{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:01:06Z","timestamp":1780639266543,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"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":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539097","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["DyGen: A Constant-Time Kernel Generator for Dynamic-Shape Neural Networks"],"prefix":"10.23919","author":[{"given":"Yuhan","family":"Kang","sequence":"first","affiliation":[{"name":"National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems, College of Computer Science,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Beijing,China,100004"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Beijing,China,100004"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Shi","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems, College of Computer Science,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchao","family":"Yang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems, College of Computer Science,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Xue","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems, College of Computer Science,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems, College of Computer Science,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Wen","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Key Laboratory of Advanced Microprocessor Chips and Systems, College of Computer Science,Changsha,China,410073"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning to optimize tensor programs","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Chen","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70018-7_41"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s42514-022-00095-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3079758"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.57"},{"key":"ref6","article-title":"oneAPI Deep Neural Network Library (oneDNN)"},{"key":"ref7","article-title":"cublas: Nvidia cuda basic linear algebra subprograms library","year":"2023"},{"key":"ref8","article-title":"CUTLASS","author":"Thakkar","year":"2023"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref11","article-title":"Dynamic neural networks: A survey","author":"Han","year":"2021"},{"key":"ref12","article-title":"A survey of dynamic graph neural networks","author":"Zheng","year":"2024"},{"key":"ref13","first-page":"521","article-title":"Orca: A distributed serving system for Transformer-Based generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1145\/3600006.3613165","article-title":"Efficient memory management for large language model serving with pagedattention","author":"Kwon","year":"2023"},{"key":"ref15","article-title":"Fast distributed inference serving for large language models","author":"Wu","year":"2024"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2015.169","article-title":"Fast R-CNN","volume-title":"CoRR","author":"Girshick","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref19","first-page":"208","article-title":"Nimble: Efficiently compiling dynamic neural networks for model inference","volume-title":"Proceedings of Machine Learning and Systems","volume":"3","author":"Shen"},{"key":"ref20","first-page":"848","article-title":"Dietcode: Automatic optimization for dynamic tensor programs","volume-title":"Proceedings of Machine Learning and Systems","volume":"4","author":"Zheng"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640390"},{"key":"ref22","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"ref23","article-title":"vllm: A high-performance language model serving framework","year":"2023"},{"key":"ref24","article-title":"Deepbench: Benchmarking deep learning performance","author":"Research","year":"2023"},{"key":"ref25","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref26","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref27","article-title":"Bert: a review of applications in natural language processing and understanding","author":"Koroteev","year":"2021"},{"key":"ref28","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref29","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref30","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref32","article-title":"Deep residual learning for image recognition","author":"He","year":"2015"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539097.pdf?arnumber=11539097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:10:26Z","timestamp":1780636226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":32,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539097","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}