Related papers: Enhancing low energy reconstruction and classifica…

Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally dense, overlapping detector signatures. In this regime, event interpretation becomes impractical…

Sequence modelling requires determining which past tokens are causally relevant from the context and their importance: a process inherent to the attention layers in transformers, yet whose underlying learned mechanisms remain poorly…

We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel…

Three-dimensional (3D) magnetic reconstruction is vital to the study of novel magnetic materials for 3D spintronics. Vector field electron tomography (VFET) is a major in house tool to achieve that. However, conventional VFET reconstruction…

Limited-angle X-ray tomography reconstruction is an ill-conditioned inverse problem in general. Especially when the projection angles are limited and the measurements are taken in a photon-limited condition, reconstructions from classical…

Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and limited label-preserving augmentations. As a result, ensemble…

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…

Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by the evidence that pure self-attention possesses a strong…

Using deep neural networks for identifying physics objects at the Large Hadron Collider (LHC) has become a powerful alternative approach in recent years. After successful training of deep neural networks, examining the trained networks not…

This paper introduces a novel lightweight computational framework for enhancing images under low-light conditions, utilizing advanced machine learning and convolutional neural networks (CNNs). Traditional enhancement techniques often fail…

Although end-to-end Neural Machine Translation (NMT) has achieved remarkable progress in the past two years, it suffers from a major drawback: translations generated by NMT systems often lack of adequacy. It has been widely observed that…

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

During recent years transformers architectures have been growing in popularity. Modulated Detection Transformer (MDETR) is an end-to-end multi-modal understanding model that performs tasks such as phase grounding, referring expression…

Accurate measurement of neutrino energies is essential to many of the scientific goals of large-volume neutrino telescopes. The fundamental observable in such detectors is the Cherenkov light produced by the transit through a medium of…

Transformers have been successful in many vision tasks, thanks to their capability of capturing long-range dependency. However, their quadratic computational complexity poses a major obstacle for applying them to vision tasks requiring…

KM3NeT/ARCA is a Cherenkov neutrino telescope under construction in the Mediterranean sea, optimised for the detection of astrophysical neutrinos with energies above $\sim$1~TeV. In this work, using Monte Carlo simulations including…

There has been great progress in understanding the neutrino sector in the last few years. One mixing angle has not yet been measured, theta-13. Detectors for the current round of long-baseline neutrino oscillation experiments, for future…

KM3NeT's detection of a muon track produced by a $\sim 220 \, {\rm PeV}$ neutrino provides an opportunity to probe physics at center-of-momentum energies greater than those probed by the Large Hadron Collider or other existing particle…

While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap is due to the fact that a) transformers…

While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change…