Related papers: Multi-scale cross-attention transformer encoder fo…
Induction head mechanism is a part of the computational circuits for in-context learning (ICL) that enable large language models (LLMs) to adapt to new tasks without fine-tuning. Most existing work explains the training dynamics behind…
We introduce a novel end-to-end framework for jet reconstruction in high-energy collider events, leveraging the efficiency and long-range modeling capabilities of the Mamba architecture. Our model unifies instance segmentation,…
The Higgs self-coupling is crucial for understanding the structure of the scalar potential and the mechanism of electroweak symmetry breaking. In this work, utilizing deep neural network based on Particle Transformer that relies on…
The interpretation of Large Hadron Collider (LHC) data in the framework of Beyond the Standard Model (BSM) theories is hampered by the need to run computationally expensive event generators and detector simulators. Performing statistically…
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…
At the Large Hadron Collider, numerous physics processes expected within the standard model and theories beyond it give rise to very high momentum particles decaying to multihadronic final states. Development of algorithms for efficient…
High-harmonic generation (HHG) in solids provides a powerful platform to probe ultrafast electron dynamics and interband--intraband coupling. However, disentangling the complex many-body contributions in the HHG spectrum remains…
This study investigates the production of multi-top quark events final states containing up to four top quarks as a probe for new physics beyond the Standard Model (SM) within the framework of the Two Higgs Doublet Model (2HDM) Type-I.…
Study of the production of pairs of top quarks in association with a Higgs boson is one of the primary goals of the Large Hadron Collider over the next decade, as measurements of this process may help us to understand whether the uniquely…
The high-luminosity era of the LHC will offer greatly increased number of events for more precise Standard Model measurements and Beyond Standard Model searches, but will also pose unprecedented challenges to the detectors. To meet these…
Emotion recognition in conversations is challenging due to the multi-modal nature of the emotion expression. We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition using a combination of recurrent…
Recent advancements in deep learning models have significantly enhanced jet classification performance by analyzing low-level features (LLFs). However, this approach often leads to less interpretable models, emphasizing the need to…
Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…
Multiple Instance Learning (MIL) and transformers are increasingly popular in histopathology Whole Slide Image (WSI) classification. However, unlike human pathologists who selectively observe specific regions of histopathology tissues under…
Processing 3D data efficiently has always been a challenge. Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for…
Interest in deep learning in collider physics has been growing in recent years, specifically in applying these methods in jet classification, anomaly detection, particle identification etc. Among those, jet classification using neural…
In this study, we investigate the Large Hadron Collider (LHC) search for the signal process $pp\to A \to Z^{*}h \to \ell^{+} \ell^{-} b \bar{b}$ ($\ell=e,\mu$) within the framework of the 2-Higgs-Doublet Model (2HDM) Type-I, considering an…
The $\text{t}\bar{\text{t}}\text{H}(\text{b}\bar{\text{b}})$ process is an essential channel to reveal the Higgs properties but has an irreducible background from the $\text{t}\bar{\text{t}}\text{b}\bar{\text{b}}$ process, which produces a…
We study the benefits of jet- and event-level deep learning methods in distinguishing vector boson fusion (VBF) from gluon-gluon fusion (GGF) Higgs production at the LHC. We show that a variety of classifiers (CNNs, attention-based…
We give a novel logical characterization of encoder-decoder transformers, the foundational architecture for LLMs that also sees use in various settings that benefit from cross-attention. We study such transformers over text in the practical…