Related papers: LIMO: Low-Power In-Memory-Annealer and Matrix-Mult…
In this work, two problems associated with a downlink multi-user system are considered with the aid of intelligent reflecting surface (IRS): weighted sum-rate maximization and weighted minimal-rate maximization. For the first problem, a…
Stacked intelligent metasurface (SIM) is an emerging design that consists of multiple layers of metasurfaces. A SIM enables holographic multiple-input multiple-output (HMIMO) precoding in the wave domain, which results in the reduction of…
Simulated annealing (SA) attracts more attention among classical heuristic algorithms because the solution of the combinatorial optimization problem can be naturally mapped to the ground state of the Ising Hamiltonian. However, in practical…
The rapid scaling of models has led to prohibitively high training and fine-tuning costs. A major factor accounting for memory consumption is the widespread use of stateful optimizers (e.g., Adam), which maintain auxiliary information of…
With IoT systems' increasing scale and complexity, maintenance of a large number of nodes using stationary devices is becoming increasingly difficult. Hence, mobile devices are being employed that can traverse through a set of target…
This paper investigates a communication-efficient split learning (SL) over multiple-input multiple-output (MIMO) communication system. In particular, we mathematically decompose the inter-layer connection of a neural network (NN) to a…
Pixel antenna is a promising technology to enhance the wireless communication data rate by adaptively reconfiguring each antenna's radiation pattern via a so-called antenna coding technique which controls the states of switches connected to…
Large language models (LLMs) with mixture-of-experts (MoE) architectures achieve remarkable scalability by sparsely activating a subset of experts per token, yet their frequent expert switching creates memory bandwidth bottlenecks that…
The high computational complexity and energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. However, mobile edge computing (MEC) makes it possible to solve this problem.…
Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, but data not deemed important during training is forgotten,…
Large multiple-input multiple-output (MIMO) appears in massive multi-user MIMO and randomly-spread code-division multiple access (CDMA)-based wireless systems. In order to cope with the excessively high complexity of optimal data detection…
Artificial intelligence (AI) models are currently driven by a significant upscaling of their complexity, with massive matrix-multiplication workloads representing the major computational bottleneck. In-memory computing (IMC) architectures…
Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models…
Holographic multiple-input multiple-output (HMIMO) is a potential technique for improving spectral efficiency (SE) while maintaining low hardware cost and power consumption. Although conventional alternating optimization (AO) methods are…
Processing-in-Memory (PIM) architectures offer promising solutions for efficiently handling AI applications in energy-constrained edge environments. While traditional PIM designs enhance performance and energy efficiency by reducing data…
Compute-in-memory (CIM) accelerators for spiking neural networks (SNNs) are promising solutions to enable $\mu$s-level inference latency and ultra-low energy in edge vision applications. Yet, their current lack of flexibility at both the…
The human brain simultaneously optimizes synaptic weights and topology by growing, pruning, and strengthening synapses while performing all computation entirely in memory. In contrast, modern artificial-intelligence systems separate weight…
Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…
Stacked Intelligent Metasurfaces (SIM) have emerged as a revolutionary architecture for next-generation wireless communications, offering wave-domain signal processing capabilities with significantly reduced hardware complexity compared to…
Extra-large scale MIMO (XL-MIMO) is a key technology for meeting sixth-generation (6G) requirements for high-rate connectivity and uniform quality of service (QoS); however, its deployment is challenged by the prohibitive complexity of…