Related papers: Multi-scale cross-attention transformer encoder fo…
To benefit the complementary information between heterogeneous data, we introduce a new Multimodal Transformer (MMFormer) for Remote Sensing (RS) image classification using Hyperspectral Image (HSI) accompanied by another source of data…
Machine Learning (ML) techniques are rapidly finding a place among the methods of High Energy Physics data analysis. Different approaches are explored concerning how much effort should be put into building high-level variables based on…
Quantum machine learning (QML) has gained increasing attention as a potential solution to address the challenges of computation requirements in the future. Earth observation (EO) has entered the era of Big Data, and the computational…
We investigate the application of hybrid quantum tensor networks to aeroelastic problems, harnessing the power of Quantum Machine Learning (QML). By combining tensor networks with variational quantum circuits, we demonstrate the potential…
While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first propose a cross-scale vision transformer, CrossFormer. It…
Objective: A clinical decision support tool that automatically interprets EEGs can reduce time to diagnosis and enhance real-time applications such as ICU monitoring. Clinicians have indicated that a sensitivity of 95% with a specificity…
We are interested in the problem of classifying Multivariate Hawkes Processes (MHP) paths coming from several classes. MHP form a versatile family of point processes that models interactions between connected individuals within a network.…
Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…
The reasoning abilities of Large Language Models (LLMs) can be improved by structurally denoising their weights, yet existing techniques primarily focus on denoising the feed-forward network (FFN) of the transformer block, and can not…
This study demonstrates the application of supervised machine learning (ML) techniques to distinguish between isotropic and jet-like event topologies in heavy-ion collisions via the spherocity observable. State-of-the-art ML algorithms,…
The extension of the Standard Model (SM) with two complex $SU(2)_{L}$ scalar triplets enables one to have the Type II seesaw mechanism operative consistently with texture-zero neutrino mass matrices. This framework predicts additional…
A complete parton level analysis of ll + four jets l = e,mu and 3lv + two jets production at the LHC is presented, including all processes at order $\ordEW$, $\ordQCD$ and $\ordQCDsq$ when appropriate. The infinite Higgs mass scenario,…
We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes. The…
These proceedings highlight a selection of recent results by the ATLAS, CMS and LHCb collaborations. The majority of the featured analyses make use of the large set of $\sqrt{s}=13$ TeV proton-proton collision data collected during the…
A search is presented for a heavy resonance $Y$ decaying into a Standard Model Higgs boson $H$ and a new particle $X$ in a fully hadronic final state. The full Large Hadron Collider Run 2 dataset of proton-proton collisions at $\sqrt{s}=…
Handwritten mathematical expression recognition is a challenging problem due to the complicated two-dimensional structures, ambiguous handwriting input and variant scales of handwritten math symbols. To settle this problem, we utilize the…
We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM…
Event classifiers are the most fundamental observables to probe the event topology of hadronic and nuclear collisions at relativistic energies. Over the last five decades, significant progress has been made to establish suitable event…
Based on the jet image approach, which treats the energy deposition in each calorimeter cell as the pixel intensity, the Convolutional neural network (CNN) method has been found to achieve a sizable improvement in jet tagging compared to…
This contribution describes the experience with the application of different Machine Learning (ML) techniques to a physics analysis case. The use case chosen is the classification of top-antitop events coming from BSM or from SM using data…