{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:44:21Z","timestamp":1784216661815,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Education Commission","doi-asserted-by":"publisher","award":["2024AIYB002"],"award-info":[{"award-number":["2024AIYB002"]}],"id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Program","doi-asserted-by":"publisher","award":["62422111"],"award-info":[{"award-number":["62422111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Program","doi-asserted-by":"publisher","award":["62371291"],"award-info":[{"award-number":["62371291"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Program","doi-asserted-by":"publisher","award":["62271316"],"award-info":[{"award-number":["62271316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Program","doi-asserted-by":"publisher","award":["62222111"],"award-info":[{"award-number":["62222111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2024YFE0200600"],"award-info":[{"award-number":["2024YFE0200600"]}]},{"name":"Science and Technology Commission Foundation of Shanghai","award":["24DP1500702"],"award-info":[{"award-number":["24DP1500702"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/twc.2025.3560231","type":"journal-article","created":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T13:40:53Z","timestamp":1745242853000},"page":"7377-7391","source":"Crossref","is-referenced-by-count":7,"title":["Addressing the Curse of Scenario and Task Generalization in AI-6G: A Multi-Modal Paradigm"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8469-853X","authenticated-orcid":false,"given":"Tianyu","family":"Jiao","sequence":"first","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0365-5398","authenticated-orcid":false,"given":"Zhuoran","family":"Xiao","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4429-5982","authenticated-orcid":false,"given":"Yin","family":"Xu","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhui","family":"Ye","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4979-3999","authenticated-orcid":false,"given":"Yihang","family":"Huang","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3540-389X","authenticated-orcid":false,"given":"Zhiyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyu","family":"Cai","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Chang","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6637-0088","authenticated-orcid":false,"given":"Dazhi","family":"He","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1993-7560","authenticated-orcid":false,"given":"Yunfeng","family":"Guan","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8656-1946","authenticated-orcid":false,"given":"Guangyi","family":"Liu","sequence":"additional","affiliation":[{"name":"China Mobile Research Institute, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-1182","authenticated-orcid":false,"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Big AI models for 6G wireless networks: Opportunities, challenges, and research directions","author":"Chen","year":"2023","journal-title":"arXiv:2308.06250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3427313"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref4","article-title":"Large generative AI models for telecom: The next big thing?","author":"Bariah","year":"2023","journal-title":"arXiv:2306.10249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/e25060920"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC51858.2021.9593182"},{"key":"ref7","article-title":"Heterogeneity matters even more in distributed learning: Study from generalization perspective","author":"Kavian","year":"2025","journal-title":"arXiv:2503.01598"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771835"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.013.2200553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3175091"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3217664"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3280966"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3274162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685564"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3229661"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278810"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC55385.2023.10118753"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT56141.2022.10073437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3317924"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps56602.2022.10008537"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3219640"},{"key":"ref22","article-title":"Self-supervised learning for WiFi CSI-based human activity recognition: A systematic study","author":"Xu","year":"2023","journal-title":"arXiv:2308.02412"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3181008"},{"key":"ref24","article-title":"WAIR-D: Wireless AI research dataset","author":"Huangfu","year":"2022","journal-title":"arXiv:2212.02159"},{"key":"ref25","article-title":"DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications","author":"Alkhateeb","year":"2019","journal-title":"arXiv:1902.06435"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/29.32276"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/49.753729"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10570565"},{"key":"ref32","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv:1802.03426"},{"key":"ref33","article-title":"Towards understanding the modality gap in CLIP","volume-title":"Proc. ICLR Workshop Multi-Modal Represent. Learn., Perks Pitfalls","author":"Shi"},{"key":"ref34","first-page":"18166","article-title":"An empirical study of training end-to-end vision-and-language transformers","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Dou"},{"key":"ref35","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref36","article-title":"Image as a foreign language: BEiT pretraining for all vision and vision-language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2208.10442"},{"key":"ref37","article-title":"Meta-transformer: A unified framework for multimodal learning","author":"Zhang","year":"2023","journal-title":"arXiv:2307.10802"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3189788"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10000718"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278998"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3389113"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3460057"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180800"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3217777"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3322799"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041397"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3265272"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC49870.2020.9289167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11159553\/10971878.pdf?arnumber=10971878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T05:16:44Z","timestamp":1757654204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10971878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":49,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/twc.2025.3560231","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}