arXiv Machine Learning June 2, 2026 By Brandon Zhao, Diana Scognamiglio, Olivier Dor\'e, Katherine L. Bouman

Generative Diffusion Priors for 3D Mapping of the Dark Universe

Read the original on arXiv Machine Learning →

arXiv:2606. 00803v1 Announce Type: cross Abstract: Reconstructing the three-dimensional distribution of dark matter from weak-lensing observations is a central but highly ill-posed inverse problem in cosmology.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

diffusion

arXiv Computer Vision

Sep 7

Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models

The paper presents a fully automated method for reconstructing the surface mass density of galaxy clusters using photometry and gravitational lensing data. It introduces DarkClusters-15k, a benchmark dataset of 15,000 simulated clusters with paired mass and photometry maps across multiple redshifts and simulation frameworks. By training a diffusion prior on this dataset, the authors generate posterior samples constrained by weak- and strong-lensing observables, achieving accurate, physics‑guided reconstructions with well‑calibrated uncertainties in minutes.

By Diego Royo, Brandon Zhao, Adolfo Mu\~noz, Diego Gutierrez, Katherine L. Bouman

diffusion benchmarks

arXiv Machine Learning

Jun 10

Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions

arXiv:2606. 10023v1 Announce Type: cross Abstract: Accurate posterior estimation is central to scientific inference, as uncertainties determine what can be reliably learned from observational data.

By Ludvig Doeser, Jens Jasche

arXiv Machine Learning

Jul 16

A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping

arXiv:2603. 22006v2 Announce Type: replace-cross Abstract: Upcoming stage-IV surveys such as Euclid and Rubin will deliver vast amounts of high-precision data, opening new opportunities to constrain cosmological models with unprecedented accuracy.

By Hubert Leterme, Andreas Tersenov, Jalal Fadili, Jean-Luc Starck

benchmarks

arXiv AI

Sep 10

Field-level weak lensing cosmology with $60$ simulations using multifidelity simulation-based inference

arXiv:2606.23346v2 Announce Type: replace-cross Abstract: We perform a realistic KiDS-Legacy mock analysis with field-level neural compression and simulation-based inference using just 60 $N$-body si...

By Alex A. Saoulis, Kiyam Lin, Niall Jeffrey, Maximilian von Wietersheim-Kramsta, Davide Piras, Alessio Spurio Mancini, Ana M. G. Ferreira, Benjamin Joachimi

fine-tuning

arXiv Machine Learning

Jul 31

Emulating Cosmic Structure Formation with a Lagrangian Neural Cellular Automaton

arXiv:2607. 27320v1 Announce Type: cross Abstract: Field-level inference of cosmological initial conditions from galaxy surveys requires a forward model that is simultaneously accurate in the non-linear regime, computationally efficient, and fully differentiable.

By Cooper Jacobus, Beatriz Tucci, Oliver Philcox

arXiv Machine Learning

Aug 6

PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior

arXiv:2512. 18367v2 Announce Type: replace-cross Abstract: Diffusion models are highly expressive image priors for Bayesian inverse problems.

By Wenhan Guo, Jinglun Yu, Yaning Wang, Jin U. Kang, Yu Sun

diffusion

One email a morning, machine-written

Related stories

Mapping Dark-Matter Clusters via Physics-Guided Diffusion Models

Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions

A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping

Field-level weak lensing cosmology with $60$ simulations using multifidelity simulation-based inference

Emulating Cosmic Structure Formation with a Lagrangian Neural Cellular Automaton

PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior