At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence

As we transition from the 5G epoch, a new horizon beckons with the advent of 6G, seeking a profound fusion with novel communication paradigms and emerging technological trends, bringing once-futuristic visions to life along with added technical intricacies. Although analytical models lay the foundat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE open journal of the Communications Society Jg. 5; S. 2433 - 2489
Hauptverfasser: Celik, Abdulkadir, Eltawil, Ahmed M.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
6G mobile communication
adversarial ML
AI-generated content
Antenna arrays
Artificial intelligence
artificial intelligence (AI)
autoregressive generative models
Autoregressive models
Communication system security
Communications traffic
Data models
deep learning (DL)
Design optimization
diffusion models
Digital twins
discriminative AI
Edge computing
explainable AI
extremely large antenna arrays
Generative adversarial networks
generative AI
Generative artificial intelligence
generative models
generative pre-trained transformers
generative transformers
holographic beamforming
integrated sensing and communications
Large language models
Machine learning
machine learning (ML)
mMIMO
mmWave
Mobile computing
Near field communication
network function virtualization
Network management systems
normalizing flows
open RAN
semantic communications
software defined networks
Surveys
Taxonomy
Technical papers
terahertz
trustworthy AI
variational autoencoders
Wireless communication
zero-touch service management
ISSN:2644-125X, 2644-125X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract As we transition from the 5G epoch, a new horizon beckons with the advent of 6G, seeking a profound fusion with novel communication paradigms and emerging technological trends, bringing once-futuristic visions to life along with added technical intricacies. Although analytical models lay the foundations and offer systematic insights, we have recently witnessed a noticeable surge in research suggesting machine learning (ML) and artificial intelligence (AI) can efficiently deal with complex problems by complementing or replacing model-based approaches. The majority of data-driven wireless research leans heavily on discriminative AI (DAI) that requires vast real-world datasets. Unlike the DAI, Generative AI (GenAI) pertains to generative models (GMs) capable of discerning the underlying data distribution, patterns, and features of the input data. This makes GenAI a crucial asset in wireless domain wherein real-world data is often scarce, incomplete, costly to acquire, and hard to model or comprehend. With these appealing attributes, GenAI can replace or supplement DAI methods in various capacities. Accordingly, this combined tutorial-survey paper commences with preliminaries of 6G and wireless intelligence by outlining candidate 6G applications and services, presenting a taxonomy of state-of-the-art DAI models, exemplifying prominent DAI use cases, and elucidating the multifaceted ways through which GenAI enhances DAI. Subsequently, we present a tutorial on GMs by spotlighting seminal examples such as generative adversarial networks, variational autoencoders, flow-based GMs, diffusion-based GMs, generative transformers, large language models, autoregressive GMs, to name a few. Contrary to the prevailing belief that GenAI is a nascent trend, our exhaustive review of approximately 120 technical papers demonstrates the scope of research across core wireless research areas, including 1) physical layer design; 2) network optimization, organization, and management; 3) network traffic analytics; 4) cross-layer network security; and 5) localization & positioning. Furthermore, we outline the central role of GMs in pioneering areas of 6G network research, including semantic communications, integrated sensing and communications, THz communications, extremely large antenna arrays, near-field communications, digital twins, AI-generated content services, mobile edge computing and edge AI, adversarial ML, and trustworthy AI. Lastly, we shed light on the multifarious challenges ahead, suggesting potential strategies and promising remedies. Given its depth and breadth, we are confident that this tutorial-cum-survey will serve as a pivotal reference for researchers and professionals delving into this dynamic and promising domain.
AbstractList As we transition from the 5G epoch, a new horizon beckons with the advent of 6G, seeking a profound fusion with novel communication paradigms and emerging technological trends, bringing once-futuristic visions to life along with added technical intricacies. Although analytical models lay the foundations and offer systematic insights, we have recently witnessed a noticeable surge in research suggesting machine learning (ML) and artificial intelligence (AI) can efficiently deal with complex problems by complementing or replacing model-based approaches. The majority of data-driven wireless research leans heavily on discriminative AI (DAI) that requires vast real-world datasets. Unlike the DAI, Generative AI (GenAI) pertains to generative models (GMs) capable of discerning the underlying data distribution, patterns, and features of the input data. This makes GenAI a crucial asset in wireless domain wherein real-world data is often scarce, incomplete, costly to acquire, and hard to model or comprehend. With these appealing attributes, GenAI can replace or supplement DAI methods in various capacities. Accordingly, this combined tutorial-survey paper commences with preliminaries of 6G and wireless intelligence by outlining candidate 6G applications and services, presenting a taxonomy of state-of-the-art DAI models, exemplifying prominent DAI use cases, and elucidating the multifaceted ways through which GenAI enhances DAI. Subsequently, we present a tutorial on GMs by spotlighting seminal examples such as generative adversarial networks, variational autoencoders, flow-based GMs, diffusion-based GMs, generative transformers, large language models, autoregressive GMs, to name a few. Contrary to the prevailing belief that GenAI is a nascent trend, our exhaustive review of approximately 120 technical papers demonstrates the scope of research across core wireless research areas, including 1) physical layer design; 2) network optimization, organization, and management; 3) network traffic analytics; 4) cross-layer network security; and 5) localization & positioning. Furthermore, we outline the central role of GMs in pioneering areas of 6G network research, including semantic communications, integrated sensing and communications, THz communications, extremely large antenna arrays, near-field communications, digital twins, AI-generated content services, mobile edge computing and edge AI, adversarial ML, and trustworthy AI. Lastly, we shed light on the multifarious challenges ahead, suggesting potential strategies and promising remedies. Given its depth and breadth, we are confident that this tutorial-cum-survey will serve as a pivotal reference for researchers and professionals delving into this dynamic and promising domain.
