Related papers: Compass: SLO-aware Query Planner for Compound AI S…
In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without…
On the Internet, sub-millisecond queueing delay and capacity-seeking have traditionally been considered mutually exclusive. We introduce a service that offers both: Low Latency Low Loss Scalable throughput (L4S). When tested under a wide…
Ensuring Service Level Objectives (SLOs) in large-scale architectures, such as Distributed Computing Continuum Systems (DCCS), is challenging due to their heterogeneous nature and varying service requirements across different devices and…
Modern distributed systems integrate heterogeneous services, REST APIs with different schema versions, GraphQL endpoints, and IoT devices with proprietary payloads that suffer from persistent schema mismatches. Traditional static adapters…
Sampling-Based Optimal(SBO) path planning has been mainly used for robotic arm manipulation tasks. Several research works have been carried out in order to evaluate performances of various SBO planners for arm manipulation. However, not…
The diverse requirements of beyond 5G services increase design complexity and demand dynamic adjustments to the network parameters. This can be achieved with slicing and programmable network architectures such as the open radio access…
Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and…
Applications in emerging domains such as XR are being built as compound inference systems, where multiple ML models are composed in the form of a task graph to service each request. Serving these compound systems efficiently raises two…
Deploying data- and computation-intensive applications such as large-scale AI into heterogeneous dispersed computing networks can significantly enhance application performance by mitigating bottlenecks caused by limited network resources,…
Efficient data processing is increasingly vital, with query optimizers playing a fundamental role in translating SQL queries into optimal execution plans. Traditional cost-based optimizers, however, often generate suboptimal plans due to…
Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…
In-network computation represents a transformative approach to addressing the escalating demands of Artificial Intelligence (AI) workloads on network infrastructure. By leveraging the processing capabilities of network devices such as…
Low Earth orbit (LEO) satellites play an essential role in intelligent Earth observation by leveraging artificial intelligence models. However, limited onboard memory and excessive inference delay prevent the practical deployment of large…
The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…
This paper investigates a paradigm for offering artificial intelligence as a service (AI-aaS) on software-defined infrastructures (SDIs). The increasing complexity of networking and computing infrastructures is already driving the…
In-flight Internet connectivity is a necessity for aircraft passengers as well as aircraft systems. It is challenging to satisfy required quality of service (QoS) levels for flows within aircraft due to the large number of users and the…
Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are…
Efficient coordination and planning is essential for large-scale multi-agent systems that collaborate in a shared dynamic environment. Heuristic search methods or learning-based approaches often lack the guarantee on correctness and…
Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…
In LLM serving, reusing the KV cache of prompts across requests is critical for reducing TTFT and serving costs. Cache-affinity scheduling, which co-locates requests with the same prompt prefix to maximize KV cache reuse, often conflicts…