Related papers: TIDAL: Recovering Temporal Phase for Cloud Block S…
This study proposes a computationally efficient method for optimizing multi-zone thermostatically controlled loads (TCLs) by leveraging dimensionality reduction through an auto-encoder. We develop a multi-task learning framework to jointly…
Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…
Developing optimized restoration strategies for power distribution systems (PDSs) is critical to enhancing resilience. Prior knowledge of customer interruption cost (CIC) and load restoration behaviors, particularly cold load pickup (CLPU),…
LLM-for-time series (TS) methods typically treat time shallowly, injecting positional or prompt-based cues once at the input of a largely frozen decoder, which limits temporal reasoning as this information degrades through the layers. We…
Industries are considering the adoption of cloud and edge computing for real-time applications due to current improvements in network latencies and the advent of Fog and Edge computing. Current cloud paradigms are not designed for real-time…
Due to the skewed scaling of interconnect versus cell delay in modern technology nodes, placement with buffer porosity (i.e., cell density) awareness is essential for timing closure in physical synthesis flows. However, existing approaches…
Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous…
Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive (AR) models, offering better hardware utilization and bidirectional context through parallel block-level decoding. However, as dLLMs…
Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…
Unexpected loads in Cloud data centers may trigger overloaded situation and performance degradation. To guarantee system performance, cloud computing environment is required to have the ability to handle overloads. The existing approaches,…
Shared memory emulation can be used as a fault-tolerant and highly available distributed storage solution or as a low-level synchronization primitive. Attiya, Bar-Noy, and Dolev were the first to propose a single-writer, multi-reader…
The demand for efficient machine learning (ML) accelerators is growing rapidly, driving the development of novel computing concepts such as resistive random access memory (RRAM)-based tiled computing-in-memory (CIM) architectures. CIM…
As computing demand and memory footprint of deep learning applications accelerate, clusters of cores sharing local (L1) multi-banked memory are widely used as key building blocks in large-scale architectures. When the cluster's core count…
Modern LLM serving systems confront inefficient GPU utilization due to the fundamental mismatch between compute-intensive prefill and memory-bound decode phases. While current practices attempt to address this by organizing these phases…
Eliminating duplicate data in primary storage of clouds increases the cost-efficiency of cloud service providers as well as reduces the cost of users for using cloud services. Existing primary deduplication techniques either use inline…
Industry 4.0 has brought numerous advantages, such as increasing productivity through automation. However, it also presents major cybersecurity issues such as cyberattacks affecting industrial processes. Federated Learning (FL) combined…
Place Recognition enables the estimation of a globally consistent map and trajectory by providing non-local constraints in Simultaneous Localisation and Mapping (SLAM). This paper presents Locus, a novel place recognition method using 3D…
Vehicular fog computing (VFC) is a promising paradigm for reducing the computation burden of vehicles, thus supporting delay-sensitive services in next-generation transportation networks. However, traditional VFC schemes rely on radio…
Multi-agent LLM applications organize execution in synchronized rounds where a central scheduler gathers outputs from all agents and redistributes the combined context. This All-Gather communication pattern creates massive KV Cache…
Distributed systems are critical to reliable and scalable computing; however, they are complicated in nature and prone to bugs. To modularly manage this complexity, network middleware has been traditionally built in layered stacks of…