Related papers: UPR: Deadlock-Free Dynamic Network Reconfiguration…
Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores…
With the high development of wireless communication techniques, it is widely used in various fields for convenient and efficient data transmission. Different from commonly used assumption of the time-invariant wireless channel, we focus on…
Route planning is important in transportation. Existing works focus on finding the shortest path solution or using metrics such as safety and energy consumption to determine the planning. It is noted that most of these studies rely on prior…
Deep Reinforcement Learning (DRL) has become a popular method for solving control problems in power systems. Conventional DRL encourages the agent to explore various policies encoded in a neural network (NN) with the goal of maximizing the…
This paper considers methods for delivering ultra reliable low latency communication (URLLC) to enable mission-critical Internet of Things (IoT) services in wireless environments with unknown channel distribution. The methods rely upon the…
Emerging reconfigurable optical communication technologies allow to enhance datacenter topologies with demand-aware links optimized towards traffic patterns. This paper studies the algorithmic problem of jointly optimizing topology and…
The utilization of the experience replay mechanism enables agents to effectively leverage their experiences on several occasions. In previous studies, the sampling probability of the transitions was modified based on their relative…
Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices. Compared with conventional methods, the recently developed dynamic…
We propose UDP, the first training-free parser for Universal Dependencies (UD). Our algorithm is based on PageRank and a small set of head attachment rules. It features two-step decoding to guarantee that function words are attached as leaf…
Flexible duplex is proposed to adapt to the channel and traffic asymmetry for future wireless networks. In this paper, we propose two novel algorithms within the flexible duplex framework for joint uplink and downlink resource allocation in…
We initiate the study of graph algorithms in the streaming setting on massive distributed and parallel systems inspired by practical data processing systems. The objective is to design algorithms that can efficiently process evolving graphs…
This study considers multiple reconfigurable intelligent surfaces (RISs)-aided multiuser downlink systems with the goal of jointly optimizing the transmitter precoding and RIS phase shift matrix to maximize spectrum efficiency. Unlike prior…
One of the main novelties in 5G is the flexible Time Division Duplex (TDD) frame, which allows adaptation to the latency requirements. However, this flexibility is not sufficient to support heterogeneous latency requirements, in which…
This letter is concerned with power control for a ultra-reliable and low-latency communications (URLLC) enabled unmanned aerial vehicle (UAV) system incorporated with deep neural network (DNN) based channel estimation. Particularly, we…
Neural circuits are able to perform computations under very diverse conditions and requirements. The required computations impose clear constraints on their fine-tuning: a rapid and maximally informative response to stimuli in general…
Future wireless networks will be characterized by heterogeneous traffic requirements. Such requirements can be low-latency or minimum-throughput. Therefore, the network has to adjust to different needs. Usually, users with low-latency…
Dynamic Time-division duplex (TDD) can provide efficient and flexible splitting of the common wireless cellular resources between uplink (UL) and downlink (DL) users. In this paper, the UL/DL optimization problem is formulated as a…
Many optical circuit switched data center networks (DCN) have been proposed in the past to attain higher capacity and topology reconfigurability, though commercial adoption of these architectures have been minimal. One major challenge these…
With the rapid development of the e-commerce industry, the logistics network is experiencing unprecedented pressure. The traditional static routing strategy most time cannot tolerate the traffic congestion and fluctuating retail demand. In…
With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…