Related papers: HARP: Hadamard-Domain Write-and-Verify for Noise-R…
This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple…
State-of-the-art techniques for addressing scaling-related main memory errors identify and repair bits that are at risk of error from within the memory controller. Unfortunately, modern main memory chips internally use on-die error…
Human Activity Recognition (HAR) such as fall detection has become increasingly critical due to the aging population, necessitating effective monitoring systems to prevent serious injuries and fatalities associated with falls. This study…
Binary and sparse ternary weights in neural networks enable faster computations and lighter representations, facilitating their use on edge devices with limited computational power. Meanwhile, vanilla RNNs are highly sensitive to changes in…
This brief presents a novel IEEE 802.16e (WiMAX) based decoder that performs close to the 5G code but without the expensive hardware re-development cost. The design uses an extension of the existing WiMAX parity check code to reduce the…
Speaker Verification (SV) systems involve mainly two individual stages: feature extraction and classification. In this paper, we explore these two modules with the aim of improving the performance of a speaker verification system under…
Non-Volatile Memory (NVM) cells are used in neuromorphic hardware to store model parameters, which are programmed as resistance states. NVMs suffer from the read disturb issue, where the programmed resistance state drifts upon repeated…
Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce…
We introduce HiFi-HARP, a large-scale dataset of 7th-order Higher-Order Ambisonic Room Impulse Responses (HOA-RIRs) consisting of more than 100,000 RIRs generated via a hybrid acoustic simulation in realistic indoor scenes. HiFi-HARP…
Aims: Even the most-precise radial-velocity instruments gather high-resolution spectra that present systematic errors that a data reduction pipeline cannot identify and correct for efficiently. In this paper, we aim at improving the…
Nowadays, machine learning based Automatic Speech Recognition (ASR) technique has widely spread in smartphones, home devices, and public facilities. As convenient as this technology can be, a considerable security issue also raises -- the…
In this paper, we study the lossless analog compression for i.i.d. nonsingular signals via the polarization-based framework. We prove that for nonsingular source, the error probability of maximum a posteriori (MAP) estimation polarizes…
Architectures that incorporate Computing-in-Memory (CiM) using emerging non-volatile memory (NVM) devices have become strong contenders for deep neural network (DNN) acceleration due to their impressive energy efficiency. Yet, a significant…
Audio-visual speech recognition (AVSR) provides a promising solution to ameliorate the noise-robustness of audio-only speech recognition with visual information. However, most existing efforts still focus on audio modality to improve…
This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions. HAWP utilizes a parsimonious Holistic Attraction (HAT) field…
Visual Place Recognition (VPR) enables coarse localization by comparing query images to a reference database of geo-tagged images. Recent breakthroughs in deep learning architectures and training regimes have led to methods with improved…
General matrix-vector multiplication (GeMV) remains a critical latency bottleneck in large language model (LLM) inference, even with quantized low-bit models. Processing-Using-DRAM (PUD), an analog in-DRAM computing technique, has the…
We investigate the problems of 1-D and 2-D signal recovery from subsampled Hadamard measurements using Haar wavelet sparsity prior. These problems are of interest in, e.g., computational imaging applications relying on optical multiplexing…
We present an architecture-level hardware-to-logical-to-decoder execution stack for hybrid continuous-variable and discrete-variable quantum error correction in LiDMaS+. Provider-native records are normalized into a single decoder IO…
A trend towards energy-efficiency, security and privacy has led to a recent focus on deploying DNNs on microcontrollers. However, limits on compute and memory resources restrict the size and the complexity of the ML models deployable in…