A generative latent diffusion framework jointly infers photometric-redshift PDFs and reconstructs rest-frame spectra from photometric data after pre-training a spectral autoencoder on millions of spectra.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
fields
astro-ph.GA 4years
2026 4representative citing papers
Symmetric kiloparsec-scale radio knots in NGC 7213 indicate a confined weak jet and recurrent nuclear activity in this low-luminosity AGN.
HI absorption is detected in three sight lines through two disk galaxies at 7-22 Mpc, yielding Local-Group-like spin temperatures but lower CNM fractions due to resolution averaging in emission spectra.
Machine learning models achieve NMAD 0.036 and 5.6% outliers for quasar photometric redshifts, identifying 185 high-probability pair candidates in MGQPC with 20 spectroscopically confirmed as physical pairs.
citing papers explorer
-
Joint probabilistic inference of galaxy redshifts and rest-frame spectra from photometric fluxes with latent diffusion
A generative latent diffusion framework jointly infers photometric-redshift PDFs and reconstructs rest-frame spectra from photometric data after pre-training a spectral autoencoder on millions of spectra.
-
Symmetric kiloparsec-scale radio knots in NGC 7213: evidence for a confined weak jet and recurrent nuclear activity
Symmetric kiloparsec-scale radio knots in NGC 7213 indicate a confined weak jet and recurrent nuclear activity in this low-luminosity AGN.
-
HI absorption in MHONGOOSE -- Spin temperatures and cold neutral medium in nearby disk galaxies
HI absorption is detected in three sight lines through two disk galaxies at 7-22 Mpc, yielding Local-Group-like spin temperatures but lower CNM fractions due to resolution averaging in emission spectra.
-
Search for quasar pairs with Gaia astrometric data. II. Photometric redshift prediction with machine learning for the MGQPC catalogue
Machine learning models achieve NMAD 0.036 and 5.6% outliers for quasar photometric redshifts, identifying 185 high-probability pair candidates in MGQPC with 20 spectroscopically confirmed as physical pairs.