Related papers: SLA-Aware Distributed LLM Inference Across Device-…
LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…
The heterogeneity of use cases that next-generation wireless systems need to support calls for flexible and programmable networks that can autonomously adapt to the application requirements. Specifically, traffic flows that support critical…
5G promises enhanced performance-not only in bandwidth and capacity, but also latency and security. Its ultra-reliable low-latency configuration targets round-trip times below 1 ms, while optional security controls extend protection across…
Network slicing enables multiple virtual networks to be instantiated and customized to meet heterogeneous use case requirements over 5G and beyond network deployments. However, most of the solutions available today face scalability issues…
Edge intelligence delivers low-latency inference, yet most edge analytics remain hard-coded and must be redeployed as conditions change. When data patterns shift or new questions arise, engineers often need to write new scripts and push…
Network slicing has been introduced in 5G/6G networks to address the challenge of providing new services with different and sometimes conflicting requirements. With SDN and NFV technologies being used in the design of 5G and 6G wireless…
Industries are recently considering the adoption of cloud computing for hosting safety critical applications. However, the use of multicore processors usually adopted in the cloud introduces temporal anomalies due to contention for shared…
Recent advancements in wireless technologies towards the next-generation cellular networks have brought a new era that made it possible to apply cellular technology on traditionally-wired networks with tighter requirements, such as…
Following state-of-the-art research results, which showed the potential for significant performance gains by applying AI/ML techniques in the cellular Radio Access Network (RAN), the wireless industry is now broadly pushing for the adoption…
Dynamic spectrum slicing is a critical enabler for 6G Radio Access Networks (RANs), allowing the coexistence of heterogeneous services. However, optimizing resource allocation in dense, interference-limited deployments remains challenging…
A systematic understanding of Apple Silicon is lacking in the current landscape of hardware efficiency; research focus is largely centered on accelerating GPUs for large-scale training or inference on CUDA devices. This paper investigates…
With the advancement of Artificial Intelligence (AI) towards multiple modalities (language, vision, speech, etc.), multi-modal models have increasingly been used across various applications (e.g., visual question answering or image…
Sixth-generation (6G) radio access networks (RANs) must enforce strict service-level agreements (SLAs) for heterogeneous slices, yet sudden latency spikes remain difficult to diagnose and resolve with conventional deep reinforcement…
The ever increasing number of connected devices and of new and heterogeneous mobile use cases implies that 5G cellular systems will face demanding technical challenges. For example, Ultra-Reliable Low-Latency Communication (URLLC) and…
Modern power grids face an acute mismatch between where data is generated and where it can be processed: protection relays, EV (Electric Vehicle) charging, and distributed renewables demand millisecond analytics at the edge, while…
Split-learning (SL) has recently gained popularity due to its inherent privacy-preserving capabilities and ability to enable collaborative inference for devices with limited computational power. Standard SL algorithms assume an ideal…
Cloud radio access network (C-RAN) architecture is a new mobile network architecture that enables cooperative baseband processing and information sharing among multiple cells and achieves high adaptability to nonuniform traffic by…
Large language models (LLMs) require substantial computational resources, leading to significant carbon emissions and operational costs. Although training is energy-intensive, the long-term environmental burden arises from inference,…
Distributed machine learning (ML) over wireless networks hinges on accurate channel state information (CSI) and efficient exchange of high-dimensional model updates. These demands are governed by channel coherence time and bandwidth, which…
Mobile devices and the immense amount and variety of data they generate are key enablers of machine learning (ML)-based applications. Traditional ML techniques have shifted toward new paradigms such as federated (FL) and split learning (SL)…