IA2 · RESEARCH

Research catalogue

AI and advanced inference across astrophysics. Papers from 2024 onward, including preprints, with an IA2 member among the first three listed authors.

66 papers · Checked 2026-09-24 · Updated every two weeks

66 matching papers

  1. 2026 · arXiv record

    Semiresolved Stellar Populations as Distance Indicators

    Ignacio Martín-Navarro, Patricia Iglesias Navarro, Francesco La Barbera et al.

    Neural posterior estimation turns partially resolved stellar populations into distance measurements.

    Simulation-based inference
  2. 2026 · arXiv record

    Beyond traditional emission-line diagnostics: using autoencoders to uncover active galactic nuclei in DESI spectra

    J. A. Alcolea, M. Siudek, M. Eriksen et al.

    An autoencoder searches DESI spectra for active galactic nuclei beyond conventional emission-line diagnostics.

    Neural networks
  3. 2026 · arXiv record

    First detection of ultra-fast outflows in a quiescent galaxy

    Yerong Xu, Malgorzata Siudek, Victor Rodríguez Morales et al.

    Bayesian spectral modelling with neural-assisted nested sampling tests evidence for an ultra-fast outflow in a quiescent galaxy.

    Bayesian inference
  4. 2026 · arXiv record

    A Pixel-by-Pixel Path to Population III Discovery with JWST

    Patricia Iglesias-Navarro, Thomas Harvey, Marc Huertas-Company et al.

    Pixel-level inference searches JWST images for signatures of Population III stars.

    Simulation-based inference
  5. 2026 · arXiv record

    3DSTokesFlow: simulation-based inference for 3D Stokes profiles using flow matching

    A. Asensio Ramos, K. E. Yang, M. J. Martinez Gonzalez et al.

    Flow matching estimates atmospheric parameters from three-dimensional Stokes profiles.

    Simulation-based inferenceGenerative models
  6. 2026 · arXiv record

    Marginal multi-object multi-frame blind deconvolution

    A. Asensio Ramos

    Marginalizing over nuisance parameters improves multi-object, multi-frame restoration of astronomical images.

    Bayesian inference
  7. 2026 · A&A 710, A256 (2026)

    Accelerating 3D Non-LTE Synthesis with Graph Neural Networks

    A. Vicente Arévalo, A. Asensio Ramos, C. J. Díaz Baso

    Graph neural networks accelerate three-dimensional non-LTE spectral synthesis.

    Neural networks
  8. 2026 · arXiv record

    IRIS NUV diagnostics for Ellerman bombs: spectral properties, thermodynamics, and formation height

    I. J. Soler Poquet, C. J. Díaz Baso, A. Sainz Dalda et al.

    IRIS²⁺ spectral inversions recover atmospheric stratification and formation heights for Ellerman bombs.

    Spectral inference
  9. 2026 · arXiv record

    A comparison of pendulum models for large-amplitude longitudinal prominence oscillations

    Iñigo Arregui

    Bayesian parameter inference and model comparison quantify prominence magnetic fields under competing pendulum models.

    Bayesian inference
  10. 2026 · arXiv record

    Inspectorch: Efficient rare event exploration in solar observations

    C. J. Díaz Baso, I. J. Soler Poquet, C. Kuckein et al.

    Flow-based density estimation identifies rare solar events through probabilistic anomaly scores.

    Machine learningGenerative models
  11. 2026 · arXiv record

    Signatures of Damping Nonlinear Oscillations by KHI-induced Turbulence in Synthetic Observations

    Sihui Zhong, Andrew Hillier, Iñigo Arregui

    Bayesian fits to synthetic loop oscillations constrain amplitudes and periods while exposing degeneracies in damping parameters.

    Bayesian inference
  12. 2026 · arXiv record

    Talking with the Latents -- how to convert your LLM into an astronomer

    Ilay Kamai, Marc-Huertas Company, Mike J. Smith et al.

