Related papers: Locality-Sensitive Hashing-Based Efficient Point T…

This paper discusses a parallelized event reconstruction of the COMET Phase-I experiment. The experiment aims to discover charged lepton flavor violation by observing 104.97 MeV electrons from neutrinoless muon-to-electron conversion in…

The application of Graph Neural Networks (GNN) in track reconstruction is a promising approach to cope with the challenges arising at the High-Luminosity upgrade of the Large Hadron Collider (HL-LHC). GNNs show good track-finding…

As a variant of Graph Neural Networks (GNNs), Unfolded GNNs offer enhanced interpretability and flexibility over traditional designs. Nevertheless, they still suffer from scalability challenges when it comes to the training cost. Although…

Large Language Models (LLMs) are increasingly adopted for complex scientific text generation tasks, yet they often suffer from limitations in accuracy, consistency, and hallucination control. This thesis introduces a Parameter-Efficient…

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…

A key scalability challenge in neural solvers for industrial-scale physics simulations is efficiently capturing both fine-grained local interactions and long-range global dependencies across millions of spatial elements. We introduce the…

Charged particle track reconstruction in silicon detectors of collider experiments in high-multiplicity events, such as heavy-ion collisions at LHC, is a difficult and resource-demanding process. The first phase of the procedure is the…

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which…

Graph generation is a critical task in numerous domains, including molecular design and social network analysis, due to its ability to model complex relationships and structured data. While most modern graph generative models utilize…

Efficient and accurate feed-forward multi-view reconstruction has long been an important task in computer vision. Recent transformer-based models like VGGT, $\pi^3$ and MapAnything have demonstrated remarkable performance with relatively…

For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on…

This paper presents a novel Fully Binary Point Cloud Transformer (FBPT) model which has the potential to be widely applied and expanded in the fields of robotics and mobile devices. By compressing the weights and activations of a 32-bit…

With the increase in energy of the Large Hadron Collider to a centre-of-mass energy of 13 TeV for Run 2, events with dense environments, such as in the cores of high-energy jets, became a focus for new physics searches as well as…

Networks are ubiquitous in the real world. Link prediction, as one of the key problems for network-structured data, aims to predict whether there exists a link between two nodes. The traditional approaches are based on the explicit…

High-energy physics is facing increasingly computational challenges in real-time event reconstruction for the near-future high-luminosity era. Using the LHCb vertex detector as a use-case, we explore a new algorithm for particle track…

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

We present the current development status and progress of traccc, a GPU track reconstruction library developed in the context of the A Common Tracking Software (ACTS) project. traccc implements tracking algorithms used in high energy…

As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…

In this work we demonstrate that significant gains in performance and data efficiency can be achieved in High Energy Physics (HEP) by moving beyond the standard paradigm of sequential optimization or reconstruction and analysis components.…

This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors. This method reduces the average compute load of an off-the-shelf Deep Neural…