相关论文: A Generalized Approach to Longitudinal Momentum De…

Accurate fault location is essential for operational reliability and fast restoration in wind farm collector networks. However, the growing integration of inverter-based resources changes the current and voltage behavior during faults,…

This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism.…

Collider experiments are equipped with trigger systems that rapidly inspect the physics content emerging from collisions to decide whether the resulting products are worth saving for later analysis. One crucial aspect for analyzing the…

We present DeepTract, a deep-learning framework for estimating white matter fibers orientation and streamline tractography. We adopt a data-driven approach for fiber reconstruction from diffusion weighted images (DWI), which does not assume…

Anomaly detection in videos is a significant yet challenging problem. Previous approaches based on deep neural networks employ either reconstruction-based or prediction-based approaches. Nevertheless, existing reconstruction-based methods…

Models with a discrete endogenous variable are typically underidentified when the instrument takes on too few values. This paper presents a new method that matches pairs of covariates and instruments to restore point identification in this…

Discriminative correlation filters show excellent performance in object tracking. However, in complex scenes, the apparent characteristics of the tracked target are variable, which makes it easy to pollute the model and cause the model…

Lifelong person re-identification attempts to recognize people across cameras and integrate new knowledge from continuous data streams. Key challenges involve addressing catastrophic forgetting caused by parameter updating and domain shift,…

Test-time adaptation (TTA) is the problem of updating a pre-trained source model at inference time given test input(s) from a different target domain. Most existing TTA approaches assume the setting in which the target domain is stationary,…

Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone design for object detection. At the macro level, we propose…

Novel String Banana Template Method (SBTM) for track reconstruction in difficult conditions is proposed and implemented for off-line analysis of relativistic heavy ion collision events. The main idea of the method is in use of features of…

High energy physics experiments, in particular experiments at the LHC, require the reconstruction of charged particle trajectories. Methods of reconstructing such trajectories have been known for decades, yet the applications at High…

As experiments in high energy physics aims to measure increasingly rare processes, the experiments continually strive to increase the expected signal yields. In the case of the High Luminosity upgrade of the LHC, the luminosity is raised by…

Point tracking aims to identify the same physical point across video frames and serves as a geometry-aware representation of motion. This representation supports a wide range of applications, from robotics to augmented reality, by enabling…

In many applications, a large number of features are collected with the goal to identify a few important ones. Sometimes, these features lie in a metric space with a known distance matrix, which partially reflects their co-importance…

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as…

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…

Track reconstruction in high track multiplicity environments at current and future high rate particle physics experiments is a big challenge and very time consuming. The search for track seeds and the fitting of track candidates are usually…

Recurrent neural networks (RNNs) are a widely used tool for modeling sequential data, yet they are often treated as inscrutable black boxes. Given a trained recurrent network, we would like to reverse engineer it--to obtain a quantitative,…

Accurately determining a change in protein binding affinity upon mutations is important for the discovery and design of novel therapeutics and to assist mutagenesis studies. Determination of change in binding affinity upon mutations…