Related papers: A differentiable and optimizable 3D model for inte…

Molecular emission is a powerful tool for studying the physical and chemical structures of dense cores. The distribution and abundance of different molecules provide information on the chemical composition and physical properties in these…

Machine learning in atomistic materials science has grown to become a powerful tool, with most approaches focusing on atomic arrangements, typically decomposed into local atomic environments. This approach, while well-suited for…

Probing properties of neutron stars from photometric observations of these objects helps us answer crucial questions at the forefront of multi-messenger astronomy, such as, what is behavior of highest density matter in extreme environments…

Structure-based molecular ML (SBML) models can be highly sensitive to input geometries and give predictions with large variance. We present an approach to mitigate the challenge of selecting conformations for such models by generating…

Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we…

This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common practice to generate distinctive geometric descriptors by fusing…

Tokens are discrete representations that allow modern deep learning to scale by transforming high-dimensional data into sequences that can be efficiently learned, generated, and generalized to new tasks. These have become foundational for…

From AlexNet to Inception, autoencoders to diffusion models, the development of novel and powerful deep learning models and learning algorithms has proceeded at breakneck speeds. In part, we believe that rapid iteration of model…

Particle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate…

Extracting information from complex data is a challenge shared by multiple frontiers of modern astrophysical research. Among those, analyzing spectra cubes, where the emission is mapped in the position-position-velocity space is a difficult…

In the area of 3D shape analysis, the geometric properties of a shape have long been studied. Instead of directly extracting representative features using expert-designed descriptors or end-to-end deep neural networks, this paper is…

Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we…

We have compared molecular line emission to dust continuum emission and modeled molecular lines using Monte Carlo simulations in order to study the depletion of molecules and the ionization fraction in three preprotostellar cores, L1512,…

This paper describes an optimized single-stage deep convolutional neural network to detect objects in urban environments, using nothing more than point cloud data. This feature enables our method to work regardless the time of the day and…

We proposed a novel graph convolutional neural network that could construct a coarse, sparse latent point cloud from a dense, raw point cloud. With a novel non-isotropic convolution operation defined on irregular geometries, the model then…

Deep learning-based computer vision is usually data-hungry. Many researchers attempt to augment datasets with synthesized data to improve model robustness. However, the augmentation of popular pedestrian datasets, such as Caltech and…

We develop a method of analyzing radio frequency spectral line observations to derive data on the temperature, density, velocity, and molecular abundance of the emitting gas. The method incorporates a radiative transfer code with a new…

Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches…

The scattering matrix, which quantifies the optical reflection and transmission of a photonic structure, is pivotal for understanding the performance of the structure. In many photonic design tasks, it is also desired to know how the…

Evolved stars are among the largest and brightest stars and they are ideal targets for the new generation of sensitive, high resolution instrumentation that pro- vides spectrophotometric, interferometric, astrometric, and imaging…