{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T19:15:19Z","timestamp":1774898119704,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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":[[2025,9,22]]},"DOI":"10.1109\/icnp65844.2025.11192368","type":"proceedings-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:38:54Z","timestamp":1760377134000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking"],"prefix":"10.1109","author":[{"given":"Linhan","family":"Xia","sequence":"first","affiliation":[{"name":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhan","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Yan","sequence":"additional","affiliation":[{"name":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yakun","family":"Ren","sequence":"additional","affiliation":[{"name":"Sf Technology,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo","family":"Yu","sequence":"additional","affiliation":[{"name":"GienTech Technology Co.,Ltd.,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Lei","sequence":"additional","affiliation":[{"name":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3216456"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-023-04534-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3208196"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512217"},{"key":"ref6","first-page":"303","article-title":"{SENSEI}: Aligning video streaming quality with dynamic user sensitivity","author":"Zhang","year":"2021","journal-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672268"},{"key":"ref8","first-page":"597","article-title":"On the computational complexity of self-attention","volume-title":"International Conference on Algorithmic Learning Theory","author":"Keles"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00098"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3435752"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/NFV-SDN61811.2024.10807499"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3511662"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3522103"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DSC63325.2024.00019"},{"key":"ref18","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"International conference on machine learning.","author":"Hua","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-54114-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07366-3"},{"key":"ref22","article-title":"Transformers to ssms: Distilling quadratic knowledge to subquadratic models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Bick"},{"key":"ref23","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","volume-title":"Forty-first International Conference on Machine Learning","author":"Zhu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679959"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3508058"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icnp61940.2024.10858569"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3699518"},{"key":"ref29","article-title":"Minillm: Knowledge distillation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342063"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3380888"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/VR55154.2023.00033"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548331"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544243"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref37","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3033127"},{"key":"ref40","article-title":"Decision mamba: Reinforcement learning via sequence modeling with selective state spaces","author":"Ota","year":"2024"},{"key":"ref41","article-title":"Mamba: an effective world model approach for meta-reinforcement learning","author":"Rimon","year":"2024"},{"key":"ref42","article-title":"On-policy distillation of language models: Learning from self-generated mistakes","volume-title":"The Twelfth International Conference on Learning Representations","author":"Agarwal"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3377214"},{"key":"ref44","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3487175"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3070520"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682864"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682901"}],"event":{"name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2025,9,22]]},"end":{"date-parts":[[2025,9,25]]}},"container-title":["2025 IEEE 33rd International Conference on Network Protocols (ICNP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11192357\/11192322\/11192368.pdf?arnumber=11192368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T05:08:20Z","timestamp":1760418500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11192368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icnp65844.2025.11192368","relation":{},"subject":[],"published":{"date-parts":[[2025,9,22]]}}}