Related papers: An End-to-End Assurance Framework for AI/ML Worklo…
As mobile edge computing (MEC) finds widespread use for relieving the computational burden of compute- and interaction-intensive applications on end user devices, understanding the resulting delay and cost performance is drawing significant…
Enterprise AI systems, built on large language models, retrieval pipelines and autonomous agents, introduce a class of risks that traditional software quality assurance was never designed to address. These systems are probabilistic,…
AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this…
In the past decade, Artificial Intelligence (AI) has become a part of our daily lives due to major advances in Machine Learning (ML) techniques. In spite of an explosive growth in the raw AI technology and in consumer facing applications on…
Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…
We present sql4ml, a system for expressing supervised machine learning (ML) models in SQL and automatically training them in TensorFlow. The primary motivation for this work stems from the observation that in many data science tasks there…
As AI technology advances, it is driving innovation across industries, increasing the demand for scalable AI project deployment. However, deployment remains a critical challenge due to complex environment configurations, dependency…
Immersive formats such as 360{\deg} and 6DoF point cloud videos require high bandwidth and low latency, posing challenges for real-time AR/VR streaming. This work focuses on reducing bandwidth consumption and encryption/decryption delay,…
Cloud-based services with resources to be provisioned for consumers are increasingly the norm, especially with respect to Big data, spatiotemporal data mining and application services that impose a user's agreed Quality of Service (QoS)…
Issue resolution, a complex Software Engineering (SWE) task integral to real-world development, has emerged as a compelling challenge for artificial intelligence. The establishment of benchmarks like SWE-bench revealed this task as…
This paper is the first study to apply deep mutual learning (DML) to end-to-end ASR models. In DML, multiple models are trained simultaneously and collaboratively by mimicking each other throughout the training process, which helps to…
Embodied AI systems, including robots and autonomous vehicles, are increasingly integrated into real-world applications, where they encounter a range of vulnerabilities stemming from both environmental and system-level factors. These…
The core challenge in automotive exterior design is balancing subjective aesthetics with objective aerodynamic performance while dramatically accelerating the development cycle. To address this, we propose a novel, LLM-driven multi-agent…
Recent technological and architectural advancements in 5G networks have proven their worth as the deployment has started over the world. Key performance elevating factor from access to core network are softwareization, cloudification and…
Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving…
Testing microservice systems involves a large amount of planning and problem-solving. The difficulty of testing microservice systems increases as the size and structure of such systems become more complex. To help the microservice community…
Today's datacenters face important challenges for providing low-latency high-quality interactive services to meet user's expectation. For improving the application throughput, recent research works have embedded application deadline…
In large-scale AI training, Sparse Mixture-of-Experts (s-MoE) layers enable scaling by activating only a small subset of experts per token. An operational challenge in this design is load balancing: routing tokens to minimize the number of…
With the rise of large language models (LLMs), researchers are increasingly exploring their applications in var ious vertical domains, such as software engineering. LLMs have achieved remarkable success in areas including code generation…
End-to-end delay is a critical attribute of quality of service (QoS) in application domains such as cloud computing and computer networks. This metric is particularly important in tandem service systems, where the end-to-end service is…