{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:07:50Z","timestamp":1782313670948,"version":"3.54.5"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Financial Program of BJAST","award":["24CA007-03"],"award-info":[{"award-number":["24CA007-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3542415","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T18:32:06Z","timestamp":1739557926000},"page":"31774-31784","source":"Crossref","is-referenced-by-count":1,"title":["Task-Agnostic Adaptive Activation Scaling Network for LLMs"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3575-4000","authenticated-orcid":false,"given":"Ni","family":"Jia","sequence":"first","affiliation":[{"name":"Beijing Academy of Science and Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Academy of Science and Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7833-3222","authenticated-orcid":false,"given":"Jiadi","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5505-2113","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing Academy of Science and Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8904-9760","authenticated-orcid":false,"given":"Song","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Academy of Science and Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MoELoRA: Contrastive learning guided mixture of experts on parameter-efficient fine-tuning for large language models","author":"Luo","year":"2024","journal-title":"arXiv:2402.12851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1063\/5.0203126"},{"key":"ref3","first-page":"506","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"Rebuffi","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref4","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1165"},{"key":"ref6","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021","journal-title":"arXiv:2110.04366"},{"key":"ref7","article-title":"Parameter-efficient transfer learning with diff pruning","author":"Guo","year":"2020","journal-title":"arXiv:2012.07463"},{"key":"ref8","first-page":"24193","article-title":"Training neural networks with fixed sparse masks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sung"},{"key":"ref9","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref10","article-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","author":"Aghajanyan","year":"2020","journal-title":"arXiv:2012.13255"},{"key":"ref11","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahabadi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref13","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Lisa Li","year":"2021","journal-title":"arXiv:2101.00190"},{"key":"ref14","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1206"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"ref22","first-page":"265","article-title":"Multi-task Gaussian process learning of robot inverse dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"21","author":"Williams"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240406"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref28","first-page":"1","article-title":"Learning multiple tasks with multilinear relationship networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Long"},{"key":"ref29","article-title":"Latent multi-task architecture learning","author":"Ruder","year":"2017","journal-title":"arXiv:1705.08142"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599769"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref33","volume-title":"NLP-progress","author":"Ruder","year":"2022"},{"key":"ref34","first-page":"1","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"ref36","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"Glm","year":"2024","journal-title":"arXiv:2406.12793"},{"key":"ref37","article-title":"A survey on in-context learning","author":"Dong","year":"2022","journal-title":"arXiv:2301.00234"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10890995.pdf?arnumber=10890995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T05:53:03Z","timestamp":1740203583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3542415","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}