Author Eltawil, Ahmed M.
Celik, Abdulkadir
Author_xml – sequence: 1
  givenname: Abdulkadir
  orcidid: 0000-0001-9007-9979
  surname: Celik
  fullname: Celik, Abdulkadir
  email: abdulkadir.celik@kaust.edu.sa
  organization: Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
– sequence: 2
  givenname: Ahmed M.
  orcidid: 0000-0003-1849-083X
  surname: Eltawil
  fullname: Eltawil, Ahmed M.
  organization: Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia
BookMark eNqFkU1P3DAQhq0KpNItv6A9WOo5W39Mkk1vqy1sF1H2AKi9WY49oV4Fm9oOiH9PlqAK9cJpRjPzvDOa9wM58MEjIZ84m3POmq_bs9X25-VcMAFzKSshav6OHIkKoOCi_H3wKn9PjlPaMcZEyTmXcETsMtP8B-l3_eBp6OgaPUad3T3S5YaeRP2NLunVkEN0ui_McFtcDvEeH2nw9AIf6GkMPjuMiTpPqzX95SL2mBLd-Ix9727QG_xIDjvdJzx-iTNyfXpytfpRnG_Xm9XyvDDAmlxo1lUaUGILVlvdGllXogVdQ9uKFq3tNKvAQAO1hQ7LzrAFb1hdQ91AKa2ckc2ka4PeqbvobnV8VEE79VwI8UbpmJ3pUWlr7WKUkxwlaGALtihbMFhxZE0n-aj1ZdK6i-HvgCmrXRiiH89Xko0nNHU90jMipykTQ0oRu39bOVN7d9Tkjtq7o17cGanmP8q4PD59fGXUrn-D_TyxDhFfbYN9t5JPNgGeiQ
CODEN IOJCAZ
CitedBy_id crossref_primary_10_1007_s12145_025_01912_y
crossref_primary_10_1088_2631_8695_ade02b
crossref_primary_10_1109_OJIES_2025_3560946
crossref_primary_10_1177_01655515251353188
crossref_primary_10_1109_ACCESS_2024_3521579
crossref_primary_10_1109_TWC_2025_3562731
crossref_primary_10_1109_MNET_2024_3420702
crossref_primary_10_1109_JIOT_2024_3487627
crossref_primary_10_1145_3742891
crossref_primary_10_1109_TNSM_2025_3543022
crossref_primary_10_1016_j_comnet_2025_111573
crossref_primary_10_1109_OJCOMS_2025_3544871
crossref_primary_10_1109_TWC_2025_3556118
crossref_primary_10_1109_TCE_2025_3526826
crossref_primary_10_1109_TCCN_2025_3527719
crossref_primary_10_1109_TCCN_2025_3558992
crossref_primary_10_1016_j_comnet_2025_111594
crossref_primary_10_1109_TCE_2025_3538785
crossref_primary_10_1016_j_comnet_2025_111614
crossref_primary_10_1109_JIOT_2024_3493611
crossref_primary_10_1109_MCOM_001_2400699
crossref_primary_10_3390_fi16100365
crossref_primary_10_1109_MCOM_001_2400558
crossref_primary_10_3390_s25113488
crossref_primary_10_1109_ACCESS_2024_3521005
crossref_primary_10_1109_JIOT_2025_3579780
crossref_primary_10_1109_OJCOMS_2025_3591535
crossref_primary_10_1109_ACCESS_2025_3573371
crossref_primary_10_1109_OJCOMS_2025_3568496
crossref_primary_10_3390_e27080815
crossref_primary_10_1109_TCCN_2025_3540256
crossref_primary_10_3390_app15062920
crossref_primary_10_3390_technologies12070099
crossref_primary_10_3390_admsci15020066
crossref_primary_10_1109_TCCN_2025_3531486
Cites_doi 10.1109/TCCN.2023.3279260
10.1007/978-0-387-21579-2_9
10.1016/j.ins.2020.04.019
10.1109/TMC.2021.3075083
10.1109/ACCESS.2020.2991337
10.1109/MILCOM.2018.8599782
10.1109/IWCMC.2019.8766353
10.1109/CBD.2014.41
10.1109/TCOMM.2020.3031930
10.1109/TETCI.2019.2948058
10.1109/ICCSN52437.2021.9463629
10.1109/LCOMM.2021.3132947
10.1109/ICC42927.2021.9500893
10.1109/MCOM.001.1900509
10.1109/GLOBECOM42002.2020.9322583
10.48550/arXiv.1312.6114
10.1109/MWC.101.2100269
10.1109/TNNLS.2020.3010724
10.1109/JIOT.2022.3211346
10.1080/02564602.2014.987328
10.1109/TWC.2017.2782690
10.1109/ACCESS.2018.2815741
