相关论文: MUSE: Multi-Tenant Model Serving With Seamless Mod…

Mixture-of-Experts (MoE) architectures have emerged as a promising direction, offering efficiency and scalability by activating only a subset of parameters during inference. However, current research remains largely performance-centric,…

As a tool to exploit economies of scale, Software as a Service cloud models promote Multi-Tenancy which is the notion of sharing instances among a large group of tenants. However, Multi-Tenancy only satisfies requirements that are common to…

Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In practice, this often involves using imperfect LLM judges and reward models since ground…

Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned. Approximate machine unlearning offers an efficient…

We design a self-decision goal-oriented multiple access scheme, where sensing agents observe a common event and individually decide to communicate the event's attributes as updates to the monitoring agents, to satisfy a certain goal.…

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

The public cloud offers a myriad of services which allows its tenants to process large scale big data in a flexible, easy and cost effective manner. Tenants generally use large scale data processing frameworks such as MapReduce, Tez, Spark…

Mobile edge caching (MEC) has been introduced to support ever-growing end-users' needs. To reduce the backhaul traffic demand and content delivery latency, cache-enabled edge servers at base stations (BSs) are employed to provision popular…

Ensemble methods for stream mining necessitate managing multiple models and updating them as data distributions evolve. Considering the calls for more sustainability, established methods are however not sufficiently considerate of ensemble…

Generative recommendation models can model user behavior as sequences of events and provide a shared backbone for multiple recommendation tasks. In production, however, pre-training gains do not automatically translate into downstream…

Deploying large language models for clinical Text-to-SQL requires distinguishing two qualitatively different causes of output diversity: (i) input ambiguity that should trigger clarification, and (ii) model instability that should trigger…

Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out multi-scenario transfer learning on the basis of the…

Mixture-of-Experts (MoE) models challenge serving infrastructures with dynamic, sparse expert utilization, causing instability on conventional systems designed for dense architectures. We propose EaaS, a novel serving system to enable…

Stakeholders make various types of decisions with respect to requirements, design, management, and so on during the software development life cycle. Nevertheless, these decisions are typically not well documented and classified due to…

The majority of multi-agent system (MAS) implementations aim to optimise agents' policies with respect to a single objective, despite the fact that many real-world problem domains are inherently multi-objective in nature. Multi-objective…

Edge computing has become a very popular service that enables mobile devices to run complex tasks with the help of network-based computing resources. However, edge clouds are often resource-constrained, which makes resource allocation a…

The aim of multimodal neural networks is to combine diverse data sources, referred to as modalities, to achieve enhanced performance compared to relying on a single modality. However, training of multimodal networks is typically hindered by…

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are…

The transition from monolithic architecture to microservices has enhanced flexibility in application design and its scalable execution. This approach typically uses a computing cluster managed by a container orchestration platform to deploy…

Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing…