{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:52:29Z","timestamp":1771923149067,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/cgo68049.2026.11395230","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:46:32Z","timestamp":1771879592000},"page":"164-175","source":"Crossref","is-referenced-by-count":0,"title":["Flow-Graph-Aware Tiling and Rescheduling for Memory-Efficient On-Device Inference"],"prefix":"10.1109","author":[{"given":"Yeonoh","family":"Jeong","sequence":"first","affiliation":[{"name":"Yonsei University,Department of Computer Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taehyeong","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Computer Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjun","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University,Department of Computer Science,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.zemedi.2018.11.002"},{"key":"ref3","author":"Bojarski","year":"2016","journal-title":"End to end learning for self-driving cars"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref9","author":"Vaswani","year":"2023","journal-title":"Attention is all you need"},{"key":"ref10","author":"Devlin","year":"2019","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref11","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iThings-GreenCom-CPSCom-SmartData-Cybermatics55523.2022.00050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.495765"},{"key":"ref14","author":"Xu","year":"2023","journal-title":"A survey on deep neural network partition over cloud, edge and end devices"},{"issue":"2","key":"ref15","first-page":"1","article-title":"Empowering edge intelligence: A comprehensive survey on on-device ai models","volume":"56","author":"Niu","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"ref16","first-page":"705","article-title":"Mistify: Automating DNN model porting for On-Device inference at the edge","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Guo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"ref18","first-page":"22941","article-title":"On-device training under 256kb memory","volume":"35","author":"Lin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3129415"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649391"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649391"},{"key":"ref22","first-page":"2346","article-title":"Memory-efficient patch-based inference for tiny deep learning","volume":"34","author":"Lin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","article-title":"Streamnet: Memory-efficient streaming tiny deep learning inference on the microcontroller","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Zheng"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00070"},{"key":"ref25","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Paszke","year":"2019"},{"key":"ref26","author":"Abadi","year":"2016","journal-title":"Tensorflow: A system for large-scale machine learning"},{"key":"ref27","volume-title":"Tensorflow lite: Machine learning for mobile and edge devices","year":"2025"},{"key":"ref28","volume-title":"Onnx runtime: Accelerating machine learning inference","year":"2025"},{"key":"ref29","first-page":"578","article-title":"Tvm: An automated end-to-end optimizing compiler for deep learning","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1090\/s0002-9939-1956-0078686-7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/opre.38.1.178"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0196-6774(88)90031-4"},{"key":"ref33","volume-title":"Tensorflow lite for microcontrollers","year":"2025"},{"key":"ref34","year":"2025","journal-title":"Raspberry pi: Low-cost, high-performance computers for learning, coding, and making"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3706107"},{"key":"ref36","first-page":"452","article-title":"vmcu: Coordinated memory management and kernel optimization for dnn inference on mcus","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Zheng"},{"key":"ref37","author":"Stahl","year":"2023","journal-title":"Fused depthwise tiling for memory optimization in tinyml deep neural network inference"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34214-1_7"},{"key":"ref39","volume-title":"Mcunet model zoo","author":"Lin","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00591"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1145\/3649329.3655922","article-title":"Motenn: Memory optimization via fine-grained scheduling for deep neural networks on tiny devices","volume-title":"Proceedings of the 61st ACM\/IEEE Design Automation Conference, DAC \u201924","author":"Chen"},{"key":"ref42","volume-title":"NUCLEO-F767ZI - stm32 nucleo-144 development board with stm32f767zi mcu","year":"2025"},{"key":"ref43","year":"2025","journal-title":"Raspberry pi 4 model b"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.11.019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.11.019"},{"key":"ref46","first-page":"1","article-title":"Tinyml: Current progress, research challenges, and future opportunities","volume-title":"Proceedings of the 58th Annual Design Automation Conference (DAC)","author":"Banbury"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2017.09.037"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323998"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716257"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2018.00049"}],"event":{"name":"2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11395173\/11394837\/11395230.pdf?arnumber=11395230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:47:19Z","timestamp":1771919239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11395230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/cgo68049.2026.11395230","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}