English
Related papers

Related papers: Efficient and Effective Tail Latency Minimization …

200 papers

Caching is crucial for system performance, but the delayed hit phenomenon, where requests queue during lengthy fetches after a cache miss, significantly degrades user-perceived latency in modern high-throughput systems. While prior works…

Networking and Internet Architecture · Computer Science 2025-05-22 Bowen Jiang , Chaofan Ma

Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can…

Machine Learning · Computer Science 2017-11-09 Bowen Baker , Otkrist Gupta , Ramesh Raskar , Nikhil Naik

This study extends the recently-developed LaCAM algorithm for multi-agent pathfinding (MAPF). LaCAM is a sub-optimal search-based algorithm that uses lazy successor generation to dramatically reduce the planning effort. We present two…

Artificial Intelligence · Computer Science 2023-05-08 Keisuke Okumura

Shared training approaches, such as multi-task learning (MTL) and gradient-based meta-learning, are widely used in various machine learning applications, but they often suffer from negative transfer, leading to performance degradation in…

Machine Learning · Computer Science 2024-12-10 Anshul Thakur , Yichen Huang , Soheila Molaei , Yujiang Wang , David A. Clifton

Retrieval Augmented Generation (RAG) is a promising technique for mitigating two key limitations of large language models (LLMs): outdated information and hallucinations. RAG system stores documents as embedding vectors in a database. Given…

Information Retrieval · Computer Science 2026-02-10 Taehee Jeong , Xingzhe Zhao , Peizu Li , Markus Valvur , Weihua Zhao

Driven by recent advances in artificial intelligence (AI), a growing literature has demonstrated the potential for using large language models (LLMs) as scalable surrogates to generate human-like responses in many business applications. Two…

Machine Learning · Computer Science 2025-12-30 Lei Wang , Zikun Ye , Jinglong Zhao

In large-scale ranking systems, cascading architectures have been widely adopted to achieve a balance between efficiency and effectiveness. The pre-ranking module plays a vital role in selecting a subset of candidates for the subsequent…

Information Retrieval · Computer Science 2024-07-18 YaChen Yan , Liubo Li

Low-latency communication has recently attracted considerable attention owing to its potential of enabling delay-sensitive services in next-generation industrial cyber-physical systems. To achieve target average or maximum delay given…

Information Theory · Computer Science 2025-06-17 Lintao Li , Wei Chen

Open-domain question answering over datalakes requires retrieving and composing information from multiple tables, a challenging subtask that demands semantic relevance and structural coherence (e.g., joinability). While exact optimization…

Information Retrieval · Computer Science 2025-11-18 Allaa Boutaleb , Bernd Amann , Rafael Angarita , Hubert Naacke

Large-scale Ads recommendation and auction scoring models at Google scale demand immense computational resources. While specialized hardware like TPUs have improved linear algebra computations, bottlenecks persist in large-scale systems.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-22 George Kurian , Somayeh Sardashti , Ryan Sims , Felix Berger , Gary Holt , Yang Li , Jeremiah Willcock , Kaiyuan Wang , Herve Quiroz , Abdulrahman Salem , Julian Grady

In industrial recommendation systems on websites and apps, it is essential to recall and predict top-n results relevant to user interests from a content pool of billions within milliseconds. To cope with continuous data growth and improve…

Information Retrieval · Computer Science 2024-11-06 Qiang Zhang , Zhipeng Teng , Disheng Wu , Jiayin Wang

Deep Neural Networks are allowing mobile devices to incorporate a wide range of features into user applications. However, the computational complexity of these models makes it difficult to run them effectively on resource-constrained mobile…

Performance · Computer Science 2020-04-02 Samuel S. Ogden , Tian Guo

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

Machine Learning · Computer Science 2025-09-03 Zixi Chen , Yinyu Ye , Zijie Zhou

Many ML applications and products train on medium amounts of input data but get bottlenecked in real-time inference. When implementing ML systems, conventional wisdom favors segregating ML code into services queried by product code via…

Machine Learning · Computer Science 2023-07-25 Daniel S Johnson , Igor L Markov

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

Machine Learning · Computer Science 2024-02-15 Yashas Samaga B L , Varun Yerram , Chong You , Srinadh Bhojanapalli , Sanjiv Kumar , Prateek Jain , Praneeth Netrapalli

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Machine Learning · Computer Science 2025-05-13 Xiaotian Lin , Yanlin Qi , Yizhang Zhu , Themis Palpanas , Chengliang Chai , Nan Tang , Yuyu Luo

Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with…

Machine Learning · Computer Science 2026-03-24 Kangqi Ni , Wenyue Hua , Xiaoxiang Shi , Jiang Guo , Shiyu Chang , Tianlong Chen

If a bus line becomes unstable, passengers waiting time will be lengthened and buses capacities will be mismatched. To stabilize a high-frequency bus line, many holding strategies have been proposed. Among these strategies, some need to…

Systems and Control · Electrical Eng. & Systems 2020-06-17 Shengxue He

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…

Computation and Language · Computer Science 2025-11-03 Avinash Kumar , Shashank Nag , Jason Clemons , Lizy John , Poulami Das

The effectiveness of multi-stage text retrieval has been solidly demonstrated since before the era of pre-trained language models. However, most existing studies utilize models that predate recent advances in large language models (LLMs).…

Information Retrieval · Computer Science 2023-10-13 Xueguang Ma , Liang Wang , Nan Yang , Furu Wei , Jimmy Lin