Related papers: SPLENDAQ: A Detector-Agnostic Data Acquisition Sys…
Time series forecasting is essential in a wide range of real world applications. Recently, frequency-domain methods have attracted increasing interest for their ability to capture global dependencies. However, when applied to non-stationary…
The upcoming PandaX-xT experiment will deploy over 3,000 readout channels operating at a 500 MSa/s sampling rate, generating a sustained data bandwidth up to 1.6 GB/s. To meet this demanding requirement, we present AURORA, a…
Fast, incremental evolution of physics instrumentation raises the question of efficient software abstraction and transferability of algorithms across similar technologies. This contribution aims to provide an answer by introducing Track…
High-throughput physics experiments require efficient and increasingly complex real-time processing. This paper presents a modular, software-defined platform combining high-bandwidth PCIe digitizers with consumer GPUs to achieve continuous,…
Spiking Neural Networks (SNNs), with their brain-inspired spatiotemporal dynamics and spike-driven computation, have emerged as promising energy-efficient alternatives to Artificial Neural Networks (ANNs). However, existing SNNs typically…
Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft…
Automatic event detection from time series signals has wide applications, such as abnormal event detection in video surveillance and event detection in geophysical data. Traditional detection methods detect events primarily by the use of…
Achieving optimal semantic segmentation with frame-based vision sensors poses significant challenges for real-time systems like UAVs and self-driving cars, which require rapid and precise processing. Traditional frame-based methods often…
Event-driven sensors such as LiDAR and dynamic vision sensor (DVS) have found increased attention in high-resolution and high-speed applications. A lot of work has been conducted to enhance recognition accuracy. However, the essential topic…
Time series anomaly detection plays a vital role in a wide range of applications. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets,…
Identification and quantification of condition-specific transcripts using RNA-Seq is vital in transcriptomics research. While initial efforts using mathematical or statistical modeling of read counts or per-base exonic signal have been…
This paper introduces a novel framework for optimizing observer-based soft sensors through dynamic causality analysis. Traditional approaches to sensor selection often rely on linearized observability indices or statistical correlations…
SGD does not produce robust results on datasets with label noise. Because the gradients calculated according to the losses of the noisy samples cause the optimization process to go in the wrong direction. In this paper, as an alternative to…
The ngdp framework is intended to provide a base for the data acquisition (DAQ) system software. The ngdp's design key features are: high modularity and scalability; usage of the kernel context (particularly kernel threads) of the operating…
Speculative Decoding (SD) accelerates large language model inference by employing a small draft model to generate predictions, which are then verified by a larger target model. The effectiveness of SD hinges on the alignment between these…
Submersible Buoy (SB) is an important apparatus capable of long-term, fixed-point, continuous and multi-directional measurement of acoustic signals and hydrological environment monitoring in the harsh marine environment, providing important…
Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform…
The field of machine learning for drug discovery is witnessing an explosion of novel methods. These methods are often benchmarked on simple physicochemical properties such as solubility or general druglikeness, which can be readily…
This paper proposes a non-intrusive, declarative, dynamic and transparent system called `HiQ` to track Python program runtime information without compromising on the run-time system performance and losing insight. HiQ can be used for…
Although CMS will not start operation for several years, many subdetector groups have active testbeam programs involving final or near-final electronics. The high-bandwidth electronics require the development of new DAQ systems including…