Related papers: SquiggleFilter: An Accelerator for Portable Virus …

The SciBath-768 detector is a prototype neutral particle detector offering high-precision reconstruction of neutrino and neutron events. It consists of a three dimensional grid of 768 wavelength-shifting fibers immersed in 82 liters of…

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible…

Deep convolutional neural networks (CNNs) obtain outstanding results in tasks that require human-level understanding of data, like image or speech recognition. However, their computational load is significant, motivating the development of…

Quantum fluctuations constitute the primary noise barrier limiting cavity-based axion dark matter searches. In an experiment designed to mimic a real axion search, we employ a quantum-enhanced sensing technique to detect a synthetic…

Hardware accelerators are essential for achieving low-latency, energy-efficient inference in edge applications like image recognition. Spiking Neural Networks (SNNs) are particularly promising due to their event-driven and temporally sparse…

The AION project has built a tabletop prototype of a single-photon long-baseline atom interferometer using the 87Sr clock transition - a type of quantum sensor designed to search for dark matter and gravitational waves. Our prototype…

The CAEN V1751 is a new generation of Waveform Digitizer recently introduced by CAEN SpA. It features 8 Channels per board, 10 bit, 1 GS/s using Flash ADCs Waveform Digitizers (or 4 channels at 2 GS/s in Dual Edge Sampling mode) with…

Currently, radiobiology experiments using heavy ions at GANIL(Grand Accelerateur National d Ions Lourds) are conducted under the supervision of the CIMAP (Center for research on Ions, MAterials and Photonics). In this context, a new beam…

Accurate real-time object detection enhances the safety of advanced driver-assistance systems, making it an essential component in driving scenarios. With the rapid development of deep learning technology, CNN-based YOLO real-time object…

COFFEE series is a HVCMOS pixel sensor using the advanced 55 nm process, currently being developed for the Upstream Pixel (UP) tracker of the LHCb Upgrade II. To ensure that COFFEE will be able to handle the particle hit rates at UP…

Spiking neural networks (SNNs) recently gained momentum due to their low-power multiplication-free computing and the closer resemblance of biological processes in the nervous system of humans. However, SNNs require very long spike trains…

Motivation: Seed filtering is critical in DNA read mapping, a process where billions of DNA fragments (reads) sampled from a donor are mapped onto a reference genome to identify genomic variants of the donor. Read mappers 1) quickly…

Scintillation light generated as charged particles traverse large liquid argon detectors adds valuable information to studies of weakly-interacting particles. This paper uses both laboratory measurements and cosmic ray data from the Blanche…

We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequence length from 729 to 81 tokens, significantly reducing…

For Edge AI applications, deploying online learning and adaptation on resource-constrained embedded devices can deal with fast sensor-generated streams of data in changing environments. However, since maintaining low-latency and…

Continual learning, the ability to acquire and transfer knowledge through a models lifetime, is critical for artificial agents that interact in real-world environments. Biological brains inherently demonstrate these capabilities while…

Computing-in-Memory architectures based on non-volatile emerging memories have demonstrated great potential for deep neural network (DNN) acceleration thanks to their high energy efficiency. However, these emerging devices can suffer from…

Liquid Argon Time Projection Chambers (LArTPCs) have been selected for the future long-baseline Deep Underground Neutrino Experiment (DUNE). To allow LArTPCs to operate in the high-multiplicity near detector environment of DUNE, a new…

This paper presents a lightweight K-Means anomaly detection model and a distributed model-sharing workflow designed for resource-constrained microcontrollers (MCUs). Using real power measurements from a mini-fridge appliance, the system…

Object detection has made impressive progress in recent years with the help of deep learning. However, state-of-the-art algorithms are both computation and memory intensive. Though many lightweight networks are developed for a trade-off…