10.1016/j.eswa.2022.117163
10.1145/3143361.3143393
10.1109/TWC.2021.3103971
10.1109/GLOBECOM54140.2023.10437200
10.1109/CISCE55963.2022.9851065
10.1038/s41928-019-0355-6
10.1109/ACCESS.2019.2921522
10.1109/jproc.2020.2998530
10.1109/TWC.2019.2921955
10.1109/CVPR.2018.00916
10.1109/MCOM.004.2200136
10.1109/JSAC.2019.2959185
10.1109/TCOMM.2018.2879508
10.1145/3491209
10.1109/MNET.001.1900287
10.1109/TCOMM.2019.2924010
10.1109/ICCV.2017.304
10.1109/ACCESS.2017.2760350
10.1109/CVPR42600.2020.00813
10.1109/MNET.011.2000493
10.1109/ISIT.2019.8849476
10.1109/CSNDSP54353.2022.9907905
10.1109/mwc.019.2100721
10.1109/iccv.2017.244
10.1109/ACCESS.2022.3195299
10.1109/MVT.2020.3017152
10.1136/svn-2017-000101
10.1109/TWC.2022.3220784
10.3390/telecom2010009
10.1109/icc45855.2022.9839142
10.1109/MCOM.006.2200480
10.1109/TII.2022.3155656
10.1109/MCOM.001.1900698
10.1016/j.dsp.2021.103188
10.1109/INFOCOM.2019.8737631
10.1109/ICCT.2018.8600032
10.1109/jsac.2021.3126076
10.1109/CVPR.2017.202
10.1109/COMST.2014.2329501
10.1109/TSMCC.2009.2038279
10.1007/978-3-030-64793-3_1
10.1109/ACCESS.2019.2917207
10.1145/3285029
10.1109/LWC.2023.3263224
10.1109/MCOM.2019.1900271
10.1109/ACCESS.2019.2919996
10.1109/PRDC50213.2020.00018
10.1109/TNNLS.2020.3011671
10.1016/j.comnet.2021.108149
10.1109/TC.2013.13
10.1109/WCNC51071.2022.9771907
10.1109/IEMCON.2019.8936224
10.1109/tip.2023.3273451
10.1007/s11004-021-09934-0
10.1109/ICC45855.2022.9838574
10.1109/WCNC49053.2021.9417513
10.1145/3229556.3229562
10.1016/0004-3702(92)90065-6
10.1109/spawc48557.2020.9154331
10.1109/ICCW.2018.8403666
10.1007/BF00058655
10.48550/ARXIV.1706.03762
10.1109/ICCW.2018.8403655
10.1145/3395352.3402622
10.3390/app12168085
10.1109/TPAMI.2013.50
10.1109/TCCN.2023.3288108
10.1007/s12243-023-00980-9
10.1109/GLOBECOM38437.2019.9014102
10.1109/BMSB53066.2021.9547015
10.1145/3439729
10.1109/LWC.2021.3081509
10.1016/j.eswa.2021.115680
10.1109/ICSP48669.2020.9320987
10.1109/TWC.2020.3047100
10.1364/AOP.361502
10.1109/ICC42927.2021.9501056
10.1016/b978-0-7506-7531-4.x5000-3
10.1016/j.phycom.2019.100900
10.1109/ACSSC.2018.8645463
10.1109/TWC.2022.3219140
10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00141
10.1007/s11276-021-02781-1
10.1162/NECO_a_00142
10.1109/MILCOM47813.2019.9020907
10.1109/WCNC51071.2022.9771710
10.1109/WACV51458.2022.00188
10.18653/v1/W18-5446
10.1109/JSEN.2021.3105404
10.1109/SNAMS60348.2023.10375400
10.1145/3324921.3328782
10.1109/TWC.2020.3039013
10.1109/CCNC51644.2023.10060056
10.1109/MWC.001.1900534
10.1109/CCAAW.2019.8904907
10.1109/TPAMI.2020.2970919
10.1145/3331184.3331303
10.1109/TCCN.2020.2970693
10.1109/LNET.2022.3193766
10.1109/WCNC.2019.8885548
10.1109/ICPAI51961.2020.00012
10.1162/neco.2006.18.7.1527
10.1145/3269206.3269294
10.1109/MVT.2020.3015184
10.1109/twc.2023.3347419
10.1109/LWC.2018.2843359
10.1109/JSEN.2019.2958201
10.1109/JSAC.2023.3288243
10.1109/ICC.2019.8761755
10.1109/LCOMM.2020.2988384
10.1109/ECTI-CON54298.2022.9795409
10.1609/aaai.v34i03.5659
10.1109/COMST.2019.2904897
10.1109/TCCN.2022.3153004
10.1109/ICCNC.2019.8685527
10.5555/2969033.2969125
