Related papers: LITHE: Bridging Best-Effort Python and Real-Time C…

Training large language models (LLMs) is known to be challenging because of the huge computational and memory capacity requirements. To address these issues, it is common to use a cluster of GPUs with 3D parallelism, which splits a model…

Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…

Learning-based controllers, such as diffusion policies and vision-language action models, often generate low-frequency or discontinuous robot state changes. Achieving smooth reference tracking requires a low-level controller that converts…

Quadruped mammals coordinate spinal bending and axial compression to enhance locomotion agility and efficiency. However, existing robotic spines typically lack the active compliance required to support such dynamic behaviours. We present…

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, yet generating reliable reasoning processes remains a significant challenge. We present a unified probabilistic framework that formalizes LLM…

Cyber-physical systems (CPS) are vulnerable to attacks targeting outgoing actuation commands that modify their physical behaviors. The limited resources in such systems, coupled with their stringent timing constraints, often prevents the…

Emerging large language model (LLM) applications involve diverse reasoning strategies and agentic workflows, straining the capabilities of existing serving systems built on a monolithic token generation loop. This paper introduces Pie, a…

Learned Index Structures (LIS) have significantly advanced data management by leveraging machine learning models to optimize data indexing. However, designing these structures often involves critical trade-offs, making it challenging for…

Modern datacenter applications are prone to high tail latencies since their requests typically follow highly-dispersive distributions. Delivering fast interrupts is essential to reducing tail latency. Prior work has proposed both OS- and…

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…

Swarms of autonomous devices are increasing in ubiquity and size, making the need for rethinking their hardware-software system stack critical. We present HiveMind, the first swarm coordination platform that enables programmable execution…

There is an urgent demand for privacy-preserving techniques capable of supporting compute and data intensive (CDI) computing in the era of big data. However, none of existing TEEs can truly support CDI computing tasks, as CDI requires high…

Runahead execution is a technique to mask memory latency caused by irregular memory accesses. By pre-executing the application code during occurrences of long-latency operations and prefetching anticipated cache-missed data into the cache…

The integration of Large Language Models (LLMs) into robotics has revolutionized human-robot interactions and autonomous task planning. However, these systems are often unable to self-correct during the task execution, which hinders their…

Current large language models reason in isolation. Although it is common to sample multiple reasoning paths in parallel, these trajectories do not interact, and often fail in the same redundant ways. We introduce LACE, a framework that…

Highly interactive development environments (HIDEs) enable uninterrupted development flow through continuous program evolution and rapid hypothesis checking. However, traditional testing approaches -- typically executed separately via CLI…

The evolution of architectures, programming models, and algorithms is driving communication towards greater asynchrony and concurrency, usually in multithreaded environments. We present LCI, a communication library designed for efficient…

Lowering costs by driving high utilization across deep learning workloads is a crucial lever for cloud providers. We present Singularity, Microsoft's globally distributed scheduling service for highly-efficient and reliable execution of…

Homomorphic encryption (HE) enables computations on encrypted data by concealing information under noise for security. However, the process of bootstrapping, which resets the noise level in the ciphertext, is computationally expensive and…

Intelligent mobile robots are critical in several scenarios. However, as their computational resources are limited, mobile robots struggle to handle several tasks concurrently and yet guaranteeing real-timeliness. To address this challenge…