Related papers: Exploring Magnetic Fields in Molecular Clouds thro…

The differences in brain dynamics across human subjects, commonly referred to as human artifacts, have long been a challenge in the field, severely limiting the generalizability of brain dynamics recognition models. Traditional methods for…

Diffusion models have emerged as a prominent technique in generative modeling with neural networks, making their mark in tasks like text-to-image translation and super-resolution. In this tutorial, we provide a comprehensive guide to build…

Denoising diffusion probabilistic models (DDPMs) have pioneered new state-of-the-art results in disciplines such as computer vision and computational biology for diverse tasks ranging from text-guided image generation to structure-guided…

Through Diffusion Models (DMs), we have made significant advances in generating high-quality images. Our exploration of these models delves deeply into their core operational principles by systematically investigating key aspects across…

Circular polarisation measurements of white dwarfs of various ages and spectral types are useful to understand the origin and evolution of the magnetic field in degenerate stars. In the latest stages of white dwarf evolution, when stars are…

The complete three-dimensional structure of the magnetic field within molecular clouds has eluded determination despite its high value in determining controlling factors in the star formation process, as it cannot be directly probed…

We propose the Binary Diffusion Probabilistic Model (BDPM), a generative framework specifically designed for data representations in binary form. Conventional denoising diffusion probabilistic models (DDPMs) assume continuous inputs, use…

Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms.…

Recently, denoising diffusion probabilistic models (DDPM) have been applied to image segmentation by generating segmentation masks conditioned on images, while the applications were mainly limited to 2D networks without exploiting potential…

Leveraging neural networks as surrogate models for turbulence simulation is a topic of growing interest. At the same time, embodying the inherent uncertainty of simulations in the predictions of surrogate models remains very challenging.…

This report presents the comprehensive implementation, evaluation, and optimization of Denoising Diffusion Probabilistic Models (DDPMs) and Denoising Diffusion Implicit Models (DDIMs), which are state-of-the-art generative models. During…

Medical image segmentation is a challenging task, made more difficult by many datasets' limited size and annotations. Denoising diffusion probabilistic models (DDPM) have recently shown promise in modelling the distribution of natural…

Measuring the strength of three dimensional (3D) magnetic field vector is challenging as it is not easy to recognize whether its line-of-sight (LOS) and plane-of-sky (POS) components are obtained from the same region. CN ($N = 1 - 0$)…

Super-Alfv\'enic turbulence is widespread in astrophysical environments, including molecular clouds and the diffuse plasma of galaxy clusters. At large scales, magnetic fields play only a minor dynamical role; however, for sufficiently…

One can estimate the characteristic magnetic field strength in GMCs by comparing submillimeter polarimetric observations of these sources with simulated polarization maps developed using a range of different values for the assumed field…

To sample from an unconditionally trained Denoising Diffusion Probabilistic Model (DDPM), classifier guidance adds conditional information during sampling, but the gradients from classifiers, especially those not trained on noisy images,…

We introduce a method for calculating the probability density function (PDF) of a turbulent density field in three dimensions using only information contained in the projected two-dimensional column density field. We test the method by…

In this work, we address two major issues in recent Denoising Diffusion Probabilistic Models (DDPM): {\bf 1)} geometric key feature extraction and {\bf 2)} network equivariance. Since the DDPM prediction network relies on the U-net…

We propose a novel unpaired image-to-image translation method that uses denoising diffusion probabilistic models without requiring adversarial training. Our method, UNpaired Image Translation with Denoising Diffusion Probabilistic Models…

Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by the evolving feature dynamics across the denoising…