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

Caching at mobile devices can facilitate device-to-device (D2D) communications, which may significantly improve spectrum efficiency and alleviate the heavy burden on backhaul links. However, most previous works ignored user mobility, thus…

As the data size in Machine Learning fields grows exponentially, it is inevitable to accelerate the computation by utilizing the ever-growing large number of available cores provided by high-performance computing hardware. However, existing…

Optimal resource allocation (RA) in massive carrier aggregation scenarios is a challenging combinatorial optimization problem whose dimension is proportional to the number of users, component carriers (CCs), and OFDMA resource blocks per…

With the rapid development of machine learning, improving its explainability has become a crucial research goal. We study the problem of making the clusters more explainable by investigating the cluster descriptors. Given a set of objects…

Next-generation wireless technologies (for immersive-massive communication, joint communication and sensing) demand highly parallel architectures for massive data processing. A common architectural template scales up by grouping tens to…

Density Peak Clustering (DPC), a popular density-based clustering approach, has received considerable attention from the research community primarily due to its simplicity and fewer-parameter requirement. However, the resultant clusters…

As pre-trained models automate many code intelligence tasks, a widely used paradigm is to fine-tune a model on the task dataset for each programming language. A recent study reported that multilingual fine-tuning benefits a range of tasks…

Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained…

A new era is dawning for wireless mobile ad hoc networks where communication will be done using a group of mobile devices called cluster, hence clustered network. In a clustered network, protocols used by these mobile devices are different…

A new technique is presented to design energy-efficient large-scale tracking systems based on mobile clustering. The new technique optimizes the formation of mobile clusters to minimize energy consumption in large-scale tracking systems.…

Load balancing is an effective approach to address the spatial-temporal fluctuation problem of mobile data traffic for cellular networks. The existing schemes that focus on channel borrowing from neighboring cells cannot be directly applied…

With the rapid development of storage and computing power on mobile devices, it becomes critical and popular to deploy models on devices to save onerous communication latencies and to capture real-time features. While quite a lot of works…

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

The Outstanding performance and growing size of Large Language Models has led to increased attention in parameter efficient learning. The two predominant approaches are Adapters and Pruning. Adapters are to freeze the model and give it a…

Modern large language model (LLM) systems increasingly rely on multi-turn pipelines that are composed of multiple task-specific adapters, yet existing serving frameworks remain inefficient, incurring substantial recomputation overhead when…

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

A delay-optimal caching problem (DOCP) in deviceto- device (D2D) networks with moblity is modelled. The problem arises in the context of achieving offloading using device caching, and the offloading effect is represented by the expected…

Low-rank Adaptation (LoRA) has demonstrated remarkable capabilities for task specific fine-tuning. However, in scenarios that involve multiple tasks, training a separate LoRA model for each one results in considerable inefficiency in terms…

We propose In-Context Clustering (ICC), a flexible LLM-based procedure for clustering data from diverse distributions. Unlike traditional clustering algorithms constrained by predefined similarity measures, ICC flexibly captures complex…

Text clustering is an important method for organising the increasing volume of digital content, aiding in the structuring and discovery of hidden patterns in uncategorised data. The effectiveness of text clustering largely depends on the…