10.1016/j.comnet.2021.108535
10.3390/s18113913
10.1109/GLOBECOM42002.2020.9348244
10.1109/GLOCOMW.2018.8644149
10.1109/MCOM.2016.7470933
10.48550/arXiv.1609.03499
10.1109/GLOCOMW.2018.8644250
10.1016/j.measurement.2021.108974
10.1109/TPAMI.2021.3116668
10.1109/TWC.2019.2951416
10.1109/TCDS.2022.3176977
10.1109/TCCN.2018.2884910
10.1007/978-981-15-8462-6_96
10.1109/GLOBECOM38437.2019.9014217
10.1109/ACCESS.2021.3132127
10.1109/TCOMM.2007.892447
10.1109/OJCOMS.2023.3320646
10.1109/TCCN.2021.3105133
10.23919/EUSIPCO.2018.8553233
10.1109/TETCI.2019.2892748
10.1609/aaai.v33i01.3301541
10.1109/TWC.2021.3124202
10.1177/1548512921991245
10.1109/LWC.2021.3075467
10.1109/SPW.2018.00019
10.1109/BigData47090.2019.9005997
10.1016/j.adhoc.2020.102151
10.1145/3324921.3329695
10.1109/ICC.2018.8422223
10.22331/q-2018-08-06-79
10.1109/JIOT.2016.2579198
10.1109/COMST.2023.3249835
10.1109/ACCESS.2021.3095546
10.1109/ICTC52510.2021.9621134
10.1109/JIOT.2020.3024800
10.1016/j.adhoc.2020.102177
10.1007/978-3-031-19842-7_39
10.1109/ACCESS.2022.3161511
10.1109/LWC.2019.2947041
10.1109/IOTM.001.2100209
10.1109/JSAC.2021.3078489
10.1109/ACCESS.2023.3296707
10.1016/j.future.2022.01.026
10.1109/ACCESS.2022.3187837
10.1056/NEJMoa1210384
10.1023/B:MACH.0000015881.36452.6e
10.1109/TCYB.2022.3163811
10.1145/3468691.3468742
10.1098/rsta.1927.0007
10.3390/s22218085
10.1109/ICCWorkshops50388.2021.9473497
10.1109/GLOBECOM48099.2022.10001178
10.1109/compsac48688.2020.0-218
10.1109/TWC.2020.3046766
10.1145/3459992
10.1109/access.2021.3130418
10.1109/ICCNC.2019.8685573
10.1109/RADAR.2018.8378737
10.1109/IPIN54987.2022.9918146
10.1109/TCCN.2020.3010330
10.1109/MCOM.001.2200866
10.1109/MILCOM55135.2022.10017520
10.3390/electronics12010084
10.1109/BalkanCom53780.2021.9593240
10.1109/WCNC51071.2022.9771754
10.1109/ICC.2018.8423008
10.1109/jiot.2021.3098028
10.1109/TPAMI.2020.2992934
10.1186/s13638-021-01950-2
10.23919/JCC.2020.02.002
10.1109/LCOMM.2022.3172171
10.1109/COMST.2015.2476474
10.1109/JIOT.2022.3213593
10.1109/MCOM.2019.1800635
10.1109/INFOCOMWKSHPS51825.2021.9484569
10.1109/GLOBECOM54140.2023.10437725
10.1109/JSAC.2022.3191346
10.1109/MTTW51045.2020.9245065
10.1109/comst.2016.2532458
10.1109/COMST.2021.3136132
10.1109/COMST.2022.3223224
10.1109/MNET.011.2000195
10.1109/UkrMiCo43733.2018.9047611
10.1109/PST.2018.8514157
10.1109/MNET.2019.1800439
10.1016/j.array.2022.100142
10.1109/MWC.004.2100362
10.1109/GLOBECOM42002.2020.9322456
10.1145/3626235
10.1162/089976602760128018
10.1109/UEMCON.2018.8796769
10.1109/TCOMM.2019.2927561
10.1109/msp.2017.3151326
10.1109/CVPR.2017.632
10.1109/ACCESS.2022.3177906
10.1109/JPROC.2020.3004555
10.1109/TCCN.2019.2948919
10.1109/LWC.2018.2867459
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOA
DOI 10.1109/OJCOMS.2024.3362271
DatabaseName IEEE Xplore (IEEE)
IEEE Xplore Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Technology Research Database
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2644-125X
EndPage 2489
ExternalDocumentID oai_doaj_org_article_addd8a0631e34a408085b4ce61e09f31
10_1109_OJCOMS_2024_3362271
10422716
Genre orig-research
