "modality": [], "summary": "Graph networks distilled into symbolic expressions, including a dark matter halo example." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "FlowPM", "title": "FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver", "venue": "Astron. Comput. 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.11847", "doi": "", "url": "https://arxiv.org/abs/2010.11847", "code": [ "https://github.com/DifferentiableUniverseInitiative/flowpm" ], "links": { "Paper": "https://arxiv.org/abs/2010.11847", "Code": "https://github.com/DifferentiableUniverseInitiative/flowpm" }, "resources": [ "code" ], "modality": [], "summary": "Differentiable particle-mesh N-body simulation for gradient-based inference and hybrid ML models." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "LDL", "title": "Learning Effective Physical Laws for Generating Cosmological Hydrodynamics with Lagrangian Deep Learning", "venue": "PNAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.02926", "doi": "", "url": "https://arxiv.org/abs/2010.02926", "code": [ "https://github.com/biweidai/LDL" ], "links": { "Paper": "https://arxiv.org/abs/2010.02926", "Code": "https://github.com/biweidai/LDL" }, "resources": [ "code" ], "modality": [], "summary": "Learned displacement layers that map dark matter simulations to baryonic fields." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "deep21", "title": "deep21: A Deep Learning Method for 21cm Foreground Removal", "venue": "JCAP 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.15843", "doi": "10.1088/1475-7516/2021/04/081", "url": "https://arxiv.org/abs/2010.15843", "code": [ "https://github.com/tlmakinen/deep21" ], "links": { "Paper": "https://arxiv.org/abs/2010.15843", "Code": "https://github.com/tlmakinen/deep21", "Journal": "https://doi.org/10.1088/1475-7516/2021/04/081" }, "resources": [ "code" ], "modality": [], "summary": "3D UNet ensemble that separates cosmological HI signal from radio foregrounds." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "Stellar Streams SBI", "title": "Towards Constraining Warm Dark Matter with Stellar Streams through Neural Simulation-based Inference", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 11, "arxiv_id": "2011.14923", "doi": "10.1093/mnras/stab2181", "url": "https://arxiv.org/abs/2011.14923", "code": [ "https://github.com/JoeriHermans/constraining-dark-matter-with-stellar-streams-and-ml" ], "links": { "Paper": "https://arxiv.org/abs/2011.14923", "Journal": "https://doi.org/10.1093/mnras/stab2181", "Code": "https://github.com/JoeriHermans/constraining-dark-matter-with-stellar-streams-and-ml" }, "resources": [ "code" ], "modality": [], "summary": "Neural ratio estimation for dark matter constraints from stream density variations." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "Moment Networks", "title": "Solving High-dimensional Parameter Inference: Marginal Posterior Densities & Moment Networks", "venue": "arXiv 2020", "publication_type": "Preprint", "note": "", "year": 2020, "month": 11, "arxiv_id": "2011.05991", "doi": "", "url": "https://arxiv.org/abs/2011.05991", "code": [ "https://github.com/NiallJeffrey/MomentNetworks" ], "links": { "Paper": "https://arxiv.org/abs/2011.05991", "Code": "https://github.com/NiallJeffrey/MomentNetworks" }, "resources": [ "code" ], "modality": [], "summary": "Networks that estimate marginal posterior moments for high-dimensional inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "ForSE", "title": "ForSE: A GAN-based Algorithm for Extending CMB Foreground Models to Subdegree Angular Scales", "venue": "ApJ 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 11, "arxiv_id": "2011.02221", "doi": "10.3847/1538-4357/abe71c", "url": "https://arxiv.org/abs/2011.02221", "code": [ "https://github.com/ai4cmb/ForSE" ], "links": { "Paper": "https://arxiv.org/abs/2011.02221", "Code": "https://github.com/ai4cmb/ForSE", "Journal": "https://doi.org/10.3847/1538-4357/abe71c" }, "resources": [ "code" ], "modality": [], "summary": "GAN that adds small-scale non-Gaussian structure to Galactic dust foreground maps." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "DeepSphere", "title": "DeepSphere: A Graph-based Spherical CNN", "venue": "ICLR 2020", "publication_type": "Conference", "note": "", "year": 2020, "month": 12, "arxiv_id": "2012.15000", "doi": "", "url": "https://arxiv.org/abs/2012.15000", "code": [ "https://github.com/deepsphere/deepsphere-pytorch" ], "links": { "Paper": "https://arxiv.org/abs/2012.15000", "Code": "https://github.com/deepsphere/deepsphere-pytorch" }, "resources": [ "code" ], "modality": [], "summary": "Graph convolutions on spherical sky maps such as HEALPix." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "globalemu", "title": "GLOBALEMU: A Novel and Robust Approach for Emulating the Sky-averaged 21-cm Signal from the Cosmic Dawn and Epoch of Reionization", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 4, "arxiv_id": "2104.04336", "doi": "", "url": "https://arxiv.org/abs/2104.04336", "code": [ "https://github.com/htjb/globalemu" ], "links": { "Paper": "https://arxiv.org/abs/2104.04336", "Code": "https://github.com/htjb/globalemu" }, "resources": [ "code" ], "modality": [], "summary": "Neural network emulator of the global 21-cm signal." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "CosmoPower", "title": "CosmoPower: Emulating Cosmological Power Spectra for Accelerated Bayesian Inference from Next-generation Surveys", "venue": "MNRAS 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 6, "arxiv_id": "2106.03846", "doi": "10.1093/mnras/stac064", "url": "https://arxiv.org/abs/2106.03846", "code": [ "https://github.com/alessiospuriomancini/cosmopower" ], "links": { "Paper": "https://arxiv.org/abs/2106.03846", "Code": "https://github.com/alessiospuriomancini/cosmopower", "Journal": "https://doi.org/10.1093/mnras/stac064" }, "resources": [ "code" ], "modality": [], "summary": "Neural emulators of CMB and matter power spectra." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "FieldIMNNs", "title": "Lossless, Scalable Implicit Likelihood Inference for Cosmological Fields", "venue": "JCAP 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 7, "arxiv_id": "2107.07405", "doi": "10.1088/1475-7516/2021/11/049", "url": "https://arxiv.org/abs/2107.07405", "code": [ "https://github.com/tlmakinen/FieldIMNNs" ], "links": { "Paper": "https://arxiv.org/abs/2107.07405", "Code": "https://github.com/tlmakinen/FieldIMNNs", "Journal": "https://doi.org/10.1088/1475-7516/2021/11/049" }, "resources": [ "code" ], "modality": [], "summary": "Information maximising neural network compression of Gaussian and lognormal fields followed by simulation-based inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "HaloGraphNet", "title": "Inferring Halo Masses with Graph Neural Networks", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.08683", "doi": "", "url": "https://arxiv.org/abs/2111.08683", "code": [ "https://github.com/PabloVD/HaloGraphNet" ], "links": { "Paper": "https://arxiv.org/abs/2111.08683", "Code": "https://github.com/PabloVD/HaloGraphNet" }, "resources": [ "code" ], "modality": [], "summary": "Graph neural networks trained on CAMELS to infer halo masses from galaxy properties." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "harmonic", "title": "Machine Learning Assisted Bayesian Model Comparison: Learnt Harmonic Mean Estimator", "venue": "arXiv 2021", "publication_type": "Preprint", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.12720", "doi": "", "url": "https://arxiv.org/abs/2111.12720", "code": [ "https://github.com/astro-informatics/harmonic" ], "links": { "Paper": "https://arxiv.org/abs/2111.12720", "Code": "https://github.com/astro-informatics/harmonic", "Flow Version": "https://arxiv.org/abs/2307.00048" }, "resources": [ "code" ], "modality": [], "summary": "Learned harmonic mean estimator of the Bayesian evidence from posterior samples." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "DeepMass CMB", "title": "Single Frequency CMB B-mode Inference with Realistic Foregrounds from a Single Training Image", "venue": "MNRAS Letters 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.01138", "doi": "", "url": "https://arxiv.org/abs/2111.01138", "code": [ "https://github.com/NiallJeffrey/DeepMass" ], "links": { "Paper": "https://arxiv.org/abs/2111.01138", "Code": "https://github.com/NiallJeffrey/DeepMass" }, "resources": [ "code" ], "modality": [], "summary": "Moment networks trained on a single foreground image for CMB B-mode inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "DeepLSS", "title": "DeepLSS: Breaking Parameter Degeneracies in Large-scale Structure with Deep Learning Analysis of Combined Probes", "venue": "PRX 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 3, "arxiv_id": "2203.09616", "doi": "", "url": "https://arxiv.org/abs/2203.09616", "code": [ "https://github.com/tomaszkacprzak/deeplss" ], "links": { "Paper": "https://arxiv.org/abs/2203.09616", "Code": "https://github.com/tomaszkacprzak/deeplss" }, "resources": [ "code" ], "modality": [], "summary": "Deep learning analysis of combined weak lensing and galaxy clustering maps." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "LINNA", "title": "LINNA: Likelihood Inference Neural Network Accelerator", "venue": "JCAP 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 3, "arxiv_id": "2203.05583", "doi": "10.1088/1475-7516/2023/01/016", "url": "https://arxiv.org/abs/2203.05583", "code": [ "https://github.com/chto/linna" ], "links": { "Paper": "https://arxiv.org/abs/2203.05583", "Journal": "https://doi.org/10.1088/1475-7516/2023/01/016", "Code": "https://github.com/chto/linna" }, "resources": [ "code" ], "modality": [], "summary": "Neural network emulation of the likelihood for accelerated cosmological parameter inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "CosmoGraphNet", "title": "Learning Cosmology and Clustering with Cosmic Graphs", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 4, "arxiv_id": "2204.13713", "doi": "10.3847/1538-4357/ac8930", "url": "https://arxiv.org/abs/2204.13713", "code": [ "https://github.com/PabloVD/CosmoGraphNet" ], "links": { "Paper": "https://arxiv.org/abs/2204.13713", "Journal": "https://doi.org/10.3847/1538-4357/ac8930", "Code": "https://github.com/PabloVD/CosmoGraphNet" }, "resources": [ "code" ], "modality": [], "summary": "Graph neural networks on galaxy catalogues for cosmological parameter inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "CONNECT", "title": "CONNECT: A Neural Network Based Framework for Emulating Cosmological Observables and Cosmological Parameter Inference", "venue": "JCAP 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 5, "arxiv_id": "2205.15726", "doi": "", "url": "https://arxiv.org/abs/2205.15726", "code": [ "https://github.com/AarhusCosmology/connect_public" ], "links": { "Paper": "https://arxiv.org/abs/2205.15726", "Code": "https://github.com/AarhusCosmology/connect_public" }, "resources": [ "code" ], "modality": [], "summary": "Iteratively trained emulators of CLASS observables for MCMC." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "21cmVAE", "title": "21cmVAE: A Very Accurate Emulator of the 21 cm Global Signal", "venue": "ApJ 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": null, "arxiv_id": "", "doi": "10.3847/1538-4357/ac6424", "url": "https://doi.org/10.3847/1538-4357/ac6424", "code": [ "https://github.com/christianhbye/21cmVAE" ], "links": { "Journal": "https://doi.org/10.3847/1538-4357/ac6424", "Code": "https://github.com/christianhbye/21cmVAE" }, "resources": [ "code" ], "modality": [], "summary": "Variational autoencoder emulator of the global 21-cm signal." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "CosmoPower-JAX", "title": "CosmoPower-JAX: High-dimensional Bayesian Inference with Differentiable Cosmological Emulators", "venue": "OJAp 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 5, "arxiv_id": "2305.06347", "doi": "10.21105/astro.2305.06347", "url": "https://arxiv.org/abs/2305.06347", "code": [ "https://github.com/dpiras/cosmopower-jax" ], "links": { "Paper": "https://arxiv.org/abs/2305.06347", "Journal": "https://doi.org/10.21105/astro.2305.06347", "Code": "https://github.com/dpiras/cosmopower-jax" }, "resources": [ "code" ], "modality": [], "summary": "JAX version of CosmoPower for gradient-based samplers." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "In Search of Global 21-cm Signal Using Artificial Neural Network in Light of ARCADE 2", "venue": "EPJC 2025", "publication_type": "Journal", "note": "", "year": 2023, "month": 6, "arxiv_id": "2306.02039", "doi": "10.1140/epjc/s10052-025-14256-0", "url": "https://arxiv.org/abs/2306.02039", "code": [], "links": { "Paper": "https://arxiv.org/abs/2306.02039", "Journal": "https://doi.org/10.1140/epjc/s10052-025-14256-0" }, "resources": [], "modality": [], "summary": "Neural network that extracts global 21-cm parameters from antenna temperatures with foregrounds and ionospheric distortion." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "Capse.jl", "title": "Capse.jl: Efficient and Auto-differentiable CMB Power Spectra Emulation", "venue": "OJAp 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 7, "arxiv_id": "2307.14339", "doi": "10.21105/astro.2307.14339", "url": "https://arxiv.org/abs/2307.14339", "code": [ "https://github.com/CosmologicalEmulators/Capse.jl" ], "links": { "Paper": "https://arxiv.org/abs/2307.14339", "Journal": "https://doi.org/10.21105/astro.2307.14339", "Code": "https://github.com/CosmologicalEmulators/Capse.jl" }, "resources": [ "code" ], "modality": [], "summary": "Julia neural emulator of CMB power spectra for gradient-based samplers." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "21cmEMU", "title": "21cmEMU: An Emulator of 21cmFAST Summary Observables", "venue": "MNRAS 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 9, "arxiv_id": "2309.05697", "doi": "", "url": "https://arxiv.org/abs/2309.05697", "code": [ "https://github.com/21cmfast/21cmEMU" ], "links": { "Paper": "https://arxiv.org/abs/2309.05697", "Code": "https://github.com/21cmfast/21cmEMU" }, "resources": [ "code" ], "modality": [], "summary": "Neural emulator of 21cmFAST power spectra and global signals." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Optimal Neural Summarisation for Full-Field Weak Lensing Cosmological Implicit Inference", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.10877", "doi": "", "url": "https://arxiv.org/abs/2407.10877", "code": [ "https://github.com/DifferentiableUniverseInitiative/sbi_lens" ], "links": { "Paper": "https://arxiv.org/abs/2407.10877", "Code": "https://github.com/DifferentiableUniverseInitiative/sbi_lens" }, "resources": [ "code" ], "modality": [], "summary": "Compares neural compression losses against an HMC full-field reference with a differentiable lognormal simulator." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Simulation-based Inference Benchmark for Weak Lensing Cosmology", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 9, "arxiv_id": "2409.17975", "doi": "", "url": "https://arxiv.org/abs/2409.17975", "code": [], "links": { "Paper": "https://arxiv.org/abs/2409.17975" }, "resources": [], "modality": [], "summary": "Compares simulation budgets of explicit and implicit full-field inference for LSST Y10-like convergence maps." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Nonlinear Reconstruction of 21cm Global Signal from 21cm Power Spectrum with Artificial Neural Networks", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 12, "arxiv_id": "2412.20862", "doi": "", "url": "https://arxiv.org/abs/2412.20862", "code": [], "links": { "Paper": "https://arxiv.org/abs/2412.20862" }, "resources": [], "modality": [], "summary": "Neural network that predicts the global 21-cm signal from power spectrum measurements under SKA-like noise." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "Effort.jl", "title": "Effort.jl: A Fast and Differentiable Emulator for the Effective Field Theory of the Large Scale Structure of the Universe", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 1, "arxiv_id": "2501.04639", "doi": "", "url": "https://arxiv.org/abs/2501.04639", "code": [ "https://github.com/CosmologicalEmulators/Effort.jl" ], "links": { "Paper": "https://arxiv.org/abs/2501.04639", "Code": "https://github.com/CosmologicalEmulators/Effort.jl" }, "resources": [ "code" ], "modality": [], "summary": "Differentiable neural emulator of EFTofLSS galaxy power spectra." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Dark Energy Survey Year 3 Results: wCDM Cosmology from Simulation-based Inference with Persistent Homology on the Sphere", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 6, "arxiv_id": "2506.13439", "doi": "", "url": "https://arxiv.org/abs/2506.13439", "code": [], "links": { "Paper": "https://arxiv.org/abs/2506.13439" }, "resources": [], "modality": [], "summary": "Spherical persistent homology summaries with neural compression and likelihood estimation on DES Y3 lensing maps." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "21cmLSTM / 21cmKAN", "title": "Emulating Global 21 cm Cosmology Observations from the Lunar Far Side to Achieve Quick and Reliable Physical Constraints", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.00976", "doi": "", "url": "https://arxiv.org/abs/2509.00976", "code": [ "https://github.com/jdorigojones/21cmKAN" ], "links": { "Paper": "https://arxiv.org/abs/2509.00976", "Code": "https://github.com/jdorigojones/21cmKAN" }, "resources": [ "code" ], "modality": [], "summary": "LSTM and Kolmogorov-Arnold network emulators of the global 21-cm signal for Bayesian inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Exploring the Early Universe with Deep Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.22018", "doi": "", "url": "https://arxiv.org/abs/2509.22018", "code": [], "links": { "Paper": "https://arxiv.org/abs/2509.22018" }, "resources": [], "modality": [], "summary": "Benchmark of deep learning models that recover the neutral hydrogen fraction from 2D 21-cm power spectra." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Dark Energy Survey Year 3 Results: Simulation-based wCDM Inference from Weak Lensing and Galaxy Clustering Maps with Deep Learning. I. Analysis Design", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.04681", "doi": "", "url": "https://arxiv.org/abs/2511.04681", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.04681" }, "resources": [], "modality": [], "summary": "Graph CNN compression of spherical lensing and clustering maps with normalizing-flow likelihoods." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Fast End-to-End Framework for Cosmological Parameter Inference from CMB Data Using Machine Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.01291", "doi": "", "url": "https://arxiv.org/abs/2511.01291", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.01291" }, "resources": [], "modality": [], "summary": "Combines analytical blind separation of foregrounds with neural network parameter inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Deep-learning Mitigation of Foregrounds and Beam Effects in 21-cm Intensity Mapping Using Hybrid Frequency Differencing and PCA", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.15072", "doi": "", "url": "https://arxiv.org/abs/2511.15072", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.15072" }, "resources": [], "modality": [], "summary": "Two-channel UNet with frequency-differenced and PCA-cleaned inputs for HI reconstruction under realistic beams." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Dark Energy Survey Year 3 Results: Optimized wCDM Simulation-based Inference with Weak Lensing Map-level Hybrid Statistics", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.11309", "doi": "", "url": "https://arxiv.org/abs/2606.11309", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.11309" }, "resources": [], "modality": [], "summary": "Hybrid power spectrum and neural summaries that compress DES Y3 lensing maps to seven statistics." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Field-level Weak Lensing Cosmology with 60 Simulations Using Multifidelity Simulation-based Inference", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.23346", "doi": "", "url": "https://arxiv.org/abs/2606.23346", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.23346" }, "resources": [], "modality": [], "summary": "Pretraining on lognormal mocks and fine-tuning on 60 N-body simulations for KiDS-Legacy field-level inference." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Simulation-Based Inference for Cluster Cosmology with Set-Based Neural Network Architectures", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.27439", "doi": "", "url": "https://arxiv.org/abs/2606.27439", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.27439" }, "resources": [], "modality": [], "summary": "Set-based networks and autoregressive flows on eRASS1-like cluster catalogues." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "From Dark Matter to Galaxies: Halo-Free Mock Generation via Conditional Point-Cloud Diffusion", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.19808", "doi": "", "url": "https://arxiv.org/abs/2607.19808", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.19808" }, "resources": [], "modality": [], "summary": "Point-cloud diffusion that generates galaxy positions and star formation rates from IllustrisTNG dark matter fields." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "JADE", "title": "Joint Inference of Weak Lensing Convergence Map and Cosmology with Diffusion Models", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.31988", "doi": "", "url": "https://arxiv.org/abs/2606.31988", "code": [ "https://github.com/b-remy/jade" ], "links": { "Paper": "https://arxiv.org/abs/2606.31988", "Code": "https://github.com/b-remy/jade" }, "resources": [ "code" ], "modality": [], "summary": "Pixel-space diffusion transformer that treats cosmological parameters as tokens and samples convergence maps and parameters jointly from noisy shear fields." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "C3NN-SBI", "title": "C3NN-SBI: Learning Hierarchies of N-Point Statistics from Cosmological Fields with Physics-Informed Neural Networks", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 2, "arxiv_id": "2602.16768", "doi": "", "url": "https://arxiv.org/abs/2602.16768", "code": [], "links": { "Paper": "https://arxiv.org/abs/2602.16768" }, "resources": [], "modality": [], "summary": "Couples a correlator convolutional network whose summaries map to given N-point orders with simulation-based inference on DES Y3-like convergence maps." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "The Shear-to-Cosmology Paradigm I. Hybrid Field-Level and Simulation-Based Framework for Weak Lensing Surveys", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.22851", "doi": "", "url": "https://arxiv.org/abs/2511.22851", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.22851" }, "resources": [], "modality": [], "summary": "Maps observed shear fields directly to cosmological parameters, roughly doubling the figure of merit of convergence-based inference on CSST-like mocks." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "", "title": "Neural Posterior Estimation for Tomographic Weak Lensing Mass Mapping", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.07833", "doi": "", "url": "https://arxiv.org/abs/2609.07833", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.07833" }, "resources": [], "modality": [], "summary": "Amortised network that maps multiband images directly to a variational posterior over tomographic shear and convergence, validated on LSST DESC DC2 images." }, { "section": "Cosmology and Large-Scale Structure", "subsection": "", "name": "CLiENT", "title": "CLiENT: A New Tool for Emulating Cosmological Likelihoods Using Deep Neural Networks", "venue": "JCAP 2026", "publication_type": "Journal", "note": "", "year": 2025, "month": 12, "arxiv_id": "2512.17509", "doi": "10.1088/1475-7516/2026/08/018", "url": "https://arxiv.org/abs/2512.17509", "code": [ "https://github.com/AarhusCosmology/client_public" ], "links": { "Paper": "https://arxiv.org/abs/2512.17509", "Journal": "https://doi.org/10.1088/1475-7516/2026/08/018", "Code": "https://github.com/AarhusCosmology/client_public" }, "resources": [ "code" ], "modality": [], "summary": "Emulates the likelihood of a data set directly with neural networks, giving an auto-differentiable surrogate that matches true-likelihood credible intervals to within 0.1 sigma using fewer than 20,000 evaluations." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "pydelfi", "title": "Fast Likelihood-free Cosmology with Neural Density Estimators and Active Learning", "venue": "MNRAS 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 3, "arxiv_id": "1903.00007", "doi": "", "url": "https://arxiv.org/abs/1903.00007", "code": [ "https://github.com/justinalsing/pydelfi" ], "links": { "Paper": "https://arxiv.org/abs/1903.00007", "Code": "https://github.com/justinalsing/pydelfi" }, "resources": [ "code" ], "modality": [], "summary": "Density-estimation likelihood-free inference with active simulation acquisition." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "swyft", "title": "Truncated Marginal Neural Ratio Estimation", "venue": "NeurIPS 2021", "publication_type": "Conference", "note": "", "year": 2021, "month": 7, "arxiv_id": "2107.01214", "doi": "", "url": "https://arxiv.org/abs/2107.01214", "code": [ "https://github.com/undark-lab/swyft" ], "links": { "Paper": "https://arxiv.org/abs/2107.01214", "Code": "https://github.com/undark-lab/swyft" }, "resources": [ "code" ], "modality": [], "summary": "Simulation-efficient marginal posterior estimation with prior truncation." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "swyft TMNRE", "title": "Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation", "venue": "JCAP 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.08030", "doi": "10.1088/1475-7516/2022/09/004", "url": "https://arxiv.org/abs/2111.08030", "code": [ "https://github.com/undark-lab/swyft" ], "links": { "Paper": "https://arxiv.org/abs/2111.08030", "Journal": "https://doi.org/10.1088/1475-7516/2022/09/004", "Code": "https://github.com/undark-lab/swyft" }, "resources": [ "code" ], "modality": [], "summary": "Truncated marginal neural ratio estimation applied to CMB cosmological inference." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "margarine", "title": "Marginal Post Processing of Bayesian Inference Products with Normalizing Flows and Kernel Density Estimators", "venue": "MNRAS 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 5, "arxiv_id": "2205.12841", "doi": "", "url": "https://arxiv.org/abs/2205.12841", "code": [ "https://github.com/htjb/margarine" ], "links": { "Paper": "https://arxiv.org/abs/2205.12841", "Code": "https://github.com/htjb/margarine" }, "resources": [ "code" ], "modality": [], "summary": "Normalizing flows and KDEs that learn nuisance-free marginal posteriors for marginal KL divergences and emulation." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "pocoMC", "title": "Accelerating Astronomical and Cosmological Inference with Preconditioned Monte Carlo", "venue": "MNRAS 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 7, "arxiv_id": "2207.05652", "doi": "10.1093/mnras/stac2272", "url": "https://arxiv.org/abs/2207.05652", "code": [ "https://github.com/minaskar/pocomc" ], "links": { "Paper": "https://arxiv.org/abs/2207.05652", "Journal": "https://doi.org/10.1093/mnras/stac2272", "Code": "https://github.com/minaskar/pocomc" }, "resources": [ "code" ], "modality": [], "summary": "Sequential Monte Carlo sampler preconditioned with normalizing flows." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "GPry", "title": "Fast and Robust Bayesian Inference Using Gaussian Processes with GPry", "venue": "JCAP 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 11, "arxiv_id": "2211.02045", "doi": "10.1088/1475-7516/2023/10/021", "url": "https://arxiv.org/abs/2211.02045", "code": [ "https://github.com/jonaselgammal/GPry" ], "links": { "Paper": "https://arxiv.org/abs/2211.02045", "Code": "https://github.com/jonaselgammal/GPry", "Journal": "https://doi.org/10.1088/1475-7516/2023/10/021" }, "resources": [ "code" ], "modality": [], "summary": "Active-learning Gaussian process surrogate of the posterior for expensive cosmological likelihoods." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "TARP", "title": "Sampling-Based Accuracy Testing of Posterior Estimators for General Inference", "venue": "ICML 2023", "publication_type": "Conference", "note": "", "year": 2023, "month": 2, "arxiv_id": "2302.03026", "doi": "", "url": "https://arxiv.org/abs/2302.03026", "code": [ "https://github.com/Ciela-Institute/tarp" ], "links": { "Paper": "https://arxiv.org/abs/2302.03026", "Code": "https://github.com/Ciela-Institute/tarp" }, "resources": [ "code" ], "modality": [], "summary": "Coverage test that checks generative posterior estimators using samples alone." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "nautilus", "title": "nautilus: Boosting Bayesian Importance Nested Sampling with Deep Learning", "venue": "MNRAS 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 6, "arxiv_id": "2306.16923", "doi": "10.1093/mnras/stad2441", "url": "https://arxiv.org/abs/2306.16923", "code": [ "https://github.com/johannesulf/nautilus" ], "links": { "Paper": "https://arxiv.org/abs/2306.16923", "Journal": "https://doi.org/10.1093/mnras/stad2441", "Code": "https://github.com/johannesulf/nautilus" }, "resources": [ "code" ], "modality": [], "summary": "Importance nested sampling with neural network emulation of the likelihood contours." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "nbi", "title": "nbi: The Astronomer's Package for Neural Posterior Estimation", "venue": "NeurIPS 2023 Workshop (DLIP)", "publication_type": "Workshop", "note": "", "year": 2023, "month": 12, "arxiv_id": "2312.03824", "doi": "", "url": "https://arxiv.org/abs/2312.03824", "code": [ "https://github.com/kmzzhang/nbi" ], "links": { "Paper": "https://arxiv.org/abs/2312.03824", "Code": "https://github.com/kmzzhang/nbi" }, "resources": [ "code" ], "modality": [], "summary": "Neural posterior estimation package with featurizers for light curves and spectra." }, { "section": "Simulation-Based Inference", "subsection": "", "name": "LtU-ILI", "title": "LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology", "venue": "OJAp 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": 2, "arxiv_id": "2402.05137", "doi": "10.33232/001c.120559", "url": "https://arxiv.org/abs/2402.05137", "code": [ "https://github.com/maho3/ltu-ili" ], "links": { "Paper": "https://arxiv.org/abs/2402.05137", "Code": "https://github.com/maho3/ltu-ili", "Journal": "https://doi.org/10.33232/001c.120559" }, "resources": [ "code" ], "modality": [], "summary": "Unified interface over sbi, pydelfi and lampe with validation and calibration tools." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "GCE BGCNN", "title": "Galactic Center Excess in a New Light: Disentangling the γ-Ray Sky with Bayesian Graph Convolutional Neural Networks", "venue": "PRL 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": 6, "arxiv_id": "2006.12504", "doi": "10.1103/PhysRevLett.125.241102", "url": "https://arxiv.org/abs/2006.12504", "code": [ "https://github.com/FloList/GCE_NN" ], "links": { "Paper": "https://arxiv.org/abs/2006.12504", "Code": "https://github.com/FloList/GCE_NN", "Journal": "https://doi.org/10.1103/PhysRevLett.125.241102" }, "resources": [ "code" ], "modality": [], "summary": "Bayesian graph CNNs on HEALPix maps that separate point-source and smooth contributions to the Fermi Galactic Center Excess." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "GCE SCD", "title": "Extracting the Galactic Center Excess' Source-count Distribution with Neural Nets", "venue": "PRD 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 7, "arxiv_id": "2107.09070", "doi": "10.1103/PhysRevD.104.123022", "url": "https://arxiv.org/abs/2107.09070", "code": [ "https://github.com/FloList/GCE_NN" ], "links": { "Paper": "https://arxiv.org/abs/2107.09070", "Code": "https://github.com/FloList/GCE_NN", "Journal": "https://doi.org/10.1103/PhysRevD.104.123022" }, "resources": [ "code" ], "modality": [], "summary": "Neural networks that estimate source-count distributions and flux fractions of gamma-ray templates." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "Fermi GCE SBI", "title": "A Neural Simulation-based Inference Approach for Characterizing the Galactic Center γ-ray Excess", "venue": "PRD 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 10, "arxiv_id": "2110.06931", "doi": "10.1103/PhysRevD.105.063017", "url": "https://arxiv.org/abs/2110.06931", "code": [ "https://github.com/smsharma/fermi-gce-flows" ], "links": { "Paper": "https://arxiv.org/abs/2110.06931", "Journal": "https://doi.org/10.1103/PhysRevD.105.063017", "Code": "https://github.com/smsharma/fermi-gce-flows" }, "resources": [ "code" ], "modality": [], "summary": "Normalizing-flow posterior estimation on spherical Fermi-LAT maps with graph neural network summaries." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "GraphNeT IceCube", "title": "Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube", "venue": "JINST 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": 9, "arxiv_id": "2209.03042", "doi": "10.1088/1748-0221/17/11/P11003", "url": "https://arxiv.org/abs/2209.03042", "code": [ "https://github.com/graphnet-team/graphnet" ], "links": { "Paper": "https://arxiv.org/abs/2209.03042", "Code": "https://github.com/graphnet-team/graphnet", "Journal": "https://doi.org/10.1088/1748-0221/17/11/P11003" }, "resources": [ "code" ], "modality": [], "summary": "Point-cloud GNN that classifies and reconstructs GeV-scale neutrino events in IceCube." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "DeepGRB", "title": "Deep Learning for Gamma-Ray Bursts: A Data Driven Event Framework for X/Gamma-Ray Analysis in Space Telescopes", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 1, "arxiv_id": "2401.15632", "doi": "", "url": "https://arxiv.org/abs/2401.15632", "code": [], "links": { "Paper": "https://arxiv.org/abs/2401.15632" }, "resources": [], "modality": [], "summary": "Neural background estimation with FOCuS-Poisson trigger search on Fermi-GBM count rates." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "", "title": "A Robust Neural Determination of the Source-count Distribution of the Fermi-LAT Sky at High Latitudes", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.02906", "doi": "", "url": "https://arxiv.org/abs/2505.02906", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.02906" }, "resources": [], "modality": [], "summary": "Neural ratio estimation with spherical convolutions on 14 years of high-latitude Fermi-LAT photon maps." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "", "title": "Unsupervised Machine Learning Classification of Gamma-ray Bursts Based on the Rest-frame Prompt Emission Parameters", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.08224", "doi": "", "url": "https://arxiv.org/abs/2509.08224", "code": [], "links": { "Paper": "https://arxiv.org/abs/2509.08224" }, "resources": [], "modality": [], "summary": "Unsupervised clustering of GRBs into types using rest-frame prompt emission properties." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "ASID", "title": "Towards a Foundation Model for Astrophysical Source Detection: An End-to-End Gamma-Ray Data Analysis Pipeline Using Deep Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.25128", "doi": "", "url": "https://arxiv.org/abs/2509.25128", "code": [], "links": { "Paper": "https://arxiv.org/abs/2509.25128" }, "resources": [], "modality": [], "summary": "U-Net detection with CNN classification and deep-ensemble flux estimation on Fermi-LAT and CTAO simulations." