Related papers: ServeFlow: A Fast-Slow Model Architecture for Netw…
Classifying network traffic according to their application-layer protocols is an important task in modern networks for traffic management and network security. Existing payload-based or statistical methods of application identification…
As the demand for vehicles continues to outpace construction of new roads, it becomes imperative we implement strategies that improve utilization of existing transport infrastructure. Traffic sensors form a crucial part of many such…
With the increasing importance of distributed scientific workflows, there is a critical need to ensure Quality of Service (QoS) constraints, such as minimizing time or limiting execution to resource subsets. However, the unpredictable…
We present the process of transitioning machine learning models to the TensorFlow framework at a large scale in an online advertising ecosystem. In this talk we address the key challenges we faced and describe how we successfully tackled…
Generating high-quality time series data has emerged as a critical research topic due to its broad utility in supporting downstream time series mining tasks. A major challenge lies in modeling the intrinsic stochasticity of temporal…
State-of-the-art deep learning systems such as TensorFlow and PyTorch tightly couple the model with the underlying hardware. This coupling requires the user to modify application logic in order to run the same job across a different set of…
Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in…
Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many…
Limited by inference latency, existing robot manipulation policies lack sufficient real-time interaction capability with the environment. Although faster generation methods such as flow matching are gradually replacing diffusion methods,…
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation.…
The power consumption of enormous network devices in data centers has emerged as a big concern to data center operators. Despite many traffic-engineering-based solutions, very little attention has been paid on performance-guaranteed energy…
We propose flow-based analysis to estimate quality of an Internet connection. Using results from the queuing theory we compare two expressions for backbone traffic that have different scopes of applicability. A curve that shows dependence…
The exponential growth of data storage demands has necessitated the evolution of hierarchical storage management strategies [1]. This study explores the application of streaming machine learning [3] to revolutionize data prefetching within…
Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks, resulting in diverse and often conflicting Service Level…
Efficient algorithms and techniques to detect and identify large flows in a high throughput traffic stream in the SDN match-and-action model are presented. This is in contrast to previous work that either deviated from the match and action…
We address the challenges associated with deploying neural networks on CPUs, with a particular focus on minimizing inference time while maintaining accuracy. Our novel approach is to use the dataflow (i.e., computation order) of a neural…
A new method of estimating some statistical characteristics of TCP flows in the Internet is developed in this paper. For this purpose, a new set of random variables (referred to as observables) is defined. When dealing with sampled traffic,…
Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…
OpenFlow is one of the most commonly used protocols for communication between the controller and the forwarding element in a software defined network (SDN). A model based on M/M/1 queues is proposed in [1] to capture the communication…
Due to network operation and maintenance relying heavily on network traffic monitoring, traffic matrix analysis has been one of the most crucial issues for network management related tasks. However, it is challenging to reliably obtain the…