{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:45:18Z","timestamp":1782798318309,"version":"3.54.5"},"reference-count":35,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","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\/infocom59046.2026.11571457","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":["Lazy but Efficient: Layer-Wise Task Scheduling with Lazy Pulling for Fast Serverless Inference"],"prefix":"10.1109","author":[{"given":"Zhexiong","family":"Li","sequence":"first","affiliation":[{"name":"China University of Geosciences,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmin","family":"Geng","sequence":"additional","affiliation":[{"name":"China University of Geosciences,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuepeng","family":"Li","sequence":"additional","affiliation":[{"name":"China University of Geosciences,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Gu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Computer Science and Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deze","family":"Zeng","sequence":"additional","affiliation":[{"name":"China University of Geosciences,School of Computer Science,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.14778\/3547305.3547313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-0072-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2455-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228890"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00206"},{"key":"ref6","first-page":"135","article-title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Fu"},{"key":"ref7","article-title":"Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference","volume-title":"Proceedings of USENIX Annual Technical Conference (USENIX ATC)","author":"Yu"},{"issue":"8","key":"ref8","first-page":"9","article-title":"Language Models are Unsupervised Multitask Learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446757"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3222509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695978"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044642"},{"key":"ref13","first-page":"315","article-title":"On-demand Container Loading in AWS Lambda","volume-title":"Proceedings of USENIX Annual Technical Conference (USENIX ATC)","author":"Brooker"},{"key":"ref14","first-page":"181","article-title":"Slacker: Fast Distribution with Lazy Docker Containers","volume-title":"Proceedings of USENIX Conference on File and Storage Technologies (FAST)","author":"Harter"},{"key":"ref15","first-page":"35","article-title":"Starlight: Fast Container Provisioning on the Edge and over the WAN","volume-title":"USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624871"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref18","first-page":"6105","article-title":"Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Tan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229072"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695947"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0879"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3315138"},{"key":"ref26","first-page":"205","article-title":"Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider","volume-title":"Proceedings of USENIX Annual Technical Conference (USENIX ATC)","author":"Shahrad"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/spe.3016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0822"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3348165"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3617688"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679824"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3727125"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3609510.3609816"}],"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\/11571457.pdf?arnumber=11571457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:21:09Z","timestamp":1782796869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571457","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}