Related papers: Continuous Prefetch for Interactive Data Applicati…

Mobile graphical user interface (GUI) agents enable AI models to autonomously operate smartphones on behalf of users. However, most existing systems focus primarily on optimizing task accuracy and rely on cloud-hosted models for inference,…

Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address this limitation, we…

In modern human-robot collaboration (HRC) applications, multiple perception modules jointly extract visual, auditory, and contextual cues to achieve comprehensive scene understanding, enabling the robot to provide appropriate assistance to…

PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation -- a phenomenon that crippled the batch size (and consequently…

Automated Machine Learning (AutoML) is used more than ever before to support users in determining efficient hyperparameters, neural architectures, or even full machine learning pipelines. However, users tend to mistrust the optimization…

For distributed systems to properly react to peaks of requests, their adaptation activities would benefit from the estimation of the amount of requests. This paper proposes a solution to produce a short-term forecast based on data…

Contrast maximization (CMAX) is a direct geometric framework for event-based motion estimation, but its iterative warp-and-accumulate pipeline incurs input-dependent computation and frequent memory accesses, challenging real-time, low-power…

Kernel density estimation (KDE) is one of the most widely used nonparametric density estimation methods. The fact that it is a memory-based method, i.e., it uses the entire training data set for prediction, makes it unsuitable for most…

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

Interactive preference elicitation (IPE) aims to substantially reduce human effort while acquiring human preferences in wide personalization systems. Dueling bandit (DB) algorithms enable optimal decision-making in IPE building on pairwise…

Diffusion models have achieved remarkable success in content generation but often incur prohibitive computational costs due to iterative sampling. Recent feature caching methods accelerate inference via temporal extrapolation, yet can…

High load latency that results from deep cache hierarchies and relatively slow main memory is an important limiter of single-thread performance. Data prefetch helps reduce this latency by fetching data up the hierarchy before it is…

Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- particularly gaming -- offer a compelling alternative: they…

In this paper, we argue that database systems be augmented with an automated data exploration service that methodically steers users through the data in a meaningful way. Such an automated system is crucial for deriving insights from…

Nowadays, many companies possess various types of AI accelerators, forming heterogeneous clusters. Efficiently leveraging these clusters for high-throughput large language model (LLM) inference services can significantly reduce costs and…

Virtualization, after having found widespread adoption in the server and desktop arena, is poised to change the architecture of embedded systems as well. The benefits afforded by virtualization - enhanced isolation, manageability,…

Resource disaggregation offers a cost effective solution to resource scaling, utilization, and failure-handling in data centers by physically separating hardware devices in a server. Servers are architected as pools of processor, memory,…

Flow-level network measurement is critical to many network applications. Among various measurement tasks, packet loss detection and heavy-hitter detection are two most important measurement tasks, which we call the two key tasks. In…

Augmented Large Language Models (LLMs) enhance the capabilities of standalone LLMs by integrating external data sources through API calls. In interactive LLM applications, efficient scheduling is crucial for maintaining low request…

Recent approaches for learning policies to improve caching, target just one out of the prefetching, admission and eviction processes. In contrast, we propose an end to end pipeline to learn all three policies using machine learning. We also…