Related papers: AmpliconHunter2: a SIMD-Accelerated In-Silico PCR …
Conventional scanning tunneling microscopy (STM) is limited to a bandwidth of circa 1kHz around DC. Here, we develop, build and test a novel amplifier circuit capable of measuring the tunneling current in the MHz regime while simultaneously…
Long contexts improve capabilities of large language models but pose serious hardware challenges: compute and memory footprints grow linearly with sequence length. Particularly, the decoding phase continuously accesses massive KV cache,…
This paper presents an accuracy-enhanced Hybrid Temporal Computing (E-HTC) framework for ultra-low-power hardware accelerators with deterministic additions. Inspired by the recently proposed HTC architecture, which leverages pulse-rate and…
We introduce a high-throughput neural network accelerator that embeds most network layers directly in hardware, minimizing data transfer and memory usage while preserving a degree of flexibility via a small neural processing unit for the…
High-Level Synthesis (HLS) enables rapid prototyping of complex hardware designs by translating C or C++ code to low-level RTL code. However, the testing and evaluation of HLS designs still typically rely on slow RTL-level simulators that…
Hyperdimensional Computing (HDC) represents data using extremely high-dimensional, low-precision vectors, termed hypervectors (HVs), and performs learning and inference through lightweight, noise-tolerant operations. However, the high…
Computing with high-dimensional (HD) vectors, also referred to as $\textit{hypervectors}$, is a brain-inspired alternative to computing with scalars. Key properties of HD computing include a well-defined set of arithmetic operations on…
The Five-hundred-meter Aperture Spherical radio Telescope (FAST) has the largest aperture and a 19-beam L-band receiver, making it powerful for investigating the neutral hydrogen atomic gas (HI) in the universe. We present HiFAST…
Homomorphic encryption (HE) enables computation on encrypted data, and hence it has a great potential in privacy-preserving outsourcing of computations to the cloud. Hardware acceleration of HE is crucial as software implementations are…
The Accelerator Test Facility 2 (ATF2) is a scaled demonstrator system for final focus beam lines of linear high energy colliders. This paper describes the high resolution cavity beam position monitor (BPM) system, which is a part of the…
The Phase-II Upgrade of the ATLAS Muon Detector requires new electronics for the readout of the MDT drift tubes. The first processing stage, the Amplifier-Shaper-Discriminator (ASD), determines the performance of the readout for crucial…
Prompting and adapter tuning have emerged as efficient alternatives to fine-tuning (FT) methods. However, existing studies on speech prompting focused on classification tasks and failed on more complex sequence generation tasks. Besides,…
State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…
Synchrotron radiation light sources produce intense beam of X-ray with ultra-short pulse and nanosecond period. This of-fers the opportunities for the time resolution experiments. Achieving higher counting rate and faster arriving time is…
A 100um thick silicon detector with 1mm2 pad readout optimized for sub-nanosecond time resolution has been developed and tested. Coupled to a purposely developed amplifier based on SiGe HBT technology, this detector was characterized at the…
The rapid adoption of Large Language Models (LLMs) has driven a growing demand for efficient inference, particularly in latency-sensitive applications such as chatbots and personalized assistants. Unlike traditional deep neural networks,…
As the importance of Privacy-Preserving Inference of Transformers (PiT) increases, a hybrid protocol that integrates Garbled Circuits (GC) and Homomorphic Encryption (HE) is emerging for its implementation. While this protocol is preferred…
High-resolution volumetric imaging techniques, such as X-ray tomography and advanced microscopy, generate increasingly large datasets that challenge existing tools for efficient processing, segmentation, and interactive exploration. This…
Hybrid Homomorphic Encryption (HHE) combines symmetric key and homomorphic encryption to reduce ciphertext expansion crucial in client-server deployments of HE. Special symmetric ciphers, amenable to efficient HE evaluation, have been…
Hardware accelerators (HAs) are essential building blocks for fast and energy-efficient computing systems. Accelerator Quick Error Detection (A-QED) is a recent formal technique which uses Bounded Model Checking for pre-silicon verification…