Related papers: Towards Resource-Efficient Compound AI Systems
Modern cluster management systems like Kubernetes and Openstack grapple with hard combinatorial optimization problems: load balancing, placement, scheduling, and configuration. Currently, developers tackle these problems by designing custom…
Next-generation mixed-criticality Systems-on-chip (SoCs) for robotics, automotive, and space must execute mixed-criticality AI-enhanced sensor processing and control workloads, ensuring reliable and time-predictable execution of critical…
Molecular dynamics (MD) simulations are widely used to study large-scale molecular systems. HPC systems are ideal platforms to run these studies, however, reaching the necessary simulation timescale to detect rare processes is challenging,…
This paper introduces a high-performance artificial intelligence operating system tailored for low-altitude aviation, designed to address key challenges such as real-time task execution, computational efficiency, and seamless modular…
The adoption of cloud-based Enterprise Resource Planning (ERP) platforms such as Workday has transformed healthcare operations by integrating financial, supply-chain, and workforce processes into a unified ecosystem. However, traditional…
Large-language-model (LLM)-based AI agents have recently showcased impressive versatility by employing dynamic reasoning, an adaptive, multi-step process that coordinates with external tools. This shift from static, single-turn inference to…
Sustainability encompasses three key facets: economic, environmental, and social. However, the nascent discourse that is emerging on sustainable artificial intelligence (AI) has predominantly focused on the environmental sustainability of…
Generative Artificial Intelligence (GenAI) has rapidly transformed various fields including code generation, text summarization, image generation and so on. Agentic AI is a recent evolution that further advances this by coupling the…
In recent years, the integration of artificial intelligence (AI) and cloud computing has emerged as a promising avenue for addressing the growing computational demands of AI applications. This paper presents a comprehensive study of…
Reuse is a common system architecture approach that seeks to instantiate a system architecture with existing components. However, reusing components with AI capabilities might introduce new risks as there is currently no framework that…
The latency-quality tradeoff is a fundamental constraint in open-domain dialogue AI systems, since comprehensive knowledge access necessitates prohibitive response delays. Contemporary approaches offer two inadequate solutions: lightweight…
Artificial intelligence (AI) is driving rapid growth in electricity demand, yet the grid-facing power dynamics of AI data centers remain poorly understood. Here we show that, in shared-GPU systems, the composition of batch and inference…
Agentic workflows have emerged as a powerful paradigm for solving complex, multi-stage tasks, but serving them at scale is computationally expensive given the many LLM inferences that each request must pass through. Configuration selection,…
In mixed-initiative systems, the mode of AI assistance delivery can be as consequential as the assistance itself. We investigated two assistance delivery modes: on-demand help (users request via Button) and pre-scheduled help (assistance…
We introduce the term Super-Reactive Systems to refer to reactive systems whose construction and behavior are complex, constantly changing and evolving, and heavily interwoven with other systems and the physical world. Finding hidden faults…
To safely and efficiently solve motion planning problems in multi-agent settings, most approaches attempt to solve a joint optimization that explicitly accounts for the responses triggered in other agents. This often results in solutions…
The increasing proliferation of IoT devices and AI applications has created a demand for scalable and efficient computing solutions, particularly for applications requiring real-time processing. The compute continuum integrates edge and…
Industrial timetabling is a critical task for decision-makers across various sectors to ensure efficient system operation. In real-world settings, it remains challenging because unexpected events often disrupt execution. When such events…
Generative, ML-driven interactive systems have the potential to change how people interact with computers in creative processes - turning tools into co-creators. However, it is still unclear how we might achieve effective human-AI…
The era of large deep learning models has given rise to advanced training strategies such as 3D parallelism and the ZeRO series. These strategies enable various (re-)configurable execution plans for a training job, which exhibit remarkably…