    A latent representation connects astronomical data to a language model for interpreting galaxy properties.

    Foundation models
  13. 2026 · arXiv record

    Inferring physical parameters of solar filaments from simultaneous longitudinal and transverse oscillations

    Upasna Baweja, Vaibhav Pant, Iñigo Arregui et al.

    Bayesian seismology combines longitudinal and transverse filament oscillations to infer magnetic fields, flux-tube lengths and twists.

    Bayesian inference
  14. 2026 · Astronomy & Astrophysics, 710, A329 (2026)

    Cored galaxies in cuspy dark matter halos

    Fernando Valenciano, Jorge Martin Camalich, Arianna Di Cintio et al.

    Likelihood-based fits and model comparison test whether cuspy dark matter halos can reproduce apparently cored galaxies.

    Statistical inference
  15. 2026 · 2026 ApJ, Volume 1002, Number 1

    ELG×LRG distribution through dark matter halo dynamics

    Ginevra Favole, Francisco-Shu Kitaura, Boryana Hadzhiyska et al.

    A two-level Bayesian framework connects emission-line and luminous red galaxies to dark matter halo dynamics.

    Bayesian inference
  16. 2026 · A&A 706, A100 (2026)

    Silicate emission in a type-2 quasar: JWST/MIRI constraints on torus geometry and radiative feedback

    C. Ramos Almeida, A. Asensio Ramos, C. Westerdorp Plaza et al.

    Bayesian torus modelling uses JWST silicate emission to constrain the geometry of an obscured quasar.

    Bayesian inference
  17. 2026 · A&A 707, A164 (2026)

    Thermodynamic and magnetic evolution of an eruptive C-class solar flare observed with SST/TRIPPEL-SP

    C. J. Díaz Baso, J. de la Cruz Rodríguez, H. -P. Doerr et al.

    Non-LTE spectropolarimetric inversions reconstruct the atmospheric evolution of an eruptive C-class solar flare.

    Spectral inference
  18. 2026 · A&A 709, A110 (2026)

    Differentiable Fuzzy Cosmic-Web for Field Level Inference

    P. Rosselló, F. -S. Kitaura, D. Forero-Sánchez et al.

    A differentiable cosmic-web description supports gradient-based inference of large-scale structure.

    Field-level inference
  19. 2025 · arXiv record

    Stellar-like Galactic center excess challenges particle dark matter

    Silvia Manconi, Christopher Eckner, Francesca Calore et al.

    Adaptive template fitting and MultiNest posterior sampling constrain dark matter contributions to the Galactic center excess.

    Bayesian inference
  20. 2025 · A&A 703, A290 (2025)

    The spatially-resolved effect of mergers on the stellar mass assembly of MaNGA galaxies

    Eirini Angeloudi, Marc Huertas-Company, Jesús Falcón-Barroso et al.

    Diffusion-based inference maps how mergers contribute to the spatial distribution of stellar mass in MaNGA galaxies.

    Generative modelsSimulation-based inference
  21. 2025 · arXiv record

    Probing the Parameter Space of Axion-Like Particles Using Simulation-Based Inference

    Pooja Bhattacharjee, Christopher Eckner, Gabrijela Zaharijas et al.

    Truncated marginal neural ratio estimation constrains axion-like particle parameters from simulated CTAO spectra.

    Simulation-based inferenceNeural networks
  22. 2025 · arXiv record

    Identification of Nonlinear Damping of Transverse Loop Oscillations by KHI-induced Turbulence

    Sihui Zhong, Andrew Hillier, Iñigo Arregui

    MCMC fitting and Bayesian model comparison test nonlinear turbulence damping against linear models of coronal-loop oscillations.

    Bayesian inference
  23. 2025 · A&A 703, A55 (2025)

    Neural translation for Stokes inversion and synthesis

    A. Asensio Ramos, J. de la Cruz Rodriguez

    A neural translation model connects Stokes spectra and atmospheric structure for both inversion and synthesis.