GrantInformation_xml – fundername: Office of Sponsored Research (OSR) at King Abdullah University of Science and Technology (KAUST)
GroupedDBID 0R~
97E
AAJGR
ABAZT
ABVLG
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
ESBDL
GROUPED_DOAJ
JAVBF
M~E
OCL
OK1
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
ID FETCH-LOGICAL-c409t-a0f6a4e3eb4dadabc3762b4a74bb2beddfa064c4947d4fe5fc0819077479453d3
IEDL.DBID RIE
ISICitedReferencesCount 51
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001214542600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2644-125X
IngestDate Fri Oct 03 12:50:29 EDT 2025
Sun Jun 29 16:00:36 EDT 2025
Tue Nov 18 21:51:10 EST 2025
Sat Nov 29 05:54:16 EST 2025
Wed Aug 27 02:06:29 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c409t-a0f6a4e3eb4dadabc3762b4a74bb2beddfa064c4947d4fe5fc0819077479453d3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-9007-9979
0000-0003-1849-083X
OpenAccessLink https://ieeexplore.ieee.org/document/10422716
PQID 3049497706
PQPubID 5075783
PageCount 57
ParticipantIDs crossref_primary_10_1109_OJCOMS_2024_3362271
doaj_primary_oai_doaj_org_article_addd8a0631e34a408085b4ce61e09f31
crossref_citationtrail_10_1109_OJCOMS_2024_3362271
proquest_journals_3049497706
ieee_primary_10422716
PublicationCentury 2000
PublicationDate 20240000
2024-00-00
20240101
2024-01-01
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 20240000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE open journal of the Communications Society
PublicationTitleAbbrev OJCOMS
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref207
ref56
ref59
ref58
Portree (ref154) 1993
Chen (ref212)
ref53
ref52
ref55
Mirza (ref206) 2014
ref54
ref202
Ferdowsi (ref219) 2020
Cao (ref295) 2022
Donahue (ref211) 2016
Dinh (ref231) 2014
ref51
ref50
Higgins (ref221)
ref46
ref218
ref45
ref216
ref47
ref217
ref42
ref214
ref41
Nair (ref253)
ref43
ref213
ref49
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref100
ref101
Van Den Oord (ref249)
ref40
ref220
ref34
ref37
ref36
ref31
ref302
ref30
ref303
ref33
ref300
ref32
Bariah (ref266) 2023
ref301
ref39
ref38
Arjovsky (ref209)
ref24
Devlin (ref240) 2018
ref23
ref26
Xu (ref19) 2023
ref25
ref20
ref22
ref21
Ren (ref194) 2021
ref28
ref27
ref29
ref200
Goodfellow (ref204) 2016
ref128
ref129
ref97
ref126
ref96
ref127
Papamakarios (ref232); 30
ref99
ref124
ref245
ref98
ref125
Lee (ref254) 2007; 20
ref93
ref133
Song (ref235) 2020
Shabaninia (ref293) 2022
ref92
ref134
ref255
ref95
ref131
ref94
ref132
ref250
ref130
ref251
ref91
Radford (ref238) 2019; 1
ref90
ref89
ref139
ref86
ref137
ref258
ref85
ref138
ref259
ref88
ref135
ref256
ref87
ref136
ref257
Sønderby (ref225)
ref82
ref144
ref81
ref145
ref84
ref263
ref83
ref143
ref264
ref140
Kingma (ref233)
ref261
ref141
ref262
ref80
Zou (ref265) 2023
ref260
ref79
ref108
ref78
ref109
ref106
ref107
ref75
ref104
Zhang (ref67) 2023
ref74
ref105
ref77
ref102
ref76
ref103
Tolstikhin (ref222)
Nemati (ref48) 2023
ref71
ref111
ref70
ref112
ref73
ref72
ref110
Zhang (ref193) 2018
Estiri (ref44) 2020
ref68
ref119
Karras (ref210) 2017
ref117
ref69
ref118
ref64
ref115
