Related papers: Embedding-Only Uplink for Onboard Retrieval Under …
End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants --…
Networks are one of the most powerful structures for modeling problems in the real world. Downstream machine learning tasks defined on networks have the potential to solve a variety of problems. With link prediction, for instance, one can…
Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into low-dimensional node-based feature representations that can be…
Large language models have recently pushed open domain question answering (ODQA) to new frontiers. However, prevailing retriever-reader pipelines often depend on multiple rounds of prompt level instructions, leading to high computational…
The increasing number of users leads to an increase in pilot overhead, and the limited pilot resources make it challenging to support all users using orthogonal pilots. By fully capturing the inherent physical characteristics of the…
Pinching-antenna systems (PASS) have recently attracted considerable attention owing to their capability of flexibly reconfiguring large-scale wireless channels. Motivated by this potential, we investigate the issue of joint localization…
Reflecting Surfaces (RSs) are being lately envisioned as an energy efficient solution capable of enhancing the signal coverage in cases where obstacles block the direct communication from Base Stations (BSs), especially at high frequency…
In this paper, we introduce an uplink optical wireless positioning system for indoor applications. This technique uses fingerprints based on the indoor optical wireless channel impulse response for localization. Exploiting the line of sight…
Place recognition is a fundamental task for robotic application, allowing robots to perform loop closure detection within simultaneous localization and mapping (SLAM), and achieve relocalization on prior maps. Current range image-based…
We apply contextualised word embeddings to lexical semantic change detection in the SemEval-2020 Shared Task 1. This paper focuses on Subtask 2, ranking words by the degree of their semantic drift over time. We analyse the performance of…
Representation learning of networks has witnessed significant progress in recent times. Such representations have been effectively used for classic network-based machine learning tasks like node classification, link prediction, and network…
According to the recent 3GPP decisions on 6G air interface, orthogonal frequency-division multiplexing (OFDM)-based waveforms are the primary candidates for future integrated sensing and communication (ISAC) systems. In this paper, we…
This paper introduces ELMO, a real-time upsampling motion capture framework designed for a single LiDAR sensor. Modeled as a conditional autoregressive transformer-based upsampling motion generator, ELMO achieves 60 fps motion capture from…
Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall. The Delta Rule mitigates this by writing each token via one step of online gradient…
With the growing number of users in multi-user multiple-input multiple-output (MU-MIMO) systems, demodulation reference signals (DMRSs) are efficiently multiplexed in the code domain via orthogonal cover codes (OCC) to ensure orthogonality…
While machine learning is widely used to optimize wireless networks, training a separate model for each task in communication and localization is becoming increasingly unsustainable due to the significant costs associated with training and…
As we move towards 6G, the demand for high-precision, cost-effective positioning solutions becomes increasingly critical. Single-anchor positioning offers a promising alternative to traditional multi-anchor approaches, particularly in…
Learning to capture dependencies between spatial positions is essential to many visual tasks, especially the dense labeling problems like scene parsing. Existing methods can effectively capture long-range dependencies with self-attention…
In this paper, we propose a novel framework, called Semi-supervised Embedding in Attributed Networks with Outliers (SEANO), to learn a low-dimensional vector representation that systematically captures the topological proximity, attribute…
Camera-based Deep Learning algorithms are increasingly needed for perception in Automated Driving systems. However, constraints from the automotive industry challenge the deployment of CNNs by imposing embedded systems with limited…