Related papers: Mitigating Interference of Microservices with a Sc…
Recommender systems are enablers of personalized content delivery, and therefore revenue, for many large companies. In the last decade, deep learning recommender models (DLRMs) are the de-facto standard in this field. The main bottleneck in…
Multiple-input multiple-output (MIMO) technology has been regarded as one of the most important technologies to enable emerging applications in current and next generation wireless communication systems, for which signal detection methods…
Multi-cloud environments enable a cost-efficient scaling of cloud-native applications across geographically distributed virtual nodes with different pricing models. In this context, the resource fragmentation caused by frequent changes in…
Spatial query and analysis results are often directly applied to decision-making processes such as facility location, proximity resource discovery, accessibility analysis, and risk assessment. Therefore, the efficiency of underlying spatial…
Recent advances in cross-prompt automated essay scoring (AES) typically train models jointly on all source prompts, often requiring additional access to unlabeled target prompt essays simultaneously. However, using all sources is suboptimal…
Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks, in which adversaries bypass safeguards with crafted input prompts, play a central role in…
With the growing demand for latency-critical and computation-intensive Internet of Things (IoT) services, the IoT-oriented network architecture, mobile edge computing (MEC), has emerged as a promising technique to reinforce the computation…
As an increasing number of businesses becomes powered by machine-learning, inference becomes a core operation, with a growing trend to be offered as a service. In this context, the inference task must meet certain service-level objectives…
Deep Learning Recommendation Models (DLRMs) have become increasingly popular and prevalent in today's datacenters, consuming most of the AI inference cycles. The performance of DLRMs is heavily influenced by available bandwidth due to their…
Evacuation planning is a crucial part of disaster management. However, joint optimization of its two essential components, routing and scheduling, with objectives such as minimizing average evacuation time or evacuation completion time, is…
Memory system is often the main bottleneck in chipmultiprocessor (CMP) systems in terms of latency, bandwidth and efficiency, and recently additionally facing capacity and power problems in an era of big data. A lot of research works have…
In this paper, we propose a novel transmissive reconfigurable intelligent surface (TRIS) transceiver-driven cooperative integrated sensing, computing, and communication (ISCC) network to meet the requirement for a diverse network with low…
Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM…
Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…
Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…
The rapid advancement of Large Language Models (LLMs) has revolutionized various aspects of human life, yet their immense computational and energy demands pose significant challenges for efficient inference. The memory wall, the growing…
We investigate a reconfigurable intelligent surface (RIS) aided wireless surveillance system. In this system, a monitor not only receives signal from suspicious transmitter via a RIS-enhanced legitimate surveillance (LS) link but also…
The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for comprehensive understanding of scaling properties. This is challenged by: 1) the…
This study suggests a new strategy for improving congestion control by deploying Long Short-Term Memory (LSTM) networks. LSTMs are recurrent neural networks (RNN), that excel at capturing temporal relationships and patterns in data.…
Antimicrobial stewardship (AMS) is critical in pediatric intensive care units (PICUs), where diagnostic uncertainty often drives broad-spectrum antibiotic use, increasing antimicrobial resistance and potential long-term harms. Machine…