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "", "title": "Multivariate Time Series Classification of Fermi-Detected Gamma-Ray Transients Using Convolutional-Recurrent Neural Networks", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.22412", "doi": "", "url": "https://arxiv.org/abs/2510.22412", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.22412" }, "resources": [], "modality": [], "summary": "CNN-LSTM classifiers that separate GRBs, TGFs, solar flares and SGRs in Fermi-GBM light curves and flag outliers." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "candela", "title": "A Differentiable Neural Surrogate for Photon Propagation in Neutrino Telescopes", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.04695", "doi": "", "url": "https://arxiv.org/abs/2609.04695", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.04695" }, "resources": [], "modality": [], "summary": "SIREN neural field that learns the IceCube photon Green function, predicting photon yield and arrival-time distributions for a point energy deposit and sensor." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "GammaLearn", "title": "Deep Learning for Cherenkov Astronomy: Performance of GammaLearn on LST-1", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 10, "arxiv_id": "2610.10392", "doi": "", "url": "https://arxiv.org/abs/2610.10392", "code": [], "links": { "Paper": "https://arxiv.org/abs/2610.10392" }, "resources": [], "modality": [], "summary": "Applies the gamma-PhysNet CNN to LST-1 Crab Nebula observations, improving sensitivity over the random forest analysis below 1 TeV." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "", "title": "Fast Low Energy Reconstruction Using Convolutional Neural Networks", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 5, "arxiv_id": "2505.16777", "doi": "", "url": "https://arxiv.org/abs/2505.16777", "code": [], "links": { "Paper": "https://arxiv.org/abs/2505.16777" }, "resources": [], "modality": [], "summary": "IceCube Collaboration CNNs that reconstruct energy, direction, vertex and flavour signature of GeV neutrinos in DeepCore for oscillation measurements." }, { "section": "High-Energy Astrophysics and Astroparticle Physics", "subsection": "", "name": "", "title": "Enhancing Events in Neutrino Telescopes through Deep Learning-Driven Super-Resolution", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 8, "arxiv_id": "2408.08474", "doi": "", "url": "https://arxiv.org/abs/2408.08474", "code": [], "links": { "Paper": "https://arxiv.org/abs/2408.08474" }, "resources": [], "modality": [], "summary": "Predicts hits on virtual optical modules between real ones to super-resolve neutrino telescope events, improving muon angular reconstruction." }, { "section": "Gravitational Waves", "subsection": "", "name": "Magic Bullet", "title": "Convolutional Neural Networks: A Magic Bullet for Gravitational-wave Detection?", "venue": "PRD 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 4, "arxiv_id": "1904.08693", "doi": "", "url": "https://arxiv.org/abs/1904.08693", "code": [ "https://github.com/timothygebhard/magic-bullet" ], "links": { "Paper": "https://arxiv.org/abs/1904.08693", "Code": "https://github.com/timothygebhard/magic-bullet" }, "resources": [ "code" ], "modality": [], "summary": "Critical evaluation of CNN-based gravitational-wave detection." }, { "section": "Gravitational Waves", "subsection": "", "name": "VItamin", "title": "Bayesian Parameter Estimation Using Conditional Variational Autoencoders for Gravitational-wave Astronomy", "venue": "Nature Physics 2022", "publication_type": "Journal", "note": "", "year": 2019, "month": 9, "arxiv_id": "1909.06296", "doi": "", "url": "https://arxiv.org/abs/1909.06296", "code": [ "https://github.com/hagabbar/vitamin_c" ], "links": { "Paper": "https://arxiv.org/abs/1909.06296", "Code": "https://github.com/hagabbar/vitamin_c" }, "resources": [ "code" ], "modality": [], "summary": "Conditional VAE for rapid compact binary parameter estimation." }, { "section": "Gravitational Waves", "subsection": "", "name": "DeepClean", "title": "Noise Reduction in Gravitational-wave Data via Deep Learning", "venue": "Phys. Rev. Res. 2020", "publication_type": "Journal", "note": "", "year": 2020, "month": 5, "arxiv_id": "2005.06534", "doi": "10.1103/PhysRevResearch.2.033066", "url": "https://arxiv.org/abs/2005.06534", "code": [ "https://github.com/ML4GW/DeepClean" ], "links": { "Paper": "https://arxiv.org/abs/2005.06534", "Journal": "https://doi.org/10.1103/PhysRevResearch.2.033066", "Code": "https://github.com/ML4GW/DeepClean" }, "resources": [ "code" ], "modality": [], "summary": "Neural network for low-frequency noise subtraction in gravitational-wave detectors." }, { "section": "Gravitational Waves", "subsection": "", "name": "nessai", "title": "Nested Sampling with Normalizing Flows for Gravitational-wave Inference", "venue": "PRD 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 2, "arxiv_id": "2102.11056", "doi": "", "url": "https://arxiv.org/abs/2102.11056", "code": [ "https://github.com/mj-will/nessai" ], "links": { "Paper": "https://arxiv.org/abs/2102.11056", "Importance Nested Sampling": "https://arxiv.org/abs/2302.08526", "Code": "https://github.com/mj-will/nessai" }, "resources": [ "code" ], "modality": [], "summary": "Nested sampler that uses normalizing flows to propose new live points." }, { "section": "Gravitational Waves", "subsection": "", "name": "DINGO", "title": "Real-time Gravitational-wave Science with Neural Posterior Estimation", "venue": "PRL 2021", "publication_type": "Journal", "note": "", "year": 2021, "month": 6, "arxiv_id": "2106.12594", "doi": "10.1103/PhysRevLett.127.241103", "url": "https://arxiv.org/abs/2106.12594", "code": [ "https://github.com/dingo-gw/dingo" ], "links": { "Paper": "https://arxiv.org/abs/2106.12594", "Code": "https://github.com/dingo-gw/dingo", "Journal": "https://doi.org/10.1103/PhysRevLett.127.241103" }, "resources": [ "code" ], "modality": [], "summary": "Normalizing-flow posteriors for binary black hole events with inference times of about a minute." }, { "section": "Gravitational Waves", "subsection": "", "name": "flowMC", "title": "flowMC: Normalizing Flow Enhanced Sampling Package for Probabilistic Inference in JAX", "venue": "JOSS 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 11, "arxiv_id": "2211.06397", "doi": "10.21105/joss.05021", "url": "https://arxiv.org/abs/2211.06397", "code": [ "https://github.com/kazewong/flowMC" ], "links": { "Paper": "https://arxiv.org/abs/2211.06397", "Journal": "https://doi.org/10.21105/joss.05021", "Code": "https://github.com/kazewong/flowMC" }, "resources": [ "code" ], "modality": [], "summary": "MCMC with normalizing-flow global proposals, used for gravitational-wave parameter estimation." }, { "section": "Gravitational Waves", "subsection": "", "name": "Peregrine", "title": "Peregrine: Sequential Simulation-based Inference for Gravitational Wave Signals", "venue": "PRD 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": 4, "arxiv_id": "2304.02035", "doi": "10.1103/PhysRevD.108.042004", "url": "https://arxiv.org/abs/2304.02035", "code": [ "https://github.com/PEREGRINE-GW/peregrine" ], "links": { "Paper": "https://arxiv.org/abs/2304.02035", "Journal": "https://doi.org/10.1103/PhysRevD.108.042004", "Code": "https://github.com/PEREGRINE-GW/peregrine" }, "resources": [ "code" ], "modality": [], "summary": "Truncated marginal neural ratio estimation for compact binary parameter estimation." }, { "section": "Gravitational Waves", "subsection": "", "name": "Aframe", "title": "A Machine-learning Pipeline for Real-time Detection of Gravitational Waves from Compact Binary Coalescences", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 3, "arxiv_id": "2403.18661", "doi": "", "url": "https://arxiv.org/abs/2403.18661", "code": [ "https://github.com/ML4GW/aframe" ], "links": { "Paper": "https://arxiv.org/abs/2403.18661", "Code": "https://github.com/ML4GW/aframe" }, "resources": [ "code" ], "modality": [], "summary": "Low-latency neural network search pipeline used in O4." }, { "section": "Gravitational Waves", "subsection": "", "name": "GWAK", "title": "GWAK: Gravitational-Wave Anomalous Knowledge with Recurrent Autoencoders", "venue": "MLST 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": null, "arxiv_id": "", "doi": "10.1088/2632-2153/ad3a31", "url": "https://doi.org/10.1088/2632-2153/ad3a31", "code": [ "https://github.com/ML4GW/gwak" ], "links": { "Journal": "https://doi.org/10.1088/2632-2153/ad3a31", "Code": "https://github.com/ML4GW/gwak" }, "resources": [ "code" ], "modality": [], "summary": "Semi-supervised anomaly detection for unmodeled gravitational-wave transients." }, { "section": "Gravitational Waves", "subsection": "", "name": "DINGO-BNS", "title": "Real-time Inference for Binary Neutron Star Mergers Using Machine Learning", "venue": "Nature 2025", "publication_type": "Journal", "note": "", "year": 2024, "month": 7, "arxiv_id": "2407.09602", "doi": "", "url": "https://arxiv.org/abs/2407.09602", "code": [ "https://github.com/dingo-gw/dingo" ], "links": { "Paper": "https://arxiv.org/abs/2407.09602", "Code": "https://github.com/dingo-gw/dingo" }, "resources": [ "code" ], "modality": [], "summary": "Prior-conditioned neural posterior estimation that infers all BNS parameters in about one second, including before merger." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "A Machine-learning Classifier for the Postmerger Remnant of Binary Neutron Stars", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 8, "arxiv_id": "2408.10678", "doi": "", "url": "https://arxiv.org/abs/2408.10678", "code": [], "links": { "Paper": "https://arxiv.org/abs/2408.10678" }, "resources": [], "modality": [], "summary": "Gradient boosted trees trained on numerical-relativity simulations predict BNS merger outcomes from inspiral parameters." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "A Binary Neutron Star Merger Search Pipeline Powered by Deep Learning", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 9, "arxiv_id": "2409.06266", "doi": "", "url": "https://arxiv.org/abs/2409.06266", "code": [], "links": { "Paper": "https://arxiv.org/abs/2409.06266" }, "resources": [], "modality": [], "summary": "CNN on matched-filter SNR time series that detects BNS mergers and is robust to glitches." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "AI-enabled Gravitational-waves Searches for Binary Neutron Stars at Optimal Sensitivity", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.01372", "doi": "", "url": "https://arxiv.org/abs/2607.01372", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.01372" }, "resources": [], "modality": [], "summary": "Neural network BNS search with heterodyned inputs that runs in real time on a single GPU." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "Scalable and Sequential Inference of the Neutron Star Equation of State with the Einstein Telescope", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 10, "arxiv_id": "2610.07975", "doi": "", "url": "https://arxiv.org/abs/2610.07975", "code": [], "links": { "Paper": "https://arxiv.org/abs/2610.07975" }, "resources": [], "modality": [], "summary": "Normalizing-flow stacking of single-event posteriors with GPU sequential Monte Carlo for EOS inference." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "Deep-Learning-Assisted Bayesian Inference for Extreme-Mass-Ratio Inspirals", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.11922", "doi": "", "url": "https://arxiv.org/abs/2611.11922", "code": [], "links": { "Paper": "https://arxiv.org/abs/2611.11922" }, "resources": [], "modality": [], "summary": "Deep learning acceleration of Bayesian parameter inference for EMRI signals." }, { "section": "Gravitational Waves", "subsection": "", "name": "labrador", "title": "A Domain-Optimized Machine-Learning Tool for Gravitational Wave Inference", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.08897", "doi": "", "url": "https://arxiv.org/abs/2604.08897", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.08897" }, "resources": [], "modality": [], "summary": "Neural posterior estimation with heterodyning, tailored coordinates and neural rescaling built on cogwheel, covering long signals with secondary masses below 10 solar masses." }, { "section": "Gravitational Waves", "subsection": "", "name": "BilbyFlow", "title": "BilbyFlow: User-Friendly Neural Posterior Estimation for Gravitational-Wave Astronomy", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.00766", "doi": "", "url": "https://arxiv.org/abs/2609.00766", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.00766" }, "resources": [], "modality": [], "summary": "Adds neural posterior estimation to Bilby, analysing 38 high-mass GWTC-3 events with a median importance-sampling efficiency of 7 percent." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "Factorized Neural Posterior Estimation for Rapid and Reliable Inference of Parameterized Post-Einsteinian Deviation Parameters in Gravitational Waves", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 2, "arxiv_id": "2602.01319", "doi": "", "url": "https://arxiv.org/abs/2602.01319", "code": [], "links": { "Paper": "https://arxiv.org/abs/2602.01319" }, "resources": [], "modality": [], "summary": "Independent normalizing flows for each ppE deviation parameter give posteriors in about 0.4 s per event, a speedup of about 9 x 10^4 over MCMC." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "Searching for Gravitational Wave Echo with Group Equivariant Neural Posterior Estimation", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.18337", "doi": "", "url": "https://arxiv.org/abs/2609.18337", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.18337" }, "resources": [], "modality": [], "summary": "DINGO-based GNPE model for echo searches that analyses an O4a event in under 20 minutes on one GPU and finds no significant echo evidence." }, { "section": "Gravitational Waves", "subsection": "", "name": "", "title": "Identifying Lensed Gravitational Waves with Physics-Informed Posterior Learning", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.03885", "doi": "", "url": "https://arxiv.org/abs/2607.03885", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.03885" }, "resources": [], "modality": [], "summary": "Fuses waveform features with neural posterior samples of common-source parameters to rank lensed multi-image signals against unrelated overlapping mergers in O4 data." }, { "section": "Gravitational Waves", "subsection": "", "name": "DINGO-lensing", "title": "Identification and Characterization of Distorted Gravitational Waves by Lensing Using Deep Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.07186", "doi": "", "url": "https://arxiv.org/abs/2511.07186", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.07186" }, "resources": [], "modality": [], "summary": "Extends DINGO to lensed signals, reducing parameter estimation and lensing Bayes factor computation from weeks to seconds while matching Bilby." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "", "title": "Identification of chromospheric dynamical signatures in the 2022 December 27 solar flare with DKIST", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 11, "arxiv_id": "2611.13147", "doi": "", "url": "https://arxiv.org/abs/2611.13147", "code": [], "links": { "Paper": "https://arxiv.org/abs/2611.13147" }, "resources": [], "modality": [], "summary": "A two-stage k-means pipeline groups 17,422 DKIST Ca II flare profiles into 19 spectral clusters and maps chromospheric kernel–halo structure." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "DeepVel", "title": "DeepVel: Deep Learning for the Estimation of Horizontal Velocities at the Solar Surface", "venue": "A&A 2017", "publication_type": "Journal", "note": "", "year": 2017, "month": 3, "arxiv_id": "1703.05128", "doi": "", "url": "https://arxiv.org/abs/1703.05128", "code": [ "https://github.com/aasensio/deepvel" ], "links": { "Paper": "https://arxiv.org/abs/1703.05128", "Code": "https://github.com/aasensio/deepvel" }, "resources": [ "code" ], "modality": [], "summary": "End-to-end network that estimates horizontal velocity fields from pairs of granulation images." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "Enhance", "title": "Enhancing SDO/HMI Images Using Deep Learning", "venue": "A&A 2018", "publication_type": "Journal", "note": "", "year": 2017, "month": 6, "arxiv_id": "1706.02933", "doi": "", "url": "https://arxiv.org/abs/1706.02933", "code": [ "https://github.com/cdiazbas/enhance" ], "links": { "Paper": "https://arxiv.org/abs/1706.02933", "Code": "https://github.com/cdiazbas/enhance" }, "resources": [ "code" ], "modality": [], "summary": "Deconvolution and super-resolution of HMI continuum images and magnetograms." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "SDOML", "title": "A Machine-learning Data Set Prepared from the NASA Solar Dynamics Observatory Mission", "venue": "ApJS 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 3, "arxiv_id": "1903.04538", "doi": "10.3847/1538-4365/ab1005", "url": "https://arxiv.org/abs/1903.04538", "code": [ "https://github.com/fluxtransport/SDOML" ], "links": { "Paper": "https://arxiv.org/abs/1903.04538", "Code": "https://github.com/fluxtransport/SDOML", "Journal": "https://doi.org/10.3847/1538-4365/ab1005" }, "resources": [ "code" ], "modality": [], "summary": "Curated 6.5 TB AIA, HMI and EVE dataset with baselines for EUV irradiance forecasting and instrument translation." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "SICON", "title": "Stokes Inversion Based on Convolutional Neural Networks", "venue": "A&A 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 4, "arxiv_id": "1904.03714", "doi": "", "url": "https://arxiv.org/abs/1904.03714", "code": [ "https://github.com/aasensio/sicon" ], "links": { "Paper": "https://arxiv.org/abs/1904.03714", "Code": "https://github.com/aasensio/sicon" }, "resources": [ "code" ], "modality": [], "summary": "Fully convolutional networks that invert Hinode Stokes maps into 3D thermodynamic and magnetic cubes." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "Slic", "title": "Fast Solar Image Classification Using Deep Learning and Its Importance for Automation in Solar Physics", "venue": "Solar Physics 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": 5, "arxiv_id": "1905.13575", "doi": "", "url": "https://arxiv.org/abs/1905.13575", "code": [ "https://github.com/rhero12/Slic" ], "links": { "Paper": "https://arxiv.org/abs/1905.13575", "Code": "https://github.com/rhero12/Slic" }, "resources": [ "code" ], "modality": [], "summary": "CNN classification of solar features in H-alpha images." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "Unsupervised MFBD", "title": "Learning to Do Multiframe Blind Deconvolution Unsupervisedly", "venue": "A&A 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 6, "arxiv_id": "2006.01438", "doi": "", "url": "https://arxiv.org/abs/2006.01438", "code": [ "https://github.com/aasensio/unsupervisedMFBD" ], "links": { "Paper": "https://arxiv.org/abs/2006.01438", "Code": "https://github.com/aasensio/unsupervisedMFBD" }, "resources": [ "code" ], "modality": [], "summary": "Unsupervised neural multiframe blind deconvolution of solar observations." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "NF2", "title": "Probing the Solar Coronal Magnetic Field with Physics-informed Neural Networks", "venue": "Nature Astronomy 2023", "publication_type": "Journal", "note": "", "year": 2023, "month": null, "arxiv_id": "", "doi": "10.1038/s41550-023-02030-9", "url": "https://doi.org/10.1038/s41550-023-02030-9", "code": [ "https://github.com/RobertJaro/NF2" ], "links": { "Code": "https://github.com/RobertJaro/NF2", "Journal": "https://doi.org/10.1038/s41550-023-02030-9", "Multi-height": "https://doi.org/10.3847/2041-8213/ad2450" }, "resources": [ "code" ], "modality": [], "summary": "Physics-informed neural network extrapolation of force-free coronal magnetic fields from photospheric magnetograms." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "Surya", "title": "Surya: Foundation Model for Heliophysics", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.14112", "doi": "", "url": "https://arxiv.org/abs/2508.14112", "code": [ "https://github.com/NASA-IMPACT/Surya" ], "links": { "Paper": "https://arxiv.org/abs/2508.14112", "Code": "https://github.com/NASA-IMPACT/Surya" }, "resources": [ "code" ], "modality": [], "summary": "366M-parameter spatiotemporal model trained on eight AIA channels and five HMI products at native resolution." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "", "title": "Solar Flare Forecasting with Foundational Transformer Models across Image, Video, and Time-series Modalities", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 10, "arxiv_id": "2510.23400", "doi": "", "url": "https://arxiv.org/abs/2510.23400", "code": [], "links": { "Paper": "https://arxiv.org/abs/2510.23400" }, "resources": [], "modality": [], "summary": "Compares SigLIP2, VideoMAE and Moirai2 on SDO/HMI magnetograms and GOES X-ray fluxes." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "JW-Flare", "title": "JW-Flare: Accurate Solar Flare Forecasting Method Based on Multimodal Large Language Models", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 11, "arxiv_id": "2511.08970", "doi": "", "url": "https://arxiv.org/abs/2511.08970", "code": [], "links": { "Paper": "https://arxiv.org/abs/2511.08970" }, "resources": [], "modality": [], "summary": "Multimodal LLM fine-tuned with LoRA on magnetograms and textual magnetic parameters for 24-hour flare forecasts." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "", "title": "Prediction of Major Solar Flares Using Interpretable Class-dependent Reward Framework with Active Region Magnetograms and Domain Knowledge", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 2, "arxiv_id": "2602.16264", "doi": "", "url": "https://arxiv.org/abs/2602.16264", "code": [], "links": { "Paper": "https://arxiv.org/abs/2602.16264" }, "resources": [], "modality": [], "summary": "CNN, CNN-BiLSTM and transformer models with class-dependent rewards for imbalanced M-class flare prediction." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "", "title": "Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.10016", "doi": "", "url": "https://arxiv.org/abs/2604.10016", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.10016" }, "resources": [], "modality": [], "summary": "ViT and LSTM hybrid that predicts whether upcoming flares will be eruptive or confined." }, { "section": "Solar Physics and Heliophysics", "subsection": "", "name": "FlareEUV", "title": "A Deep Learning Framework for Predicting Solar EUV Irradiance During Significant Flares", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.19597", "doi": "", "url": "https://arxiv.org/abs/2607.19597", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.19597" }, "resources": [], "modality": [], "summary": "Attention model on 13 co-aligned SDO AIA and HMI channels that forecasts daily 6.5 nm EVE irradiance over three days for 33 significant flares." }, { "section": "Radio Astronomy", "subsection": "", "name": "FETCH", "title": "FETCH: A Deep-learning Based Classifier for Fast Transient Classification", "venue": "MNRAS 2020", "publication_type": "Journal", "note": "", "year": 2019, "month": 2, "arxiv_id": "1902.06343", "doi": "", "url": "https://arxiv.org/abs/1902.06343", "code": [ "https://github.com/devanshkv/fetch" ], "links": { "Paper": "https://arxiv.org/abs/1902.06343", "Code": "https://github.com/devanshkv/fetch" }, "resources": [ "code" ], "modality": [], "summary": "CNN classifier for fast radio burst and single-pulse candidates." }, { "section": "Radio Astronomy", "subsection": "", "name": "ClaRAN", "title": "Radio Galaxy Zoo: ClaRAN, a Deep Learning Classifier for Radio Morphologies", "venue": "MNRAS 2019", "publication_type": "Journal", "note": "", "year": 2019, "month": null, "arxiv_id": "", "doi": "10.1093/mnras/sty2646", "url": "https://doi.org/10.1093/mnras/sty2646", "code": [ "https://github.com/chenwuperth/rgz_rcnn" ], "links": { "Journal": "https://doi.org/10.1093/mnras/sty2646", "Code": "https://github.com/chenwuperth/rgz_rcnn" }, "resources": [ "code" ], "modality": [], "summary": "Faster R-CNN detection and classification of radio source morphologies." }, { "section": "Radio Astronomy", "subsection": "", "name": "Pulsar SGAN", "title": "Pulsar Candidate Identification Using Semi-supervised Generative Adversarial Networks", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.07457", "doi": "10.1093/mnras/stab1308", "url": "https://arxiv.org/abs/2010.07457", "code": [ "https://github.com/vishnubk/sgan" ], "links": { "Paper": "https://arxiv.org/abs/2010.07457", "Code": "https://github.com/vishnubk/sgan", "Journal": "https://doi.org/10.1093/mnras/stab1308" }, "resources": [ "code" ], "modality": [], "summary": "Semi-supervised GAN classifier for pulsar candidates with few labelled examples." }, { "section": "Radio Astronomy", "subsection": "", "name": "Attention Gating", "title": "Attention-gating for Improved Radio Galaxy Classification", "venue": "MNRAS 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 12, "arxiv_id": "2012.01248", "doi": "", "url": "https://arxiv.org/abs/2012.01248", "code": [ "https://github.com/mb010/AstroAttention" ], "links": { "Paper": "https://arxiv.org/abs/2012.01248", "Code": "https://github.com/mb010/AstroAttention" }, "resources": [ "code" ], "modality": [], "summary": "Attention-gated CNNs for FRI and FRII radio galaxy classification." }, { "section": "Radio Astronomy", "subsection": "", "name": "POLISH", "title": "Deep Radio-interferometric Imaging with POLISH: DSA-2000 and Weak Lensing", "venue": "MNRAS 2022", "publication_type": "Journal", "note": "", "year": 2021, "month": 11, "arxiv_id": "2111.03249", "doi": "", "url": "https://arxiv.org/abs/2111.03249", "code": [ "https://github.com/liamconnor/polish-pub" ], "links": { "Paper": "https://arxiv.org/abs/2111.03249", "Code": "https://github.com/liamconnor/polish-pub" }, "resources": [ "code" ], "modality": [], "summary": "Super-resolution network for radio interferometric image reconstruction." }, { "section": "Radio Astronomy", "subsection": "", "name": "radionets", "title": "Deep Learning-based Imaging in Radio Interferometry", "venue": "A&A 2022", "publication_type": "Journal", "note": "", "year": 2022, "month": null, "arxiv_id": "", "doi": "10.1051/0004-6361/202142113", "url": "https://doi.org/10.1051/0004-6361/202142113", "code": [ "https://github.com/radionets-project/radionets" ], "links": { "Journal": "https://doi.org/10.1051/0004-6361/202142113", "Code": "https://github.com/radionets-project/radionets" }, "resources": [ "code" ], "modality": [], "summary": "Neural networks that reconstruct radio images from incomplete visibility data." }, { "section": "Radio Astronomy", "subsection": "", "name": "Radio Galaxy Zoo FM", "title": "Radio Galaxy Zoo: Towards Building the First Multipurpose Foundation Model for Radio Astronomy with Self-supervised Learning", "venue": "RASTI 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 5, "arxiv_id": "2305.16127", "doi": "10.1093/rasti/rzad055", "url": "https://arxiv.org/abs/2305.16127", "code": [ "https://github.com/inigoval/byol" ], "links": { "Paper": "https://arxiv.org/abs/2305.16127", "Journal": "https://doi.org/10.1093/rasti/rzad055", "Code": "https://github.com/inigoval/byol" }, "resources": [ "code" ], "modality": [], "summary": "BYOL pretraining on unlabelled radio galaxy images for downstream classification." }, { "section": "Radio Astronomy", "subsection": "", "name": "AIRI", "title": "The AIRI Plug-and-Play Algorithm for Image Reconstruction in Radio-Interferometry: Variations and Robustness", "venue": "MNRAS 2025", "publication_type": "Journal", "note": "", "year": 2023, "month": 12, "arxiv_id": "2312.07137", "doi": "10.1093/mnras/staf022", "url": "https://arxiv.org/abs/2312.07137", "code": [ "https://github.com/basp-group/AIRI" ], "links": { "Paper": "https://arxiv.org/abs/2312.07137", "Journal": "https://doi.org/10.1093/mnras/staf022", "Code": "https://github.com/basp-group/AIRI" }, "resources": [ "code" ], "modality": [], "summary": "Learned denoisers in proximal algorithms for radio-interferometric imaging with uncertainty quantification." }, { "section": "Radio Astronomy", "subsection": "", "name": "R2D2", "title": "The R2D2 Deep Neural Network Series Paradigm for Fast Precision Imaging in Radio Astronomy", "venue": "ApJS 2024", "publication_type": "Journal", "note": "", "year": 2024, "month": 3, "arxiv_id": "2403.05452", "doi": "10.3847/1538-4365/ad46f5", "url": "https://arxiv.org/abs/2403.05452", "code": [ "https://github.com/basp-group/R2D2-RI" ], "links": { "Paper": "https://arxiv.org/abs/2403.05452", "Code": "https://github.com/basp-group/R2D2-RI", "Journal": "https://doi.org/10.3847/1538-4365/ad46f5" }, "resources": [ "code" ], "modality": [], "summary": "Series of residual networks for radio interferometric imaging." }, { "section": "Radio Astronomy", "subsection": "", "name": "", "title": "Simulating Images of Radio Galaxies with Diffusion Models", "venue": "arXiv 2024", "publication_type": "Preprint", "note": "", "year": 2024, "month": 10, "arxiv_id": "2410.07794", "doi": "", "url": "https://arxiv.org/abs/2410.07794", "code": [], "links": { "Paper": "https://arxiv.org/abs/2410.07794" }, "resources": [], "modality": [], "summary": "Continuous-time diffusion model that generates radio galaxy images with control over flux and morphology." }, { "section": "Radio Astronomy", "subsection": "", "name": "", "title": "Classification of Radio Sources Through Self-Supervised Learning", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 3, "arxiv_id": "2503.19111", "doi": "", "url": "https://arxiv.org/abs/2503.19111", "code": [], "links": { "Paper": "https://arxiv.org/abs/2503.19111" }, "resources": [], "modality": [], "summary": "Self-supervised pretraining and deep clustering that classify LoTSS-DR2 radio galaxies into 12 morphology classes." }, { "section": "Radio Astronomy", "subsection": "", "name": "", "title": "Simulating Realistic Radio Continuum Survey Maps with Diffusion Models", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 6, "arxiv_id": "2506.11715", "doi": "", "url": "https://arxiv.org/abs/2506.11715", "code": [], "links": { "Paper": "https://arxiv.org/abs/2506.11715" }, "resources": [], "modality": [], "summary": "Diffusion-generated radio galaxies assembled into sky models and imaged to mimic LoTSS pointings." }, { "section": "Radio Astronomy", "subsection": "", "name": "YOLO-CIANNA", "title": "YOLO-CIANNA: Galaxy Detection with Deep Learning in Radio Data. II. Winning the SKA SDC2 Using a Generalized 3D-YOLO Network", "venue": "A&A 2026", "publication_type": "Journal", "note": "", "year": 2025, "month": 9, "arxiv_id": "2509.12082", "doi": "", "url": "https://arxiv.org/abs/2509.12082", "code": [], "links": { "Paper": "https://arxiv.org/abs/2509.12082" }, "resources": [], "modality": [], "summary": "3D CNN detector for HI sources in SKA SDC2 hyperspectral cubes, extending the method that won SDC2." }, { "section": "Radio Astronomy", "subsection": "", "name": "YOLO-Chars", "title": "Radio Galaxies Detection and Characterization Using Deep Learning Techniques", "venue": "MNRAS 2026", "publication_type": "Journal", "note": "", "year": 2026, "month": 8, "arxiv_id": "2608.21474", "doi": "", "url": "https://arxiv.org/abs/2608.21474", "code": [], "links": { "Paper": "https://arxiv.org/abs/2608.21474" }, "resources": [], "modality": [], "summary": "Two-stage YOLO detection and characterisation network for flux, size and position angle on SKA SDC1 images." }, { "section": "Radio Astronomy", "subsection": "", "name": "StarWhisper-Pulsar", "title": "Pulsar Candidate Classification with Multimodal Large Language Models", "venue": "NeurIPS 2024 Workshop (FM4Science)", "publication_type": "Workshop", "note": "", "year": 2024, "month": null, "arxiv_id": "", "doi": "", "url": "https://openreview.net/forum?id=8SKgWpZiDL", "code": [ "https://github.com/ACMISLab/StarWhisper-Pulsar" ], "links": { "Paper": "https://openreview.net/forum?id=8SKgWpZiDL", "Code": "https://github.com/ACMISLab/StarWhisper-Pulsar" }, "resources": [ "code" ], "modality": [], "summary": "Fine-tunes multimodal LLMs on diagnostic plots, text and numerical features to classify pulsar candidates, outperforming earlier machine learning classifiers after a few training epochs." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "DeepMoon", "title": "Lunar Crater Identification via Deep Learning", "venue": "Icarus 2019", "publication_type": "Journal", "note": "", "year": 2018, "month": 3, "arxiv_id": "1803.02192", "doi": "", "url": "https://arxiv.org/abs/1803.02192", "code": [ "https://github.com/silburt/DeepMoon" ], "links": { "Paper": "https://arxiv.org/abs/1803.02192", "Code": "https://github.com/silburt/DeepMoon", "Data": "https://doi.org/10.5281/zenodo.1133969" }, "resources": [ "code", "data" ], "modality": [], "summary": "CNN crater detection on lunar digital elevation maps, transferred to Mercury." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "AstroVision", "title": "AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep Learning", "venue": "Acta Astronaut. 2023", "publication_type": "Journal", "note": "", "year": 2022, "month": 8, "arxiv_id": "2208.02053", "doi": "10.1016/j.actaastro.2023.01.009", "url": "https://arxiv.org/abs/2208.02053", "code": [], "links": { "Paper": "https://arxiv.org/abs/2208.02053", "Data": "https://huggingface.co/datasets/travisdriver/astrovision-data", "Journal": "https://doi.org/10.1016/j.actaastro.2023.01.009" }, "resources": [ "data" ], "modality": [], "summary": "115,970 annotated real images of 16 small bodies for keypoint detection and description benchmarks." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "", "title": "A Flexible Deep Learning Crater Detection Scheme Using Segment Anything Model (SAM)", "venue": "Icarus 2024", "publication_type": "Journal", "note": "", "year": 2023, "month": 4, "arxiv_id": "2304.07764", "doi": "10.1016/j.icarus.2023.115797", "url": "https://arxiv.org/abs/2304.07764", "code": [], "links": { "Paper": "https://arxiv.org/abs/2304.07764", "Journal": "https://doi.org/10.1016/j.icarus.2023.115797" }, "resources": [], "modality": [], "summary": "Zero-shot crater segmentation with SAM on lunar and Martian images and DEMs." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "Lunar Twins", "title": "Lunar Twins: We Choose to Go to the Moon with Large Language Models", "venue": "ACL Findings 2025", "publication_type": "Conference", "note": "", "year": 2025, "month": null, "arxiv_id": "", "doi": "", "url": "https://aclanthology.org/2025.findings-acl.69/", "code": [], "links": { "Paper": "https://aclanthology.org/2025.findings-acl.69/" }, "resources": [], "modality": [], "summary": "Earth-Moon collaborative Chang'e large model with Yutu-Text and Yutu-VL small models, the Lunar_GenData multi-agent instruction workflow built on Chang'e mission data, and the Lunar_Eval suite." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "", "title": "Deep Learning Framework for Crater Detection and Identification on the Moon and Mars", "venue": "arXiv 2025", "publication_type": "Preprint", "note": "", "year": 2025, "month": 8, "arxiv_id": "2508.03920", "doi": "", "url": "https://arxiv.org/abs/2508.03920", "code": [ "https://github.com/sydney-machine-learning/crater-identification" ], "links": { "Paper": "https://arxiv.org/abs/2508.03920", "Code": "https://github.com/sydney-machine-learning/crater-identification" }, "resources": [ "code" ], "modality": [], "summary": "Two-stage YOLO detection and CNN or ResNet-50 size classification of craters with an annotated dataset." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "", "title": "Vision-Language Model for Accurate Crater Detection", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 1, "arxiv_id": "2601.07795", "doi": "", "url": "https://arxiv.org/abs/2601.07795", "code": [], "links": { "Paper": "https://arxiv.org/abs/2601.07795" }, "resources": [], "modality": [], "summary": "OWLv2 vision transformer fine-tuned on LRO images for lunar crater detection." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "LLaVA-LE", "title": "LLaVA-LE: Large Language-and-Vision Assistant for Lunar Exploration", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.24696", "doi": "", "url": "https://arxiv.org/abs/2603.24696", "code": [], "links": { "Paper": "https://arxiv.org/abs/2603.24696" }, "resources": [], "modality": [], "summary": "LLaVA adapted to lunar remote sensing with LUCID, 96k panchromatic images paired with scientific captions and question-answer pairs." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "", "title": "Deep Learning-Based Lunar Crater Terrain Relative Navigation", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 6, "arxiv_id": "2606.14776", "doi": "", "url": "https://arxiv.org/abs/2606.14776", "code": [], "links": { "Paper": "https://arxiv.org/abs/2606.14776" }, "resources": [], "modality": [], "summary": "U-Net++ crater detector coupled with an extended Kalman filter for lunar landing navigation." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "Lunar-Bench", "title": "Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios", "venue": "ACL Findings 2026", "publication_type": "Conference", "note": "", "year": 2026, "month": null, "arxiv_id": "", "doi": "", "url": "https://aclanthology.org/2026.findings-acl.83/", "code": [], "links": { "Paper": "https://aclanthology.org/2026.findings-acl.83/" }, "resources": [], "modality": [], "summary": "3,000 tasks derived from lunar mission procedures with Environmental Scenario Indicators for safety, efficiency, integrity and alignment; the best of 36 models reaches 47.8% against 65.1% for human experts." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "Lunar-R1", "title": "Lunar-R1: Efficient Reasoning of Large Language Models for Lunar Exploration via Reinforcement Learning", "venue": "EMNLP 2026 Industry", "publication_type": "Conference", "note": "", "year": 2026, "month": null, "arxiv_id": "", "doi": "", "url": "https://aclanthology.org/2026.emnlp-industry.5/", "code": [], "links": { "Paper": "https://aclanthology.org/2026.emnlp-industry.5/" }, "resources": [], "modality": [], "summary": "8B reasoning model trained by continued pretraining, SFT and RL, with Latent Difficulty Perception that cuts chain-of-thought tokens by 38.9%, the Lunar-QA benchmark and RK3588 NPU deployment." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "LunarFM", "title": "LunarFM: A Shared Multimodal Representation of the Moon's Surface", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 7, "arxiv_id": "2607.22408", "doi": "", "url": "https://arxiv.org/abs/2607.22408", "code": [], "links": { "Paper": "https://arxiv.org/abs/2607.22408" }, "resources": [], "modality": [], "summary": "Foundation model mapping 18 channels from six instruments on three lunar missions into one embedding for similarity search, resource mapping, mineral regression and geology classification." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "", "title": "Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 9, "arxiv_id": "2609.13283", "doi": "", "url": "https://arxiv.org/abs/2609.13283", "code": [], "links": { "Paper": "https://arxiv.org/abs/2609.13283" }, "resources": [], "modality": [], "summary": "TerraMind-style model pretrained on nearly two million co-registered tile bundles over 11 modalities at 1 m and 100 m scales, evaluated on craters, irregular mare patches and ice prospectivity." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "VAD4Space", "title": "VAD4Space: Visual Anomaly Detection for Planetary Surface Imagery", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 3, "arxiv_id": "2603.13993", "doi": "", "url": "https://arxiv.org/abs/2603.13993", "code": [], "links": { "Paper": "https://arxiv.org/abs/2603.13993" }, "resources": [], "modality": [], "summary": "Benchmarks unsupervised visual anomaly detection methods on lunar and Mars rover imagery, with PaDiM localising craters without labels." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "MOMO", "title": "MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications", "venue": "arXiv 2026", "publication_type": "Preprint", "note": "", "year": 2026, "month": 4, "arxiv_id": "2604.02719", "doi": "", "url": "https://arxiv.org/abs/2604.02719", "code": [], "links": { "Paper": "https://arxiv.org/abs/2604.02719" }, "resources": [], "modality": [], "summary": "Multi-sensor foundation model for Mars that combines representations from several orbital instruments for downstream remote sensing tasks." }, { "section": "Planetary Science and Small Bodies", "subsection": "", "name": "ThermoONet", "title": "Deep Learning-enabled Size Estimation of Comets Indicates a More Dynamic Early Solar System", "venue": "Nat. Commun. 2026", "publication_type": "Journal", "note": "", "year": 2026, "month": null, "arxiv_id": "", "doi": "10.1038/s41467-026-72646-8", "url": "https://doi.org/10.1038/s41467-026-72646-8", "code": [ "https://github.com/zsjnb7/ThermoONet-Comet" ], "links": { "Journal": "https://doi.org/10.1038/s41467-026-72646-8", "Code": "https://github.com/zsjnb7/ThermoONet-Comet" }, "resources": [ "code" ], "modality": [], "summary": "DeepONet thermophysical model of water sublimation, fitted with simulated annealing to the water production curves of 28 comets to estimate nucleus sizes." }, { "section": "Datasets", "subsection": "Observational Datasets", "name": "PLAsTiCC", "title": "The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Data Set", "venue": "arXiv 2018", "publication_type": "Preprint", "note": "", "year": 2018, "month": 10, "arxiv_id": "1810.00001", "doi": "", "url": "https://arxiv.org/abs/1810.00001", "code": [], "links": { "Paper": "https://arxiv.org/abs/1810.00001", "Kaggle": "https://www.kaggle.com/c/PLAsTiCC-2018" }, "resources": [ "data" ], "modality": [], "summary": "Simulated LSST multi-band light curves for transient and variable classification." }, { "section": "Datasets", "subsection": "Observational Datasets", "name": "Multimodal Universe", "title": "The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data", "venue": "NeurIPS 2024 (Datasets and Benchmarks)", "publication_type": "Conference", "note": "", "year": 2024, "month": 12, "arxiv_id": "2412.02527", "doi": "", "url": "https://arxiv.org/abs/2412.02527", "code": [ "https://github.com/MultimodalUniverse/MultimodalUniverse" ], "links": { "Paper": "https://arxiv.org/abs/2412.02527", "Code": "https://github.com/MultimodalUniverse/MultimodalUniverse" }, "resources": [ "code" ], "modality": [], "summary": "Images, spectra, time series and catalogs for hundreds of millions of objects, distributed as Hugging Face datasets with benchmark tasks." }, { "section": "Datasets", "subsection": "Simulation Datasets", "name": "Quijote", "title": "The Quijote Simulations", "venue": "ApJS 2020", "publication_type": "Journal", "note": "", "year": 2019, "month": 9, "arxiv_id": "1909.05273", "doi": "10.3847/1538-4365/ab9d82", "url": "https://arxiv.org/abs/1909.05273", "code": [], "links": { "Paper": "https://arxiv.org/abs/1909.05273", "Journal": "https://doi.org/10.3847/1538-4365/ab9d82" }, "resources": [], "modality": [], "summary": "44,100 N-body simulations spanning more than 7,000 cosmological models, designed for information quantification and ML training." }, { "section": "Datasets", "subsection": "Simulation Datasets", "name": "CAMELS", "title": "The CAMELS Project: Cosmology and Astrophysics with MachinE Learning Simulations", "venue": "ApJ 2021", "publication_type": "Journal", "note": "", "year": 2020, "month": 10, "arxiv_id": "2010.00619", "doi": "", "url": "https://arxiv.org/abs/2010.00619", "code": [ "https://github.com/franciscovillaescusa/CAMELS" ], "links": { "Paper": "https://arxiv.org/abs/2010.00619", "Code": "https://github.com/franciscovillaescusa/CAMELS", "Project": "https://www.camel-simulations.org" }, "resources": [ "code" ], "modality": [], "summary": "4,233 cosmological simulations varying cosmological and feedback parameters, designed for training ML models." }, { "section": "Datasets", "subsection": "Simulation Datasets", "name": "The Well", "title": "The Well: A Large-Scale Collection of Diverse Physics Simulations for Machine Learning", "venue": "NeurIPS 2024 (Datasets and Benchmarks)", "publication_type": "Conference", "note": "", "year": 2024, "month": 12, "arxiv_id": "2412.00568", "doi": "", "url": "https://arxiv.org/abs/2412.00568", "code": [ "https://github.com/PolymathicAI/the_well" ], "links": { "Paper": "https://arxiv.org/abs/2412.00568", "Code": "https://github.com/PolymathicAI/the_well" }, "resources": [ "code" ], "modality": [], "summary": "15 TB across 16 physics simulation datasets, including MHD and supernova explosion simulations." } ], "links": [ { "section": "Tools and Libraries", "name": "AspGap", "url": "https://github.com/jiadonglee/aspgap", "description": "infers red giant stellar parameters and abundances from Gaia XP spectra." }, { "section": "Tools and Libraries", "name": "astroML", "url": "https://github.com/astroML/astroML", "description": "provides machine learning and statistics routines for astronomy." }, { "section": "Tools and Libraries", "name": "astrorapid", "url": "https://github.com/daniel-muthukrishna/astrorapid", "description": "classifies transients in real time with recurrent neural networks." }, { "section": "Tools and Libraries", "name": "avocado", "url": "https://github.com/kboone/avocado", "description": "classifies photometric transients with Gaussian process augmentation and boosted trees." }, { "section": "Tools and Libraries", "name": "BLISS", "url": "https://github.com/prob-ml/bliss", "description": "performs Bayesian light source separation with amortized variational inference." }, { "section": "Tools and Libraries", "name": "ctlearn", "url": "https://github.com/ctlearn-project/ctlearn", "description": "trains deep learning models for imaging atmospheric Cherenkov telescope event reconstruction." }, { "section": "Tools and Libraries", "name": "D3M", "url": "https://github.com/siyucosmo/ML-Recon", "description": "emulates N-body displacement fields with deep learning." }, { "section": "Tools and Libraries", "name": "DASH", "url": "https://github.com/daniel-muthukrishna/astrodash", "description": "classifies supernova spectra with deep learning." }, { "section": "Tools and Libraries", "name": "Deep-HiTS", "url": "https://github.com/guille-c/Deep-HiTS", "description": "classifies HiTS transient candidates with convolutional neural networks." }, { "section": "Tools and Libraries", "name": "deep-potential", "url": "https://github.com/gregreen/deep-potential", "description": "recovers gravitational potentials from phase-space snapshots with normalizing flows." }, { "section": "Tools and Libraries", "name": "DeepBench", "url": "https://github.com/deepskies/DeepBench", "description": "generates simple physics and astronomy benchmark datasets for machine learning." }, { "section": "Tools and Libraries", "name": "DeepDISC", "url": "https://github.com/grantmerz/deepdisc", "description": "applies Detectron2 instance segmentation to astronomical source detection." }, { "section": "Tools and Libraries", "name": "DeepMerge", "url": "https://github.com/deepskies/deepmerge-public", "description": "classifies high-redshift merging galaxies with CNNs." }, { "section": "Tools and Libraries", "name": "DeepSource", "url": "https://github.com/vafaei-ar/deepsource", "description": "detects point sources in radio images with deep learning." }, { "section": "Tools and Libraries", "name": "E2CNNRadGal", "url": "https://github.com/as595/E2CNNRadGal", "description": "classifies