{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:31Z","timestamp":1782798271196,"version":"3.54.5"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571678","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Rocket: Warming Serverless Inference via Hierarchical ML Artifact Pre-loading and Sharing"],"prefix":"10.1109","author":[{"given":"Xiaofei","family":"Yue","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youqi","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Temple University,Department of Computer and Information Sciences,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Computing in the era of large generative models: From cloud-native to AI-native","author":"Lu","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref3","first-page":"1049","article-title":"MArk: Exploiting cloud services for cost-effective and SLO-aware machine learning inference serving","volume-title":"Proc. of the USENIX ATC","author":"Zhang"},{"key":"ref4","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","volume-title":"Proc. of the USENIX ATC","author":"Romero"},{"key":"ref5","first-page":"205","article-title":"Serverless in the wild: Characterizing and optimizing the serverless workload at a large cloud provider","volume-title":"Proc. of the USENIX ATC","author":"Shahrad"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3632089"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044553"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707285"},{"key":"ref9","article-title":"Amazon SageMaker","year":"2025"},{"key":"ref10","article-title":"Azure Container Instances","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446757"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624871"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567960"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698509"},{"key":"ref16","first-page":"473","article-title":"Tetris: Memory-efficient serverless inference through tensor sharing","volume-title":"Proc. of the USENIX ATC","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645383"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629567"},{"key":"ref19","first-page":"69","article-title":"Help rather than recycle: Alleviating cold startup in serverless computing through inter-function container sharing","volume-title":"Proc. of the USENIX ATC","author":"Li"},{"key":"ref20","article-title":"Torpor: GPU-enabled serverless computing for low-latency, resource-efficient inference","author":"Yu","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3486788"},{"key":"ref22","article-title":"Modern hierarchical, agglomerative clustering algorithms","author":"M\u00fcllner","year":"2011"},{"issue":"133","key":"ref23","first-page":"1","article-title":"A contextual bandit bake-off","volume":"22","author":"Bietti","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507709"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517905"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624664"},{"key":"ref27","article-title":"Delving into what happens when you \u2018import torch\u2019","year":"2023"},{"key":"ref28","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1740-9713.2018.01123.x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3184400"},{"key":"ref31","first-page":"149","article-title":"Autothrottle: A practical Bi-level approach to resource management for SLO-targeted microservices","volume-title":"Proc. of the USENIX NSDI","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00044"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621303"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695477"},{"key":"ref35","first-page":"1638","article-title":"Taming the monster: A fast and simple algorithm for contextual bandits","volume-title":"Proc. of the PMLR ICML","author":"Agarwal"},{"key":"ref36","article-title":"Apache OpenWhisk","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref43","article-title":"Imgclsmob: A large-scale, high-performance, and open-source image classification model zoo","year":"2021"},{"key":"ref44","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref46","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"Chen","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3548320"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707251"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3524270"},{"key":"ref51","first-page":"419","article-title":"Firecracker: Lightweight virtualization for serverless applications","volume-title":"Proc. of the USENIX NSDI","author":"Agache"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507732"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571678.pdf?arnumber=11571678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:11:46Z","timestamp":1782796306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571678","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}