Related papers: TSNet-SAC: Leveraging Transformers for Efficient T…
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention…
Mobile edge computing (MEC) and terahertz (THz)enabled unmanned aerial vehicle (UAV) communication systems are gaining significant attention for improving user service delays in future mobile networks. This article introduces a novel…
In the realm of neural architecture design, achieving high performance is largely reliant on the manual expertise of researchers. Despite the emergence of Neural Architecture Search (NAS) as a promising technique for automating this…
Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited…
Optimization algorithms for wireless systems play a fundamental role in improving their performance and efficiency. However, it is known that the complexity of conventional optimization algorithms in the literature often exponentially…
Edge computing decentralizes computing resources, allowing for novel applications in domains such as the Internet of Things (IoT) in healthcare and agriculture by reducing latency and improving performance. This decentralization is achieved…
Recently, a new trend of exploring sparsity for accelerating neural network training has emerged, embracing the paradigm of training on the edge. This paper proposes a novel Memory-Economic Sparse Training (MEST) framework targeting for…
The existing computation and communication (2C) optimization schemes for vehicular edge computing (VEC) networks mainly focus on the physical domain without considering the influence from the social domain. This may greatly limit the…
Mobile edge computing (MEC) is a promising technique for providing low-latency access to services at the network edge. The services are hosted at various types of edge nodes with both computation and communication capabilities. Due to the…
As a consequence of the COVID-19 pandemic, the demand for telecommunication for remote learning/working and telemedicine has significantly increased. Mobile Edge Caching (MEC) in the 6G networks has been evolved as an efficient solution to…
Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…
Emerging mobile virtual reality (VR) systems will require to continuously perform complex computer vision tasks on ultra-high-resolution video frames through the execution of deep neural networks (DNNs)-based algorithms. Since…
Vehicular crowdsensing is anticipated to become a key catalyst for data-driven optimization in the Intelligent Transportation System (ITS) domain. Yet, the expected growth in massive Machine-type Communication (mMTC) caused by…
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…
To overcome devices' limitations in performing computation-intense applications, mobile edge computing (MEC) enables users to offload tasks to proximal MEC servers for faster task computation. However, current MEC system design is based on…
In the era of 6G, with compelling visions of intelligent transportation systems and digital twins, remote surveillance is poised to become a ubiquitous practice. Substantial data volume and frequent updates present challenges in wireless…
Task-Oriented Semantic Communication (TOSC) has been regarded as a promising communication framework, serving for various Artificial Intelligence (AI) task driven applications. The existing TOSC frameworks focus on extracting the full…
With the development of artificial intelligence integrated next-generation communication networks, mobile users (MUs) are increasingly demanding the efficient processing of computation-intensive and latency-sensitive tasks. However,…
In the context of 6th generation (6G) networks, vehicular edge computing (VEC) is emerging as a promising solution to let battery-powered ground vehicles with limited computing and storage resources offload processing tasks to more powerful…
We present a new algorithm, Cross-Episodic Curriculum (CEC), to boost the learning efficiency and generalization of Transformer agents. Central to CEC is the placement of cross-episodic experiences into a Transformer's context, which forms…