Related papers: Intrinsic Dimension Estimation for Radio Galaxy Zo…
In this work, we study the generalizability of diffusion models by looking into the hidden properties of the learned score functions, which are essentially a series of deep denoisers trained on various noise levels. We observe that as…
In this work, we propose a novel framework for estimating the dimension of the data manifold using a trained diffusion model. A diffusion model approximates the score function i.e. the gradient of the log density of a noise-corrupted…
Radio maps (RMs) are essential for environment-aware communication and sensing, providing location-specific wireless channel information. Existing RM construction methods often rely on precise environmental data and base station (BS)…
Fr\'echet Inception Distance (FID) is widely used to evaluate image generators, yet lower FID does not always correspond to better sample quality. We show that this mismatch depends in part on the geometry of the reference dataset. In a…
The Star Formation Rate Density (SFRD) history of the Universe is well constrained up to redshift $z \sim 2$. At earlier cosmic epochs, the picture has been largely inferred from UV-selected galaxies (e.g. Lyman-break galaxies, LBGs).…
In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural…
This paper demonstrates a novel and efficient unsupervised clustering method with the combination of a Self-Organising Map (SOM) and a convolutional autoencoder. The rapidly increasing volume of radio-astronomical data has increased demand…
Quantifying how the baryonic matter traces the underlying dark matter distribution is key to both understanding galaxy formation and our ability to constrain the cosmological model. Using the cross-correlation function of radio and…
We theoretically investigate the phenomena of generalization and memorization in diffusion models. Empirical studies suggest that these phenomena are influenced by model complexity and the size of the training dataset. In our experiments,…
We present predictions for the evolution of the galaxy luminosity function, number counts and redshift distributions in the IR based on the Lambda-CDM cosmological model. We use the combined GALFORM semi-analytical galaxy formation model…
Hybrid morphology radio sources are a rare type of radio galaxy that display different Fanaroff-Riley classes on opposite sides of their nuclei. To enhance the statistical analysis of hybrid morphology radio sources, we embarked on a…
Recent methods have shown that pre-trained diffusion models can be fine-tuned to enable generative inverse rendering by learning image-conditioned noise-to-intrinsic mapping. Despite their remarkable progress, they struggle to robustly…
We present a novel approach to reconstruct gas and dark matter projected density maps of galaxy clusters using score-based generative modeling. Our diffusion model takes in mock SZ and X-ray images as conditional inputs, and generates…
The cosmic Distance Duality Relation (DDR) is a fundamental prediction of metric gravity under photon number conservation. In this work, we perform a model-independent test of the DDR using Pantheon+ type Ia supernovae (SN Ia), \emph{Fermi}…
We use the GOODS-MUSIC sample, a catalog of ~3000 Ks-selected galaxies based on VLT and HST observation of the GOODS-South field with extended multi-wavelength coverage (from 0.3 to 8 micron) and accurate estimates of the photometric…
Cross-correlating the Planck High Frequency Instrument (HFI) maps against quasars from the Sloan Digital Sky Survey (SDSS) DR7, we estimate the intensity distribution of the Cosmic Infrared Background (CIB) over the redshift range 0 < z <…
Extragalactic radio sources have been classified into two classes, Fanaroff-Riley I and II, which differ in morphology and radio power. Strongly emitting sources belong to the edge-brightened FR II class, and weakly emitting sources to the…
The Bayesian neural network (BNN) has been applied to evaluate and predict the nuclear data. However, how to provide physics guides in BNN is a key but an open question. In this work, the case study on giant dipole resonance (GDR) energy is…
Previous studies based on the latest realisation of the International Celestial Reference Frame (ICRF3) have suggested a correlation between astrometric properties (such as the radio-optical offset) and redshift for active galactic nuclei…
Room geometry inference (RGI) aims at estimating room shapes from measured room impulse responses (RIRs) and has received lots of attention for its importance in environment-aware audio rendering and virtual acoustic representation of a…