    Neural networksGenerative models
  24. 2025 · A&A 700, A209 (2025)

    Beyond Traditional Diagnostics: Identifying Active Galactic Nuclei with Spectral Energy Distribution Fitting in DESI Data

    M. Siudek, M. Mezcua, C. Circosta et al.

    CIGALE spectral energy distribution modelling identifies AGN in DESI data and compares them with traditional selections.

    Spectral inference
  25. 2025 · A&A 703, A229 (2025)

    Simulation-based inference of galaxy properties from JWST pixels

    Patricia Iglesias-Navarro, Marc Huertas-Company, Pablo Pérez-González et al.

    Neural inference estimates resolved galaxy properties directly from JWST pixels.

    Simulation-based inference
  26. 2025 · A&A 699, A121 (2025)

    Chromospheric velocities in an M3.2 flare using He I 1083.0 nm and Ca II 854.2 nm

    C. Kuckein, M. Collados, A. Asensio Ramos et al.

    Inversions of helium and calcium spectra recover chromospheric velocities during a solar flare.

    Spectral inference
  27. 2025 · A&A 703, A269 (2025)

    torchmfbd: a flexible multi-object multi-frame blind deconvolution code

    A. Asensio Ramos, C. Díaz Baso, C. Kuckein et al.

    A flexible image-restoration framework estimates objects and atmospheric aberrations through maximum-a-posteriori optimization.

    Bayesian inference
  28. 2025 · A&A 699, A54 (2025)

    Automatic detection of Ellerman bombs using Deep Learning

    I. J. Soler Poquet, C. J. Díaz Baso, L. H. M. Rouppe van der Voort et al.

    Neural networks detect Ellerman bombs in solar observations and assess the spectral and spatial information needed.

    Machine learningNeural networks
  29. 2025 · arXiv record

    A robust neural determination of the source-count distribution of the Fermi-LAT sky at high latitudes

    Christopher Eckner, Noemi Anau Montel, Florian List et al.

    Neural ratio estimation detects gamma-ray sources and reconstructs source-count distributions from Fermi-LAT data.

    Simulation-based inferenceNeural networks
  30. 2025 · arXiv record

    Euclid Quick Data Release (Q1) Exploring galaxy properties with a multi-modal foundation model

    Euclid Collaboration, M. Siudek, M. Huertas-Company et al.

    A multimodal foundation model extracts physical information from Euclid galaxy observations.

    Foundation models
  31. 2025 · arXiv record

    Euclid Quick Data Release (Q1), A first look at the fraction of bars in massive galaxies at z<1

    Euclid Collaboration, M. Huertas-Company, M. Walmsley et al.

    Deep-learning morphology measurements characterize the fraction of barred galaxies in Euclid Q1.

    Machine learning
  32. 2025 · arXiv record

    Euclid Quick Data Release (Q1): First visual morphology catalogue

    Euclid Collaboration, M. Walmsley, M. Huertas-Company et al.

    A deep-learning pipeline produces the first visual morphology catalogue for Euclid Q1.

    Machine learning
  33. 2025 · A&A 703, A140 (2025)

    Galaxy mass profiles with convolutional neural networks

    Jorge Sarrato-Alós, Christopher Brook, Arianna Di Cintio et al.

    Convolutional networks recover galaxy mass profiles and quantify uncertainty from simulated observations.

    Neural networks
  34. 2025 · A&A 699, A330 (2025)

    MaNGA AGN dwarf galaxies (MAD). III. The role of mergers and environment in active galactic nucleus activity in dwarf galaxies

    A. Eróstegui, M. Mezcua, M. Siudek et al.

    CIGALE fits correct stellar masses and pair mass ratios when testing mergers as triggers of dwarf-galaxy AGN.

    Spectral inference
  35. 2025 · arXiv record

    Study of an active region prominence using spectropolarimetric data in the He I D3 multiplet

    S. Esteban Pozuelo, A. Asensio Ramos, J. Trujillo Bueno et al.

    Helium-line spectropolarimetric inversions probe the magnetic structure of an active-region prominence.

    Spectral inference
  36. 2025 · The Astrophysical Journal, 986(2), 133 (June 2025)

    Cosmology with One Galaxy: Auto-Encoding the Galaxy Properties Manifold

    Amanda Lue, Shy Genel, Marc Huertas-Company et al.

    An autoencoder explores the galaxy-property manifold and the cosmological information encoded in individual galaxies.

    Neural networks
  37. 2025 · A&A 704, A94 (2025)

    COSMOS-Web: The emergence of the Hubble Sequence

    M. Huertas-Company, M. Shuntov, Y. Dong et al.

    Deep-learning morphology measurements trace the emergence of the Hubble sequence in COSMOS-Web.

    Machine learning
  38. 2025 · A&A 694, L7 (2025)

    ZF-UDS-7329: A relic galaxy in the early Universe

    Eduardo A. Hartmann, Ignacio Martín-Navarro, Marc Huertas-Company et al.

    Full-spectrum stellar-population fitting and Monte Carlo uncertainties reconstruct the formation history of a high-redshift relic galaxy.

    Spectral inference
  39. 2025 · A&A 699, A118 (2025)

    A statistical study of lopsided galaxies using random forest

    Valentina Fontirroig, Facundo A. Gomez, Marcelo Jaque Arancibia et al.

    Random forests identify which galaxy properties are associated with lopsided structure.

    Machine learning
  40. 2025 · A&A 693, A272 (2025)

    Spectral resolution effects on the information content in solar spectra

    C. J. Díaz Baso, I. Milić, L. Rouppe van der Voort et al.

    SIR inversions of degraded synthetic Stokes spectra measure how spectral resolution affects inferred solar atmospheric parameters.

    Spectral inference
  41. 2025 · A&A 693, A170 (2025)

    Exploring spectropolarimetric inversions using neural fields. Solar chromospheric magnetic field under the weak-field approximation

    C. J. Díaz Baso, A. Asensio Ramos, J. de la Cruz Rodríguez et al.

    Neural fields regularize spectropolarimetric inversions of the solar chromospheric magnetic field.

    Neural networksSpectral inference
  42. 2025 · A&A 693, A104 (2025)

    New constraints on the central mass contents of Omega Centauri from combined stellar kinematics and pulsar timing

    Andrés Bañares-Hernández, Francesca Calore, Jorge Martin Camalich et al.

    Nested sampling combines stellar motions and pulsar timing to constrain the central mass components of Omega Centauri.

    Bayesian inference
  43. 2024 · arXiv record

    Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in Reconstructions

    Alessio Spagnoletti, Alexandre Boucaud, Marc Huertas-Company et al.

    Diffusion priors support Bayesian image deconvolution and reveal which reconstructed features are driven by the prior.

    Bayesian inferenceGenerative models
  44. 2024 · A&A 692, A169 (2024)

    Non-Local Thermodynamic Equilibrium inversions of the Si I 10827 A spectral line

    C. Quintero Noda, N. G. Shchukina, A. Asensio Ramos et al.

    Non-LTE inversions recover solar atmospheric information from the silicon 10827 Å line.

    Spectral inference
  45. 2024 · arXiv record

    Simulation-based inference of the 2D ex-situ stellar mass fraction distribution of galaxies using variational autoencoders

    Eirini Angeloudi, Marc Huertas-Company, Jesús Falcón-Barroso et al.

    Variational autoencoders infer two-dimensional maps of stellar mass acquired through galaxy mergers.

    Simulation-based inferenceNeural networks
  46. 2024 · arXiv record

    No evidence for gamma-ray emission from the Sagittarius dwarf spheroidal galaxy

    Christopher Eckner, Silvia Manconi, Francesca Calore

    Adaptive gamma-ray templates and nested sampling of pixel-count statistics test emission associated with the Sagittarius dwarf galaxy.

