Related papers: Zero-Permutation Jet-Parton Assignment using a Sel…

We compute resummed and matched predictions for jet angularities in hadronic dijet and Z+jet events with and without grooming the candidate jets using the SoftDrop technique. Our theoretical predictions also account for non-perturbative…

Semantic segmentation in very high resolution (VHR) aerial images is one of the most challenging tasks in remote sensing image understanding. Most of the current approaches are based on deep convolutional neural networks (DCNNs). However,…

We extend the lowest-order matching of tree-level matrix elements with parton showers to give a complete description at the next higher perturbative accuracy in alpha_s at both small and large jet resolutions, which has not been achieved so…

The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles. Bayesian Attention Networks are defined by introducing an attention factor per a training sample loss as a function of two sample…

This paper provides a novel solution to a task allocation problem, by which a group of agents decides on the assignment of a discrete set of tasks in a distributed manner. In this setting, heterogeneous agents have individual preferences…

We study momentum imbalance as a function of jet asymmetry in high-energy heavy-ion collisions. To implement parton production during the collision, we include all Leading Order (LO) $2\to 2$ and $2\to 3$ parton processes in pQCD. The…

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Machine learning (ML) techniques have recently enabled enormous gains in sensitivity to new phenomena across the sciences. In particle physics, much of this progress has relied on excellent simulations of a wide range of physical processes.…

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based…

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language…

Fast data generation based on Machine Learning has become a major research topic in particle physics. This is mainly because the Monte Carlo simulation approach is computationally challenging for future colliders, which will have a…

Transformers have become the primary architecture for natural language processing. In this study, we explore their use for auto-regressive density estimation in high-energy jet physics, which involves working with a high-dimensional space.…

A tree level merging algorithm which guarantees the leading order (LO) accuracy of angular correlations between jets is proposed and studied. The algorithm is designed so that n-jet events are generated exclusively according to the LO…

Self-attention (SA) has become the cornerstone of modern vision backbones for its powerful expressivity over traditional Convolutions (Conv). However, its quadratic complexity remains a critical bottleneck for practical applications. Given…

Self-attention network (SAN) has recently attracted increasing interest due to its fully parallelized computation and flexibility in modeling dependencies. It can be further enhanced with multi-headed attention mechanism by allowing the…

Explicit applications of factorization theorems for processes at hadron colliders near the hadronic endpoint have largely focused on simple final states with either no jets (e.g., Drell-Yan) or one inclusive jet (e.g., deep inelastic…

We investigate the self-attention mechanism of BERT in a fine-tuning scenario for the classification of scientific articles over a taxonomy of research disciplines. We observe how self-attention focuses on words that are highly related to…

The jet charge is an old observable that has proven uniquely useful for discrimination of jets initiated by different flavors of light quarks, for example. In this Letter, we propose an approach to understanding the jet charge by…

Trajectory prediction has been a long-standing problem in intelligent systems like autonomous driving and robot navigation. Models trained on large-scale benchmarks have made significant progress in improving prediction accuracy. However,…

Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse attention to full-attention-trained models causes performance degradation due to train-inference…