Related papers: Disk Wind Feedback from High-mass Protostars. V. A…

Recent advancements in areas such as natural language processing and computer vision rely on intricate and massive models that have been trained using vast amounts of unlabelled or partly labeled data and training or deploying these…

The increased adoption of reinforced polymer (RP) composite materials, driven by eco-design standards, calls for a fine balance between lightness, stiffness, and effective vibration control. These materials are integral to enhancing…

We present a deep machine learning (ML) approach to constraining cosmological parameters with multi-wavelength observations of galaxy clusters. The ML approach has two components: an encoder that builds a compressed representation of each…

Given the widespread availability of grids of models for stellar atmospheres, it is necessary to recover intermediate atmospheric models by means of accurate techniques that go beyond simple linear interpolation and capture the intricacies…

High-mass stars, with their powerful winds and intense radiation fields, are fundamental in regulating galactic dynamics and evolution; however, despite their great relevance, the mechanisms involved in their formation are still not fully…

In protoplanetary disks micron-size dust grains coagulate to form larger structures with complex shapes and compositions. The coagulation process changes the absorption and scattering properties of particles in the disk in significant ways.…

Context: Because it is viewed simply edge-on, the HH212 protostellar system is an ideal laboratory for studying the interplay of infall, outflow, and rotation in the earliest stages of low-mass star formation. Aims: We wish to exploit the…

Estimating motion from spatiotemporal geoscientific data is a fundamental component of many environmental modeling and forecasting tasks. In this work, we propose a physics-informed deep learning framework for estimating altitude-wise…

We present a Bayesian machine learning architecture that combines a physically motivated parametrization and an analytic error model for the likelihood with a deep generative model providing a powerful data-driven prior for complex signals.…

Finding appropriate low dimensional representations of high-dimensional multi-modal data can be challenging, since each modality embodies unique deformations and interferences. In this paper, we address the problem using manifold learning,…

In the realm of autonomous driving, accurate 3D perception is the foundation. However, developing such models relies on extensive human annotations -- a process that is both costly and labor-intensive. To address this challenge from a data…

Four-dimensional scanning transmission electron microscopy (4D-STEM) of local atomic diffraction patterns is emerging as a powerful technique for probing intricate details of atomic structure and atomic electric fields. However, efficient…

We present high angular resolution dust polarization and molecular line observations carried out with the Atacama Large Millimeter/submillimeter Array (ALMA) toward the Class 0 protostar Serpens SMM1. By complementing these observations…

Context. To further understand the processes involved in the formation of massive stars, we have undertaken a study of the gas dynamics surrounding three massive star forming regions. By observing the large scale structures at high…

Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image sequences. Most existing approaches combine autoregressive…

Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-text inputs. Yet despite these gains, it remains unclear how…

Galactic winds shape galaxy evolution; however, the outflowing gas is complex: it consists of multiple ionization phases, and its properties vary spatially. Therefore, methods that combine high-fidelity observations with state-of-the-art…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

We develop a novel method based on machine learning principles to achieve optimal initiation of CPU-intensive computations for forward asteroseismic modeling in a multi-D parameter space. A deep neural network is trained on a precomputed…

Multi-modal image fusion integrates complementary information from different modalities into a unified representation. Current methods predominantly optimize statistical correlations between modalities, often capturing dataset-induced…