radio galaxies with group-equivariant CNNs." }, { "section": "Tools and Libraries", "name": "Fink", "url": "https://github.com/astrolabsoftware/fink-broker", "description": "is an LSST alert broker with machine learning classification modules." }, { "section": "Tools and Libraries", "name": "fink-science", "url": "https://github.com/astrolabsoftware/fink-science", "description": "hosts the science modules and classifiers run on the Fink alert stream." }, { "section": "Tools and Libraries", "name": "FLEET", "url": "https://github.com/gmzsebastian/FLEET", "description": "selects superluminous supernova and tidal disruption event candidates for follow-up." }, { "section": "Tools and Libraries", "name": "FlexCode", "url": "https://github.com/tpospisi/FlexCode", "description": "estimates conditional densities for photometric redshifts." }, { "section": "Tools and Libraries", "name": "Galaxy Zoo Bayesian CNN", "url": "https://github.com/mwalmsley/galaxy-zoo-bayesian-cnn", "description": "trains Bayesian CNNs with active learning on Galaxy Zoo labels." }, { "section": "Tools and Libraries", "name": "galaxy-datasets", "url": "https://github.com/mwalmsley/galaxy-datasets", "description": "loads Galaxy Zoo datasets for PyTorch training." }, { "section": "Tools and Libraries", "name": "Galaxy10 DECaLS", "url": "https://github.com/henrysky/Galaxy10", "description": "provides 17,736 DECaLS g, r, z galaxy images in 10 morphology classes with Galaxy Zoo labels (Zenodo)." }, { "section": "Tools and Libraries", "name": "GalaxyGAN", "url": "https://github.com/SpaceML/GalaxyGAN_python", "description": "recovers features from degraded galaxy images with GANs." }, { "section": "Tools and Libraries", "name": "GPz", "url": "https://github.com/OxfordML/GPz", "description": "estimates photometric redshifts with sparse Gaussian processes." }, { "section": "Tools and Libraries", "name": "Gravity Spy", "url": "https://github.com/Gravity-Spy/GravitySpy", "description": "classifies LIGO detector glitches with citizen science and machine learning." }, { "section": "Tools and Libraries", "name": "herculens", "url": "https://github.com/Herculens/herculens", "description": "performs differentiable strong lens modeling in JAX." }, { "section": "Tools and Libraries", "name": "InstrumentToInstrument", "url": "https://github.com/RobertJaro/InstrumentToInstrument", "description": "translates solar observations between instruments." }, { "section": "Tools and Libraries", "name": "IrregularTimeSeriesAutoencoder", "url": "https://github.com/bnaul/IrregularTimeSeriesAutoencoderPaper", "description": "learns recurrent autoencoder features from irregularly sampled light curves." }, { "section": "Tools and Libraries", "name": "jax-cosmo", "url": "https://github.com/DifferentiableUniverseInitiative/jax_cosmo", "description": "provides differentiable cosmology computations in JAX." }, { "section": "Tools and Libraries", "name": "jax-lensing", "url": "https://github.com/CosmoStat/jax-lensing", "description": "implements probabilistic mass mapping with neural score estimation (paper)." }, { "section": "Tools and Libraries", "name": "JaxPM", "url": "https://github.com/DifferentiableUniverseInitiative/JaxPM", "description": "implements a differentiable particle-mesh N-body solver in JAX." }, { "section": "Tools and Libraries", "name": "jim", "url": "https://github.com/kazewong/jim", "description": "performs gravitational-wave parameter estimation in JAX with flow-enhanced sampling." }, { "section": "Tools and Libraries", "name": "lampe", "url": "https://github.com/probabilists/lampe", "description": "implements neural ratio and posterior estimation for likelihood-free inference in PyTorch." }, { "section": "Tools and Libraries", "name": "lc_classifier", "url": "https://github.com/alercebroker/lc_classifier", "description": "classifies light curves in the ALeRCE broker." }, { "section": "Tools and Libraries", "name": "LIA", "url": "https://github.com/dgodinez77/LIA", "description": "classifies microlensing events with random forests." }, { "section": "Tools and Libraries", "name": "light-curve", "url": "https://github.com/light-curve/light-curve-python", "description": "extracts light-curve features for transient and variable classification." }, { "section": "Tools and Libraries", "name": "magnify", "url": "https://github.com/jiwoncpark/magnify", "description": "models AGN light curves with Gaussian process and neural network tools." }, { "section": "Tools and Libraries", "name": "map2map", "url": "https://github.com/eelregit/map2map", "description": "trains field-to-field neural networks on cosmological simulations." }, { "section": "Tools and Libraries", "name": "MCCD", "url": "https://github.com/CosmoStat/mccd", "description": "models the PSF across multiple CCDs with data-driven methods." }, { "section": "Tools and Libraries", "name": "ml4gw", "url": "https://github.com/ML4GW/ml4gw", "description": "provides PyTorch utilities for gravitational-wave machine learning." }, { "section": "Tools and Libraries", "name": "ML_GBT_SETI", "url": "https://github.com/PetchMa/ML_GBT_SETI", "description": "searches Green Bank Telescope data for technosignatures with machine learning." }, { "section": "Tools and Libraries", "name": "MLZ", "url": "https://github.com/mgckind/MLZ", "description": "estimates photometric redshifts with TPZ random forests." }, { "section": "Tools and Libraries", "name": "Morpheus", "url": "https://github.com/morpheus-project/morpheus", "description": "performs pixel-level morphological classification of astronomical images." }, { "section": "Tools and Libraries", "name": "MuyGPyS", "url": "https://github.com/LLNL/MuyGPyS", "description": "provides scalable Gaussian process estimation used for star-galaxy separation." }, { "section": "Tools and Libraries", "name": "ParSNIP", "url": "https://github.com/kboone/parsnip", "description": "builds generative models of transient light curves with physics-enabled deep learning." }, { "section": "Tools and Libraries", "name": "PICS", "url": "https://github.com/zhuww/ubc_AI", "description": "classifies pulsar candidates with image pattern recognition." }, { "section": "Tools and Libraries", "name": "pmwd", "url": "https://github.com/eelregit/pmwd", "description": "implements differentiable particle-mesh N-body simulation in JAX." }, { "section": "Tools and Libraries", "name": "PySR", "url": "https://github.com/MilesCranmer/PySR", "description": "performs symbolic regression for interpretable scientific models (paper)." }, { "section": "Tools and Libraries", "name": "QuasarNET", "url": "https://github.com/ngbusca/QuasarNET", "description": "classifies quasar spectra and estimates redshifts with a convolutional network." }, { "section": "Tools and Libraries", "name": "ramjet", "url": "https://github.com/golmschenk/ramjet", "description": "detects transits and microlensing events in light curves with neural networks." }, { "section": "Tools and Libraries", "name": "RESSPECT", "url": "https://github.com/COINtoolbox/RESSPECT", "description": "applies active learning to supernova spectroscopic follow-up." }, { "section": "Tools and Libraries", "name": "sbi", "url": "https://github.com/sbi-dev/sbi", "description": "implements neural posterior, likelihood and ratio estimation (JOSS)." }, { "section": "Tools and Libraries", "name": "ShapeDeconv", "url": "https://github.com/CosmoStat/ShapeDeconv", "description": "deconvolves galaxy images with deep learning for shape measurement." }, { "section": "Tools and Libraries", "name": "SimBIG", "url": "https://github.com/changhoonhahn/simbig", "description": "performs simulation-based inference of galaxy clustering." }, { "section": "Tools and Libraries", "name": "single_pulse_ml", "url": "https://github.com/liamconnor/single_pulse_ml", "description": "classifies single-pulse and fast radio burst candidates with deep learning." }, { "section": "Tools and Libraries", "name": "star-galaxy CNN", "url": "https://github.com/EdwardJKim/dl4astro", "description": "separates stars and galaxies with CNNs." }, { "section": "Tools and Libraries", "name": "StarNet", "url": "https://github.com/astroai/starnet", "description": "infers stellar parameters from spectra with CNNs." }, { "section": "Tools and Libraries", "name": "StarWhisper", "url": "https://github.com/Yu-Yang-Li/StarWhisper", "description": "collects code, data and model weights for astronomy language models, light-curve and spectral classification and autonomous telescope observing, with research skills for AI coding agents." }, { "section": "Tools and Libraries", "name": "sunbird", "url": "https://github.com/florpi/sunbird", "description": "emulates galaxy clustering summary statistics with neural networks." }, { "section": "Tools and Libraries", "name": "Superphot", "url": "https://github.com/griffin-h/superphot", "description": "classifies supernovae from photometric light curves." }, { "section": "Tools and Libraries", "name": "Superphot+", "url": "https://github.com/VTDA-Group/superphot-plus", "description": "fits and classifies supernova light curves." }, { "section": "Tools and Libraries", "name": "SuperRAENN", "url": "https://github.com/villrv/SuperRAENN", "description": "classifies supernova light curves with recurrent autoencoder features." }, { "section": "Tools and Libraries", "name": "The Cannon", "url": "https://github.com/andycasey/AnniesLasso", "description": "provides a data-driven model for stellar labels from spectra." }, { "section": "Tools and Libraries", "name": "The Payne", "url": "https://github.com/tingyuansen/The_Payne", "description": "fits stellar spectra with neural network spectral emulators." }, { "section": "Tools and Libraries", "name": "transomaly", "url": "https://github.com/daniel-muthukrishna/transomaly", "description": "detects anomalous transients in real time." }, { "section": "Tools and Libraries", "name": "xVal", "url": "https://github.com/PolymathicAI/xVal", "description": "encodes real numbers as continuous embeddings for language models on scientific data." }, { "section": "Communities and Groups", "name": "Polymathic AI", "url": "https://polymathic-ai.org", "description": "develops AstroCLIP, AION-1, MPP, the Multimodal Universe and The Well." }, { "section": "Communities and Groups", "name": "UniverseTBD", "url": "https://universetbd.org", "description": "develops AstroLLaMA, AstroPT and AstroLLaVA." }, { "section": "Communities and Groups", "name": "AstroMLab", "url": "https://huggingface.co/AstroMLab", "description": "develops the AstroMLab benchmark and the AstroSage models." }, { "section": "Communities and Groups", "name": "ML4GW", "url": "https://github.com/ML4GW", "description": "develops machine learning pipelines for gravitational-wave astronomy." }, { "section": "Related Awesome Lists", "name": "awesome-astronomy", "url": "https://github.com/jonathansick/awesome-astronomy", "description": "covers general resources for professional astronomers." }, { "section": "Related Awesome Lists", "name": "awesome-astro-datascience", "url": "https://github.com/mpi-astronomy/awesome-astro-datascience", "description": "covers astronomical data science resources." }, { "section": "Related Awesome Lists", "name": "awesome-astrodata", "url": "https://github.com/gully/awesome-astrodata", "description": "covers data and tools for machine learning in astronomy." }, { "section": "Related Awesome Lists", "name": "taotie", "url": "https://github.com/dr-guangtou/taotie", "description": "covers resources for astrophysical research." }, { "section": "Related Awesome Lists", "name": "awesome-space", "url": "https://github.com/orbitalindex/awesome-space", "description": "covers space-related packages and resources." }, { "section": "Related Awesome Lists", "name": "Awesome-Scientific-Language-Models", "url": "https://github.com/yuzhimanhua/Awesome-Scientific-Language-Models", "description": "covers scientific language models across domains." } ] }