Related papers: Self-Supervised ConvLSTM for Fermi Large Area Tele…
Supernovae (SNe) exploding in a dense circumstellar medium (CSM) are predicted to accelerate cosmic rays in collisionless shocks and emit GeV gamma rays and TeV neutrinos on a time scale of several months. Here we summarize the results of…
This study proposes a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) ensemble framework that leverages diverse temporal input resolutions to mitigate error accumulation and improve long-horizon forecasting of…
The exploration of the time-variable astronomical sky at submm wavelengths is rapidly becoming more feasible with large sky surveys by Cosmic Microwave Background telescopes with tens of thousands of detectors. Observations with the Atacama…
We perform a comprehensive stacking analysis of data collected by the Fermi Large Area Telescope (LAT) of gamma-ray bursts (GRB) localized by the Swift spacecraft, which were not detected by the LAT but which fell within the instrument's…
This study presents a framework for predicting unsteady transonic wing pressure distributions, integrating an autoencoder architecture with graph convolutional networks and graph-based temporal layers to model time dependencies. The…
We investigate the prospects for discovering blazars at very high-redshifts (z>3-6) with the Fermi Gamma-Ray Space Telescope (Fermi), employing a model for the evolving gamma-ray luminosity function (GLF) of the blazar population. Our…
As synthetic data proliferates across the Internet, it is often reused to train successive generations of generative models. This creates a ``self-consuming loop" that can lead to training instability or \textit{model collapse}. Common…
Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow…
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for…
This paper presents a physics-informed framework that integrates graph convolutional networks (GCN) with long short-term memory (LSTM) architecture to forecast microstructure evolution over long time horizons in both 2D and 3D with…
Recently, a spatially extended excess of gamma rays collected by the Fermi-LAT from the inner region of the Milky Way has been detected by different groups and with increasingly sophisticated techniques. Yet, any final conclusion about the…
Temporal anomaly detection looks for irregularities over space-time. Unsupervised temporal models employed thus far typically work on sequences of feature vectors, and much less on temporal multiway data. We focus our investigation on…
Automating real-time anomaly detection is essential for identifying rare transients, with modern survey telescopes generating tens of thousands of alerts per night, and future telescopes, such as the Vera C. Rubin Observatory, projected to…
We use nine years of gamma-ray data provided by the Fermi Large Area Telescope (LAT) to systematically study the light curves of more than two thousand active galactic nuclei (AGN) included in recent Fermi-LAT catalogs. Ten different…
Integral Field Spectroscopy (IFS) surveys offer a unique new landscape in which to learn in both spatial and spectroscopic dimensions and could help uncover previously unknown insights into galaxy evolution. In this work, we demonstrate a…
Real-time identification and quantification of greenhouse-gas emissions under transient atmospheric conditions is a critical challenge in environmental monitoring. We introduce a spatio-temporal inversion framework that embeds a…
Breast-Conserving Surgery (BCS) requires precise intraoperative margin assessment to preserve healthy tissue. Deep Ultraviolet Fluorescence Scanning Microscopy (DUV-FSM) offers rapid, high-resolution surface imaging for this purpose;…
We set conservative, robust constraints on the annihilation and decay of dark matter into various Standard Model final states under various assumptions about the distribution of the dark matter in the Milky Way halo. We use the inclusive…
Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal…
With the upcoming Vera C.~Rubin Observatory Legacy Survey of Space and Time (LSST), it is expected that only $\sim 0.1\%$ of all transients will be classified spectroscopically. To conduct studies of rare transients, such as Type I…