Related papers: Data-driven Clustering and Merging of Adapters for…

Clustering techniques create hierarchal network structures, called clusters, on an otherwise flat network. In a dynamic environment-in terms of node mobility as well as in terms of steadily changing device parameters-the clusterhead…

In this paper, the utilization of mobile devices (MDs) as decode-and-forward relays in a device-to-device assisted virtual MIMO (VMIMO) system is studied. Single antenna MDs are randomly distributed on a 2D plane according to a Poisson…

Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models…

Large Language Models (LLMs) are increasingly deployed in both latency-sensitive online services and cost-sensitive offline workloads. Co-locating these workloads on shared serving instances can improve resource utilization, but directly…

Transformers provide promising accuracy and have become popular and used in various domains such as natural language processing and computer vision. However, due to their massive number of model parameters, memory and computation…

The widespread diffusion of distributed energy resources, especially those based on renewable energy, and energy storage devices has deeply modified power systems. As a consequence, demand response, the ability of customers to respond to…

The problem of multimodal clustering arises whenever the data are gathered with several physically different sensors. Observations from different modalities are not necessarily aligned in the sense there there is no obvious way to associate…

Existing clustering methods are based on a single granularity of information, such as the distance and density of each data. This most fine-grained based approach is usually inefficient and susceptible to noise. Inspired by adaptive process…

LoRA achieves remarkable resource efficiency and comparable performance when adapting LLMs for specific tasks. Since ChatGPT demonstrated superior performance on various tasks, there has been a growing desire to adapt one model for all…

In the era of large language models (LLMs), supervised neural methods remain the state-of-the-art (SOTA) for Coreference Resolution. Yet, their full potential is underexplored, particularly in incremental clustering, which faces the…

In modern mobile applications, users frequently encounter various new contexts, necessitating on-device continual learning (CL) to ensure consistent model performance. While existing research predominantly focused on developing lightweight…

We formulate and solve the energy minimization problem for a clustered device-to-device (D2D) network with cache-enabled mobile devices. Devices are distributed according to a Poisson cluster process (PCP) and are assumed to have a surplus…

Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art…

Large language models (LLMs) are rapidly replacing help forums like StackOverflow, and are especially helpful for non-professional programmers and end users. These users are often interested in data-centric tasks, such as spreadsheet…

Continual fine-tuning aims to adapt a pre-trained backbone to new tasks sequentially while preserving performance on earlier tasks whose data are no longer available. Existing approaches fall into two categories which include input- and…

Federated Learning (FL) enables collaborative learning of large-scale distributed clients without data sharing. However, due to the disparity of computing resources among massive mobile computing devices, the performance of traditional…

In our increasingly interconnected world, where intelligent devices continually amass copious personalized multi-modal data, a pressing need arises to deliver high-quality, personalized device-aware services. However, this endeavor presents…

The current and envisaged increase of cellular traffic poses new challenges to Mobile Network Operators (MNO), who must densify their Radio Access Networks (RAN) while maintaining low Capital Expenditure and Operational Expenditure to…

In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing. First, we explore the effect of additional information by adopting a pretrained language model…

Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior. Recently, large language models (LLMs) have gained prominence for their capabilities in…