    Bayesian inference
  47. 2024 · A&A 691, A308 (2024)

    Value Added Catalog of physical properties of more than 1.3 million galaxies from the DESI Survey

    M. Siudek, R. Pucha, M. Mezcua et al.

    Spectral energy distribution fitting estimates physical properties for more than 1.3 million DESI galaxies.

    Spectral inference
  48. 2024 · arXiv record

    Properties of sunspot light bridges on a geometric height scale

    S. Esteban Pozuelo, A. Asensio Ramos, C. J. Díaz Baso et al.

    Spectral inversions reconstruct the atmospheric properties of sunspot light bridges on a geometric height scale.

    Spectral inference
  49. 2024 · arXiv record

    The negative BAO shift in the Lyα forest from cosmological simulations

    Francesco Sinigaglia, Francisco-Shu Kitaura, Kentaro Nagamine et al.

    Markov-chain Monte Carlo fits quantify the baryon acoustic oscillation shift in simulated Lyman-alpha forests.

    Bayesian inference
  50. 2024 · Nature Astronomy 8, 1310–1320 (2024)

    Constraints on the in-situ and ex-situ stellar masses in nearby galaxies with Artificial Intelligence

    Eirini Angeloudi, Jesús Falcón-Barroso, Marc Huertas-Company et al.

    AI estimates how much stellar mass nearby galaxies formed internally and acquired through mergers.

    Machine learning
  51. 2024 · A&A 689, A58 (2024)

    Deriving the star formation histories of galaxies from spectra with simulation-based inference

    Patricia Iglesias-Navarro, Marc Huertas-Company, Ignacio Martín-Navarro et al.

    Simulation-based inference reconstructs galaxy star-formation histories from spectra with posterior uncertainties.

    Simulation-based inference
  52. 2024 · MNRAS 531, 4930–4943 (2024)

    A fast neural emulator for interstellar chemistry

    A. Asensio Ramos, C. Westendorp Plaza, D. Navarro-Almaida et al.

    A neural emulator accelerates interstellar chemical calculations for physical modelling and inference.

    Neural networks
  53. 2024 · A&A 689, A37 (2024)

    The PAU Survey: galaxy stellar population properties estimates with narrowband data

    Benjamin Csizi, Luca Tortorelli, Małgorzata Siudek et al.

    CIGALE and Prospector infer galaxy properties from PAU narrow-band photometry and assess model-dependent uncertainties.

    Bayesian inferenceSpectral inference
  54. 2024 · arXiv record

    Simulation-based inference of radio millisecond pulsars in globular clusters

    Joanna Berteaud, Christopher Eckner, Francesca Calore et al.

    Marginal neural ratio estimation constrains the size and luminosity distribution of millisecond-pulsar populations in globular clusters.

    Simulation-based inferenceNeural networks
  55. 2024 · A&A 690, A27 (2024)

    Fast simulation mapping: from standard to modified gravity cosmologies using the bias assignment method

    Jorge Enrique García-Farieta, Andrés Balaguera-Antolínez, Francisco-Shu Kitaura

    A calibrated bias-assignment method maps standard cosmological simulations into modified-gravity tracer distributions.

    Machine learning
  56. 2024 · A&A 688, A88 (2024)

    Solar multi-object multi-frame blind deconvolution with a spatially variant convolution neural emulator

    A. Asensio Ramos

    A neural emulator accelerates solar image restoration with spatially varying atmospheric degradation.

    Neural networks
  57. 2024 · A&A 687, A76 (2024)

    From VIPERS to SDSS: Unveiling galaxy spectra evolution over 9 Gyr through unsupervised machine-learning

    J. Dubois, M. Siudek, D. Fraix-Burnet et al.

    Unsupervised spectral classification compares galaxy populations across nine billion years of evolution.