ref236
ref63
ref116
ref237
ref66
ref113
ref65
ref114
Welling (ref252)
Rezende (ref227)
Li (ref284); 35
ref60
ref122
ref243
ref123
ref62
ref120
ref61
Li (ref281) 2018
ref168
ref289
ref169
Kim (ref277) 2018
Bowles (ref192) 2018
ref170
Larochelle (ref246)
ref177
ref298
ref178
ref299
ref175
ref296
ref176
ref297
ref173
ref294
ref174
ref171
ref292
ref172
ref179
ref180
Larsen (ref228)
ref181
Box (ref244) 2015
ref188
ref189
ref186
ref187
Ivanov (ref223)
ref184
Kingma (ref229); 31
ref185
ref182
ref183
ref148
ref149
ref146
ref267
ref147
ref268
Brown (ref239); 33
ref155
Radford (ref208) 2015
ref156
ref153
ref274
ref275
ref151
ref272
ref152
ref270
ref150
ref271
ref159
ref157
ref278
ref158
ref166
ref287
ref167
ref288
ref164
ref285
ref165
ref286
ref162
ref283
ref163
ref160
ref161
Chen (ref276) 2018
ref282
ref13
ref12
ref15
ref14
ref11
ref10
ref17
ref16
Ho (ref234) 2020; 33
Papamakarios (ref279) 2021; 22
Sorzano (ref197) 2014
Ho (ref203)
Sallab (ref280) 2019
Metz (ref205)
Spinner (ref273)
Piantadosi (ref269) 2022
Liu (ref18) 2023
Yang (ref121)
Dinh (ref230) 2016
Germain (ref247)
Tschantz (ref201) 2020
ref2
ref1
Smith (ref242) 2022
ref191
ref190
ref199
ref198
ref195
Van Den Oord (ref224)
ref196
Van Den Oord (ref248)
Liu (ref142) 2022
Raffel (ref241) 2019
Song (ref35)
Cheng (ref290) 2023
Bariah (ref291) 2022
Sohn (ref226)
Springenberg (ref215) 2015
References_xml – volume: 30
  start-page: 1
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref232
  article-title: Masked autoregressive flow for density estimation
– ident: ref55
  doi: 10.1109/TCCN.2023.3279260
– ident: ref176
  doi: 10.1007/978-0-387-21579-2_9
– ident: ref299
  doi: 10.1016/j.ins.2020.04.019
– ident: ref151
  doi: 10.1109/TMC.2021.3075083
– ident: ref200
  doi: 10.1109/ACCESS.2020.2991337
– ident: ref71
  doi: 10.1109/MILCOM.2018.8599782
– ident: ref116
  doi: 10.1109/IWCMC.2019.8766353
– ident: ref109
  doi: 10.1109/CBD.2014.41
– ident: ref66
  doi: 10.1109/TCOMM.2020.3031930
– ident: ref133
  doi: 10.1109/TETCI.2019.2948058
– ident: ref263
  doi: 10.1109/ICCSN52437.2021.9463629
– ident: ref272
  doi: 10.1109/LCOMM.2021.3132947
– ident: ref83
  doi: 10.1109/ICC42927.2021.9500893
– ident: ref188
  doi: 10.1109/MCOM.001.1900509
– ident: ref90
  doi: 10.1109/GLOBECOM42002.2020.9322583
– ident: ref220
  doi: 10.48550/arXiv.1312.6114
– ident: ref4
  doi: 10.1109/MWC.101.2100269
– ident: ref124
  doi: 10.1109/TNNLS.2020.3010724
– year: 2023
  ident: ref18
  article-title: Deep generative model and its applications in efficient wireless network management: A tutorial and case study
  publication-title: arXiv:2303.17114
– year: 2020
  ident: ref235
  article-title: Score-based generative modeling through stochastic differential equations
  publication-title: arXiv:2011.13456
– year: 2018
  ident: ref240
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
  publication-title: arXiv:1810.04805
– ident: ref112
  doi: 10.1109/JIOT.2022.3211346
– ident: ref196
  doi: 10.1080/02564602.2014.987328
– year: 2023
  ident: ref266
  article-title: Large Generative AI model for telecom: The next big thing?
