Related papers: RL-Based Interference Mitigation in Uncoordinated …
Meta-learning for offline reinforcement learning (OMRL) is an understudied problem with tremendous potential impact by enabling RL algorithms in many real-world applications. A popular solution to the problem is to infer task identity as…
We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in…
The surge in Reinforcement Learning (RL) applications in Intelligent Transportation Systems (ITS) has contributed to its growth as well as highlighted key challenges. However, defining objectives of RL agents in traffic control and…
Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive…
The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks. To ensure robust communication against jamming, an…
Speech Large Language Models have achieved breakthroughs in multilingual speech-to-text translation. However, existing approaches often overlook semantic commonalities across source languages, leading to biased translation performance. In…
This paper studies the two-user Gaussian interference channel with half-duplex causal cognition. This channel model consists of two source-destination pairs sharing a common wireless channel. One of the sources, referred to as the…
Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT). However, it usually fails to achieve notable gains (sometimes, even worse) on resource-rich NMT on par with its…
5G is regarded as a revolutionary mobile network, which is expected to satisfy a vast number of novel services, ranging from remote health care to smart cities. However, heterogeneous Quality of Service (QoS) requirements of different…
Techniques to improve the data quality of interferometric radio observations are considered. Fundaments of fringe frequencies in the uv-plane are discussed and filters are used to attenuate radio-frequency interference (RFI) and off-axis…
Interference alignment is a transmission technique for exploiting all available degrees of freedom in the interference channel with an arbitrary number of users. Most prior work on interference alignment, however, neglects interference from…
Over-the-air computation (AirComp) integrates analog communication with task-oriented computation, serving as a key enabling technique for communication-efficient federated learning (FL) over wireless networks. However, owing to its analog…
This paper studies the achievable rates of Gaussian interference channels with additive white Gaussian noise (AWGN), when improper or circularly asymmetric complex Gaussian signaling is applied. For the Gaussian multiple-input…
Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of…
Future wireless networks are expected to support diverse mobile services, including artificial intelligence (AI) services and ubiquitous data transmissions. Federated learning (FL), as a revolutionary learning approach, enables…
We propose a novel uplink communication method, coined random orthogonalization, for federated learning (FL) in a massive multiple-input and multiple-output (MIMO) wireless system. The key novelty of random orthogonalization comes from the…
The mode selection and resource allocation in fog radio access networks (F-RANs) have been advocated as key techniques to improve spectral and energy efficiency. In this paper, we investigate the joint optimization of mode selection and…
In cognitive radio (CR) networks, secondary users (SUs) are allowed to opportunistically access the primary users (PUs) spectrum to improve the spectrum utilization; however, this increases the interference levels at the PUs. In this paper,…
Diffusion-based visuomotor policies built on 3D visual representations have achieved strong performance in learning complex robotic skills. However, most existing methods employ an oversized denoising decoder. While increasing model…
With the rapid deployment of the Internet of Things (IoT), fifth-generation (5G) and beyond 5G networks are required to support massive access of a huge number of devices over limited radio spectrum radio. In wireless networks, different…