    Machine learning
  58. 2024 · A&A 686, A229 (2024)

    Probing star formation rates and histories in AGN and non-AGN galaxies across diverse cosmic environments and extensive X-ray luminosity ranges

    G. Mountrichas, M. Siudek, O. Cucciati

    Likelihood-weighted CIGALE estimates compare star formation in AGN hosts and inactive galaxies across environments.

    Spectral inference
  59. 2024 · 2024MNRAS.530.4395S

    Robust inference of the Galactic centre gamma-ray excess spatial properties

    Deheng Song, Christopher Eckner, Chris Gordon et al.

    Bayesian evidence compares Galactic center excess morphologies after adaptive optimization of diffuse-emission backgrounds.

    Bayesian inference
  60. 2024 · arXiv record

    A post-merger enhancement only in star-forming Type 2 Seyfert galaxies: the deep learning view

    M. S. Avirett-Mackenzie, C. Villforth, M. Huertas-Company et al.

    Deep-learning merger identification tests the connection between galaxy interactions and Seyfert activity.

    Machine learning
  61. 2024 · The Astrophysical Journal, 2024, 963, 69

    Global Coronal Magnetic Field Estimation Using Bayesian Inference

    Upasna Baweja, Vaibhav Pant, Iñigo Arregui

    Bayesian inference maps coronal magnetic-field strengths from CoMP wave and density measurements, including uncertainty.

    Bayesian inference
  62. 2024 · The Astrophysical Journal 963 (2024)

    Galaxies Going Bananas: Inferring the 3D Geometry of High-Redshift Galaxies with JWST-CEERS

    Viraj Pandya, Haowen Zhang, Marc Huertas-Company et al.

    Bayesian geometric inference reconstructs the three-dimensional shapes of high-redshift galaxies from JWST observations.

    Bayesian inference
  63. 2024 · A&A 684, A100 (2024)

    Bayesian deep learning for cosmic volumes with modified gravity

    Jorge Enrique García-Farieta, Héctor J Hortúa, Francisco-Shu Kitaura

    Bayesian neural networks distinguish modified-gravity cosmologies from cosmic density volumes while quantifying uncertainty.

    Bayesian inferenceNeural networks
  64. 2024 · Phys. Rev. D 109, 043010 (2024)

    Uncovering axion-like particles in supernova gamma-ray spectra

    Francesca Calore, Pierluca Carenza, Christopher Eckner et al.

    MultiNest posterior sampling reconstructs axion-like particle parameters from simulated supernova gamma-ray spectra.

    Bayesian inference
  65. 2024 · A&A 685, A48 (2024)

    Galaxy Morphology from z≈6 through the eyes of JWST

    M. Huertas-Company, K. G. Iyer, E. Angeloudi et al.

    Deep-learning morphology classification follows galaxy structure to redshift six with JWST.

    Machine learning
  66. 2024 · The Astrophysical Journal 961, 51 (2024)

    On the nature of disks at high redshift seen by JWST/CEERS with contrastive learning and cosmological simulations

    J. Vega-Ferrero, M. Huertas-Company, L. Costantin et al.

    Contrastive learning compares high-redshift JWST galaxies with cosmological simulations to investigate disk structure.

    Foundation models
How papers are selected

At least one current group member must appear in positions 1–3 of the source author list. Collaboration names count as listed entries. We include explicit applications of machine learning, Bayesian or simulation-based inference, and advanced inverse methods; ordinary regression or a future inference application alone does not qualify.

Dates refer to the journal year where available, otherwise the first preprint year. Earlier preprints published since 2024 are included when publication metadata is verified. Preprint and journal versions are combined. The initial collection was checked against abstracts and, where needed, full texts; new entries are selected automatically from explicit method evidence in titles and abstracts.

Coverage depends on source indexing and author-name variants. Methods described only in full text may need a manual addition. Search record and maintenance details ↗