  publication-title: arXiv:2306.10249
– ident: ref144
  doi: 10.1109/TWC.2017.2782690
– ident: ref39
  doi: 10.1109/ACCESS.2018.2815741
– ident: ref187
  doi: 10.1016/j.eswa.2022.117163
– ident: ref79
  doi: 10.1145/3143361.3143393
– year: 2014
  ident: ref197
  article-title: A survey of dimensionality reduction techniques
  publication-title: arXiv:1403.2877
– ident: ref29
  doi: 10.1109/TWC.2021.3103971
– ident: ref81
  doi: 10.1109/GLOBECOM54140.2023.10437200
– ident: ref88
  doi: 10.1109/CISCE55963.2022.9851065
– ident: ref2
  doi: 10.1038/s41928-019-0355-6
– volume: 1
  start-page: 9
  issue: 8
  year: 2019
  ident: ref238
  article-title: Language models are unsupervised multitask learners
  publication-title: OpenAI Blog
– ident: ref143
  doi: 10.1109/ACCESS.2019.2921522
– ident: ref170
  doi: 10.1109/jproc.2020.2998530
– ident: ref152
  doi: 10.1109/TWC.2019.2921955
– ident: ref213
  doi: 10.1109/CVPR.2018.00916
– ident: ref12
  doi: 10.1109/MCOM.004.2200136
– ident: ref60
  doi: 10.1109/JSAC.2019.2959185
– volume-title: Proc. Workshop Vis. AI Explain.
  ident: ref273
  article-title: Towards an interpretable latent space: An intuitive comparison of autoencoders with variational autoencoders
– ident: ref260
  doi: 10.1109/TCOMM.2018.2879508
– ident: ref303
  doi: 10.1145/3491209
– ident: ref169
  doi: 10.1109/MNET.001.1900287
– ident: ref14
  doi: 10.1109/TCOMM.2019.2924010
– ident: ref216
  doi: 10.1109/ICCV.2017.304
– ident: ref261
  doi: 10.1109/ACCESS.2017.2760350
– ident: ref218
  doi: 10.1109/CVPR42600.2020.00813
– ident: ref5
  doi: 10.1109/MNET.011.2000493
– start-page: 1
  volume-title: Proc. NIPS
  ident: ref35
  article-title: Blind channel equalization using vector-quantized variational autoencoders
– volume-title: Time Series Analysis: Forecasting and Control
  year: 2015
  ident: ref244
– ident: ref45
  doi: 10.1109/ISIT.2019.8849476
– ident: ref84
  doi: 10.1109/CSNDSP54353.2022.9907905
– ident: ref174
  doi: 10.1109/mwc.019.2100721
– ident: ref207
  doi: 10.1109/iccv.2017.244
– ident: ref180
  doi: 10.1109/ACCESS.2022.3195299
– ident: ref259
  doi: 10.1109/MVT.2020.3017152
– ident: ref164
  doi: 10.1136/svn-2017-000101
– ident: ref34
  doi: 10.1109/TWC.2022.3220784
– ident: ref62
  doi: 10.3390/telecom2010009
– ident: ref179
  doi: 10.1109/icc45855.2022.9839142
– year: 2015
  ident: ref208
  article-title: Unsupervised representation learning with deep convolutional generative adversarial networks
  publication-title: arXiv:1511.06434
– year: 2018
  ident: ref277
  article-title: FloWaveNet: A generative flow for raw audio
  publication-title: arXiv:1811.02155
– ident: ref7
  doi: 10.1109/MCOM.006.2200480
– ident: ref21
  doi: 10.1109/TII.2022.3155656
– ident: ref9
  doi: 10.1109/MCOM.001.1900698
– ident: ref52
  doi: 10.1016/j.dsp.2021.103188
– ident: ref76
  doi: 10.1109/INFOCOM.2019.8737631
– ident: ref41
  doi: 10.1109/ICCT.2018.8600032
– year: 2022
  ident: ref291
  article-title: The interplay of ai and digital twin: Bridging the gap between data-driven and model-driven approaches
  publication-title: arXiv:2209.12423
– ident: ref173
  doi: 10.1109/jsac.2021.3126076
– ident: ref214
  doi: 10.1109/CVPR.2017.202
– ident: ref6
  doi: 10.1109/COMST.2014.2329501
– ident: ref178
  doi: 10.1109/TSMCC.2009.2038279
– ident: ref100
  doi: 10.1007/978-3-030-64793-3_1
– ident: ref297
  doi: 10.1109/ACCESS.2019.2917207
– ident: ref162
  doi: 10.1145/3285029
– ident: ref148
  doi: 10.1109/LWC.2023.3263224
– start-page: 1530
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref227
  article-title: Variational inference with normalizing flows
– start-page: 881
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref247
  article-title: MADE: Masked autoencoder for distribution estimation
– ident: ref165
  doi: 10.1109/MCOM.2019.1900271
– ident: ref77
  doi: 10.1109/ACCESS.2019.2919996
– year: 2019
  ident: ref241
  article-title: Exploring the limits of transfer learning with a unified text-to-text transformer
  publication-title: arXiv:1910.10683
– year: 2023
  ident: ref19
  article-title: Unleashing the power of edge-cloud generative ai in mobile networks: A survey of AIGC services
  publication-title: arXiv:2303.16129
– ident: ref74
  doi: 10.1109/PRDC50213.2020.00018
– start-page: 3745
  volume-title: Proc. 30th Int. Conf. Neural Inf. Process. Syst.
