Related papers: Sparse Vector Transmission: An Idea Whose Time Has…

Current distributed representations of words show little resemblance to theories of lexical semantics. The former are dense and uninterpretable, the latter largely based on familiar, discrete classes (e.g., supersenses) and relations (e.g.,…

We consider the transmission of short packets over a bidirectional communication link where multiple devices, e.g., sensors and actuators, exchange small-data payloads with a base station equipped with a large antenna array. Using results…

Real-world problems often involve complex and unstructured sets of measurements, which occur when sensors are sparsely placed in either space or time. Being able to model this irregular spatiotemporal data and extract meaningful forecasts…

Wireless power transfer (WPT) technologies are becoming ubiquitous, but unlike wire technologies, they do not allow efficient energy transfer through barely transparent barriers. The proposed solutions to this issue rely on resonantly…

To strike a balance between energy efficiency and data quality control, this paper proposes a sensor censoring scheme for distributed sparse signal recovery via compressive-sensing based wireless sensor networks. In the proposed approach,…

The first generation of wireless sensor nodes have constrained energy resources and computational power, which discourages applications to process any task other than measuring and transmitting towards a central server. However, nowadays,…

Video compression aims to maximize reconstruction quality with minimal bitrates. Beyond standard distortion metrics, perceptual quality and temporal consistency are also critical. However, at ultra-low bitrates, traditional end-to-end…

In this work, we propose a sparse transformer architecture that incorporates prior information about the underlying data distribution directly into the transformer structure of the neural network. The design of the model is motivated by a…

Convolutional network are the de-facto standard for analysing spatio-temporal data such as images, videos, 3D shapes, etc. Whilst some of this data is naturally dense (for instance, photos), many other data sources are inherently sparse.…

This paper provides a novel approach for finding sparse state-space realizations of linear systems (e.g., controllers). Sparse controllers are commonly used in distributed control, where a controller is synthesized with some sparsity…

The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior…

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

Accurate vehicular sensing is a basic and important operation in autonomous driving. Unfortunately, the existing techniques have their own limitations. For instance, the communication-based approach (e.g., transmission of GPS information)…

An efficient communication mechanism forms the backbone for any multi-robot system to achieve fruitful collaboration and coordination. Limitation in the existing asynchronous transmission based strategies in fast dissemination and…

Backscatter communication is a hot candidate for future IoT systems. It offers the possibility for connectivity with tiny amounts of energy that can be easily obtained from energy harvesting. This is possible as backscatter devices do not…

This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. The primary goal is to learn the few causal features of a high-dimensional dataset based on noisy observations…

Due to the limited number of traditional orthogonal pilots, pilot collision will severely degrade the performance of contention-based grant-free transmission. To alleviate the pilot collision and exploit the spatial degree of freedom as…

Visual servoing enables robots to precisely position their end-effector relative to a target object. While classical methods rely on hand-crafted features and thus are universally applicable without task-specific training, they often…

Wireless power transfer (WPT) is expected to be a technology reshaping the landscape of low-power applications such as the Internet of Things, machine-to-machine communications and radio frequency identification networks. Although there has…