{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T22:26:25Z","timestamp":1769034385756,"version":"3.49.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,14]]},"DOI":"10.1109\/cloudcom67567.2025.11331339","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:37:16Z","timestamp":1768941436000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["ModelMap: Kernel-Level Zero-Copy On-Demand Model Loading for Edge AI"],"prefix":"10.1109","author":[{"given":"Fei","family":"Yi","sequence":"first","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3088875"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386351"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD63220.2024.00076"},{"key":"ref4","first-page":"813","article-title":"Optimizing memory-mapped i\/o for fast storage devices","volume-title":"2020 USENIX Annual Technical Conference (USENIX ATC 20)","author":"Papagiannis"},{"key":"ref5","article-title":"Why parallel nfs is the right choice for ai\/ml workloads","volume-title":"NetApp Blog","author":"Kaligotla","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3170574"},{"key":"ref7","article-title":"Why network file system (nfs) is not suitable for ai workloads?","volume-title":"wEKA Blog","author":"Murphy","year":"2020"},{"key":"ref8","article-title":"User level page faults","volume-title":"PhD diss., Carnegie Mellon University","author":"Li","year":"2020"},{"issue":"1","key":"ref9","volume":"23","author":"Fedus","year":"2022","journal-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity"},{"key":"ref10","author":"Mirzayeva","year":"2023","journal-title":"A review on secure file access protocols for nfs in biomedical it"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2452376.2452377"},{"key":"ref12","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2024.3521978"},{"key":"ref15","volume-title":"Enabling client-side caching of nfs content","year":"2025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref17","article-title":"Beyond efficiency: A systematic survey of resource-efficient large language models","author":"Bai","year":"2024","journal-title":"ar Xiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.32628\/cseit251112210"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCHPC49590.2019.00017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3672197.3673432"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/10943420241303145"},{"key":"ref22","first-page":"649","article-title":"Efficient memory disaggregation with infiniswap","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Gu","year":"2017"},{"key":"ref23","first-page":"551","article-title":"Zero-offload: Democratizing billion-scale model training","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Ren"},{"key":"ref24","volume-title":"Serving large language models on huawei cloudmatrix384","author":"Zuo","year":"2025"},{"key":"ref25","first-page":"775","article-title":"Remote regions: a simple abstraction for remote memory","volume-title":"2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Aguilera"},{"key":"ref26","first-page":"181","article-title":"Hermit:low-latency, high-throughput, and transparent remote memory via feedback-directed asynchrony","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Qiao"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3721146.3721954"},{"key":"ref29","volume-title":"Qwen2.5\u20133b: A scalable open language model","year":"2024"}],"event":{"name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","location":"Shenzhen, China","start":{"date-parts":[[2025,11,14]]},"end":{"date-parts":[[2025,11,16]]}},"container-title":["2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11330195\/11331311\/11331339.pdf?arnumber=11331339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:12:02Z","timestamp":1768979522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11331339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/cloudcom67567.2025.11331339","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]}}}