Related papers: Using Galaxy Evolution as Source of Physics-Based …
Cosmological simulations are a powerful tool to advance our understanding of galaxy formation and many simulations model key properties of real galaxies. A question that naturally arises for such simulations in light of high-quality…
Generative models cover various application areas, including image, video and music synthesis, natural language processing, and molecular design, among many others. As digital generative models become larger, scalable inference in a fast…
Recently, several methods have leveraged deep generative modeling to produce example-based explanations of image classifiers. Despite producing visually stunning results, these methods are largely disconnected from classical explainability…
When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological…
Denoising Diffusion Probabilistic Models (DDPMs) are powerful generative deep learning models that have been very successful at image generation, and, very recently, in path planning and control. In this paper, we investigate how to…
Score-based generative models have emerged as alternatives to generative adversarial networks (GANs) and normalizing flows for tasks involving learning and sampling from complex image distributions. In this work we investigate the ability…
The diffusion model has recently emerged as a potent approach in computer vision, demonstrating remarkable performances in the field of generative artificial intelligence. Capable of producing high-quality synthetic images, diffusion models…
The main foundations of the standard $\Lambda $CDM model of cosmology are that: 1) The redshifts of the galaxies are due to the expansion of the Universe plus peculiar motions; 2) The cosmic microwave background radiation and its…
I outline a quantitative method for characterizing galaxies both by photometric `form' and indices of spectral-type, applicable to both nearby and distant galaxies. Such a characterization provides insight on galaxy evolution because there…
The gravitational lensing effect provides various ways to study the mass environment of galaxies. We investigate how galaxy-galaxy(-galaxy) lensing can be used to test models of galaxy formation and evolution. We consider two semi-analytic…
For a considerable time, researchers have focused on developing a method that establishes a deep connection between the generative diffusion model and mathematical physics. Despite previous efforts, progress has been limited to the pursuit…
This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization, from a stochastic differential equation perspective. We show that DMs can be…
Cosmological simulations play a crucial role in elucidating the effect of physical parameters on the statistics of fields and on constraining parameters given information on density fields. We leverage diffusion generative models to address…
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions. However, relying solely on text for…
We study the sources of biases and systematics in the derivation of galaxy properties of observational studies, focusing on stellar masses, star formation rates, gas/stellar metallicities, stellar ages and magnitudes/colors. We use…
Generative models have shown great promise in generating 3D geometric systems, which is a fundamental problem in many natural science domains such as molecule and protein design. However, existing approaches only operate on static…
In recent years there has been increased interest in understanding the interplay between deep generative models (DGMs) and the manifold hypothesis. Research in this area focuses on understanding the reasons why commonly-used DGMs succeed or…
Generative models aim to learn the distribution of observed data by generating new instances. With the advent of neural networks, deep generative models, including variational autoencoders (VAEs), generative adversarial networks (GANs), and…
End-to-end deep learning models fed with multi-band galaxy images are powerful data-driven tools used to estimate galaxy physical properties in the absence of spectroscopy. However, due to a lack of interpretability and the associational…
The development of accurate medical image classification models is often constrained by privacy concerns and data scarcity for certain conditions, leading to small and imbalanced datasets. To address these limitations, this study explores…