Related papers: Using Galaxy Evolution as Source of Physics-Based …
Generative models trained on internet-scale data are capable of generating novel and realistic texts, images, and videos. A natural next question is whether these models can advance science, for example by generating novel stable materials.…
Generative models of graphs based on discrete Denoising Diffusion Probabilistic Models (DDPMs) offer a principled approach to molecular generation by systematically removing structural noise through iterative atom and bond adjustments.…
Deconstructing galaxies through two-dimensional decompositions has been shown to be a powerful technique to derive the physical properties of stellar structures in galaxies. However, most studies employ fitting algorithms that are prone to…
We develop and present the Descriptive Parametric Model (DPM), a tool for generating profiles of gaseous halos (pressure, electron density, and metallicity) as functions of radius, halo mass, and redshift. The model assumes single-phase,…
Generative models have recently emerged as powerful surrogates for physical systems, demonstrating increased accuracy, stability, and/or statistical fidelity. Most approaches rely on iteratively denoising a Gaussian, a choice that may not…
We present a method of including galaxy formation in dissipationless N-body simulations. Galaxies that form during the evolution are identified at several epochs and replaced by single massive soft particles. This allows one to produce…
Generating healthy counterfactuals from pathological images holds significant promise in medical imaging, e.g., in anomaly detection or for application of analysis tools that are designed for healthy scans. These counterfactuals should…
This paper introduces Diffuse-TreeVAE, a deep generative model that integrates hierarchical clustering into the framework of Denoising Diffusion Probabilistic Models (DDPMs). The proposed approach generates new images by sampling from a…
Molecule generation, especially generating 3D molecular geometries from scratch (i.e., 3D \textit{de novo} generation), has become a fundamental task in drug designs. Existing diffusion-based 3D molecule generation methods could suffer from…
Generative models are a class of AI models capable of creating new instances of data by learning and sampling from their statistical distributions. In recent years, these models have gained prominence in machine learning due to the…
Generative modeling seeks to approximate the statistical properties of real data, enabling synthesis of new data that closely resembles the original distribution. Generative Adversarial Networks (GANs) and Denoising Diffusion Probabilistic…
Studies of the distribution and evolution of galaxies are of fundamental importance to modern cosmology; these studies, however, are hampered by the complexity of the competing effects of spectral and density evolution. Constructing a…
Anatomical atlases are widely used for population studies and analysis. Conditional atlases target a specific sub-population defined via certain conditions, such as demographics or pathologies, and allow for the investigation of…
Estimating physical properties of galaxies from wide-field surveys remains a central challenge in astrophysics. While spectroscopy provides precise measurements, it is observationally expensive, and photometry discards morphological…
In this work, we propose to study the global geometrical properties of generative models. We introduce a new Riemannian metric to assess the similarity between any two data points. Importantly, our metric is agnostic to the parametrization…
With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…
Deep generative models are able to suggest new organic molecules by generating strings, trees, and graphs representing their structure. While such models allow one to generate molecules with desirable properties, they give no guarantees…
Large volume cosmological simulations succeed in reproducing the large-scale structure of the Universe. However, they lack resolution and may not take into account all relevant physical processes to test if the detail properties of galaxies…
The task of deducing three-dimensional molecular configurations from their two-dimensional graph representations holds paramount importance in the fields of computational chemistry and pharmaceutical development. The rapid advancement of…
Deep generative models have shown tremendous capability in data density estimation and data generation from finite samples. While these models have shown impressive performance by learning correlations among features in the data, some…