Related papers: Compass: Optimizing Compound AI Workflows for Dyna…
Modern enterprise AI applications increasingly rely on compound AI systems - architectures that compose multiple models, retrievers, and tools to accomplish complex tasks. Deploying such systems in production demands inference…
In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with…
Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS…
The Versal Adaptive Compute Acceleration Platform (ACAP) is a new architecture that combines AI Engines (AIEs) with reconfigurable fabric. This architecture offers significant acceleration potential for uniform recurrences in various…
Advances in vehicular communication technologies are expected to facilitate cooperative driving. Connected and Automated Vehicles (CAVs) are able to collaboratively plan and execute driving maneuvers by sharing their perceptual knowledge…
Modern cloud-native systems increasingly rely on multi-cluster deployments to support scalability, resilience, and geographic distribution. However, existing resource management approaches remain largely reactive and cluster-centric,…
Compound AI applications chain together subcomponents such as generative language models, document retrievers, and embedding models. Applying traditional systems optimizations such as parallelism and pipelining in compound AI systems is…
In modern distributed cloud environments, efficient resource allocation is required as traditional scaling mechanisms are often subject to cloud thrashing due to network-induced latencies. In this paper, we propose C-SAS (Complex-Stability…
Deciding how to distribute work between humans and AI systems is a central challenge in organisational design. Most approaches treat this as a binary choice, yet the operational reality is richer: humans and AI routinely share tasks or take…
Cross-silo federated learning offers a promising solution to collaboratively train robust and generalized AI models without compromising the privacy of local datasets, e.g., healthcare, financial, as well as scientific projects that lack a…
Modern operating system schedulers employ a single, static policy, which struggles to deliver optimal performance across the diverse and dynamic workloads of contemporary systems. This "one-policy-fits-all" approach leads to significant…
In today's world, circumstances, processes, and requirements for software systems are becoming increasingly complex. In order to operate properly in such dynamic environments, software systems must adapt to these changes, which has led to…
The 3D continuum presents a complex environment that spans the terrestrial, aerial and space domains, with 6Gnetworks serving as a key enabling technology. Current AI approaches for network management rely on monolithic models that fail to…
Supply chain planning is the critical process of anticipating future demand and coordinating operational activities across the logistics network. However, within the context of contemporary e-commerce, traditional planning paradigms,…
Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or…
In human-AI decision making, designing AI that complements human expertise has been a natural strategy to enhance human-AI collaboration, yet it often comes at the cost of decreased AI performance in areas of human strengths. This can…
The effectiveness of the machine learning methods for real-world tasks depends on the proper structure of the modeling pipeline. The proposed approach is aimed to automate the design of composite machine learning pipelines, which is…
The performance of an algorithm often critically depends on its parameter configuration. While a variety of automated algorithm configuration methods have been proposed to relieve users from the tedious and error-prone task of manually…
Dynamic resource allocation to parallel queues is a cornerstone of network scheduling, yet classical solutions often fail when accounting for the overhead of switching delays to queues with superior link conditions. In particular, system…
While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.…