Related papers: STRAW: A Stress-Aware WL-Based Read Reclaim Techni…
As memory technologies continue to shrink and memory error rates increase, the demand for stronger reliability becomes increasingly critical. Fine-grain memory replication has emerged as an appealing approach to improving memory fault…
Maintaining benefits of CMOS technology scaling is becoming challenging due to increased manufacturing complexities and unwanted passive power dissipations. This is particularly challenging in SRAM, where manufacturing precision and leakage…
Machine learning algorithms, such as Support Vector Machine (SVM) and Deep Neural Network (DNN), have gained a lot of interests recently. When training a machine learning algorithm, randomly shuffle all the training data can improve the…
Although we may be at the end of Moore's law, lowering chip power consumption is still the primary driving force for the designers. To enable low-power operation, we propose a resonant energy recovery static random access memory (SRAM). We…
Passive crossbar arrays based upon memristive devices, at crosspoints, hold great promise for the future high-density and non-volatile memories. The most significant challenge facing memristive device based crossbars today is the problem of…
Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as…
Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input…
Sparse recovery Space-time Adaptive Processing (STAP) can reduce the requirements of clutter samples, and suppress clutter effectively using limited training samples for airborne radar. The whole angle-Doppler plane is discretized into…
While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and…
In this paper we analyze the influence that lower layers (file system, OS, SSD) have on HDFS' ability to extract maximum performance from SSDs on the read path. We uncover and analyze three surprising performance slowdowns induced by lower…
Solid-State Drives (SSDs) have significant performance advantages over traditional Hard Disk Drives (HDDs) such as lower latency and higher throughput. Significantly higher price per capacity and limited lifetime, however, prevents…
This paper presents a model of NAND flash SSD utilization and write amplification when the ATA/ATAPI SSD Trim command is incorporated into object-based storage under a variety of user workloads, including a uniform random workload with…
Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we…
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this…
Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…
Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches often demand substantial computational resources, creating…
The use of Dynamic Random Access Memory (DRAM) for storing Machine Learning (ML) models plays a critical role in accelerating ML inference tasks in the next generation of communication systems. However, periodic refreshment of DRAM results…
Safeguarding intellectual property and preventing potential misuse of AI-generated images are of paramount importance. This paper introduces a robust and agile plug-and-play watermark detection framework, dubbed as RAW. As a departure from…
Neural document rerankers are extremely effective in terms of accuracy. However, the best models require dedicated hardware for serving, which is costly and often not feasible. To avoid this serving-time requirement, we present a method of…