Related papers: LSCHC: Layered Static Context Header Compression f…
The Session Initiation Protocol (SIP) is an application-layer control protocol for creating, modifying and terminating multimedia sessions. An open issue is the control of overload that occurs when a SIP server lacks sufficient CPU and…
Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…
Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less than 4-bits) performs…
Although the lightweight Vision Transformer has significantly advanced image super-resolution (SR), it faces the inherent challenge of a limited receptive field due to the window-based self-attention modeling. The quadratic computational…
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,…
Communication overhead is one of the major performance bottlenecks in large-scale distributed computing systems, in particular for machine learning applications. Conventionally, compression techniques are used to reduce the load of…
Locality-sensitive hashing (LSH) based frameworks have been used efficiently to select weight vectors in a dense hidden layer with high cosine similarity to an input, enabling dynamic pruning. While this type of scheme has been shown to…
We propose sandwiched video compression -- a video compression system that wraps neural networks around a standard video codec. The sandwich framework consists of a neural pre- and post-processor with a standard video codec between them.…
Spatially-coupled (SC) codes are a class of low-density parity-check (LDPC) codes that have excellent performance thanks to the degrees of freedom they offer. An SC code is designed by partitioning a base matrix into components, the number…
Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several…
We propose a novel, lightweight supervised dictionary learning framework for text classification based on data compression and representation. This two-phase algorithm initially employs the Lempel-Ziv-Welch (LZW) algorithm to construct a…
Recently, 3D SSDs are widely adopted in PCs, data centers, and cloud storage systems. To increase capacity, high bit-density cells, such as Triple-Level Cell (TLC), are utilized within 3D SSDs. However, due to the inferior performance of…
Homomorphic Encryption (HE) is one of the most promising security solutions to emerging Machine Learning as a Service (MLaaS). Leveled-HE (LHE)-enabled Convolutional Neural Networks (LHECNNs) are proposed to implement MLaaS to avoid large…
Ultra-reliable low-latency vehicular communications (URLLC) require sufficient physical-layer (PHY) compute headroom at the network edge, where roadside units (RSUs) and compact next-generation base stations (gNBs) must meet strict timing…
Memory-intensive applications, such as in-memory databases, caching systems and key-value stores, are increasingly demanding larger main memory to fit their working sets. Conventional swapping can enlarge the memory capacity by paging out…
Multi-antenna coded caching combines a global caching gain, proportional to the total cache size in the network, with an additional spatial multiplexing gain that stems from multiple transmitting antennas. However, classic centralized coded…
This paper deals with the routing protocols for distributed wireless sensor networks. The conventional protocols for WSNs like Low Energy adaptive Clustering Hierarchy (LEACH), Stable Election Protocol (SEP), Threshold Sensitive Energy…
We study the problem of uplink compression for cell-free multi-input multi-output networks with limited fronthaul capacity. In compress-forward mode, remote radio heads (RRHs) compress the received signal and forward it to a central unit…
WiFi-enabled Internet-of-Things (IoT) devices are evolving from mere communication devices to sensing instruments, leveraging Channel State Information (CSI) extraction capabilities. Nevertheless, resource-constrained IoT devices and the…
Software defined networks offer global visibility, yet centralized control loops are too slow for transient congestion and bursty traffic dynamics. Existing learned traffic control schemes often rely on offline training, making them fragile…