  ident: ref225
  article-title: Ladder variational autoencoders
– ident: ref274
  doi: 10.1109/TNNLS.2020.3011671
– ident: ref20
  doi: 10.1016/j.comnet.2021.108149
– ident: ref117
  doi: 10.1109/TC.2013.13
– year: 2018
  ident: ref281
  article-title: Anomaly detection with generative adversarial networks for multivariate time series
  publication-title: arXiv:1809.04758
– ident: ref33
  doi: 10.1109/WCNC51071.2022.9771907
– year: 2018
  ident: ref276
  article-title: When provably secure steganography meets generative models
  publication-title: arXiv:1811.03732
– ident: ref73
  doi: 10.1109/IEMCON.2019.8936224
– ident: ref288
  doi: 10.1109/tip.2023.3273451
– ident: ref283
  doi: 10.1007/s11004-021-09934-0
– ident: ref87
  doi: 10.1109/ICC45855.2022.9838574
– ident: ref135
  doi: 10.1109/WCNC49053.2021.9417513
– ident: ref167
  doi: 10.1145/3229556.3229562
– ident: ref245
  doi: 10.1016/0004-3702(92)90065-6
– ident: ref46
  doi: 10.1109/spawc48557.2020.9154331
– ident: ref36
  doi: 10.1109/ICCW.2018.8403666
– ident: ref175
  doi: 10.1007/BF00058655
– start-page: 2180
  volume-title: Proc. 30th Int. Conf. Neural Inf. Process. Syst.
  ident: ref212
  article-title: InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets
– volume: 31
  start-page: 1
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref229
  article-title: Glow: Generative flow with invertible 1x1 convolutions
– ident: ref237
  doi: 10.48550/ARXIV.1706.03762
– ident: ref91
  doi: 10.1109/ICCW.2018.8403655
– year: 2022
  ident: ref293
  article-title: Transformers in action recognition: A review on temporal modeling
  publication-title: arXiv:2302.01921
– ident: ref38
  doi: 10.1145/3395352.3402622
– start-page: 214
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref209
  article-title: Wasserstein generative adversarial networks
– ident: ref302
  doi: 10.3390/app12168085
– year: 2016
  ident: ref230
  article-title: Density estimation using real NVP
  publication-title: arXiv:1605.08803
– ident: ref198
  doi: 10.1109/TPAMI.2013.50
– ident: ref262
  doi: 10.1109/TCCN.2023.3288108
– ident: ref22
  doi: 10.1007/s12243-023-00980-9
– ident: ref119
  doi: 10.1109/GLOBECOM38437.2019.9014102
– ident: ref139
  doi: 10.1109/BMSB53066.2021.9547015
– ident: ref300
  doi: 10.1145/3439729
– volume-title: All-in-one: VQ-VAE for end-to-end joint source-channel coding
  year: 2023
  ident: ref48
– ident: ref93
  doi: 10.1109/LWC.2021.3081509
– start-page: 1481
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref252
  article-title: Exponential family harmoniums with an application to information retrieval
– ident: ref202
  doi: 10.1016/j.eswa.2021.115680
– volume: 22
  start-page: 2617
  issue: 1
  year: 2021
  ident: ref279
  article-title: Normalizing flows for probabilistic modeling and inference
  publication-title: J. Mach. Learn. Res.
– ident: ref89
  doi: 10.1109/ICSP48669.2020.9320987
– ident: ref30
  doi: 10.1109/TWC.2020.3047100
– ident: ref158
  doi: 10.1364/AOP.361502
– ident: ref28
  doi: 10.1109/ICC42927.2021.9501056
– year: 2020
  ident: ref44
  article-title: A variational autoencoder approach for image transmission in wireless channel
  publication-title: arXiv:2010.03967
– ident: ref163
  doi: 10.1016/b978-0-7506-7531-4.x5000-3
– ident: ref156
  doi: 10.1016/j.phycom.2019.100900
– year: 2023
  ident: ref265
  article-title: Wireless multi-agent generative AI: From connected intelligence to collective intelligence
  publication-title: arXiv:2307.02757
– year: 2023
  ident: ref290
  article-title: Bifidelity variational auto-encoder for uncertainty quantification
  publication-title: arXiv:2305.16530
– ident: ref27
  doi: 10.1109/ACSSC.2018.8645463
– ident: ref10
  doi: 10.1109/TWC.2022.3219140
– year: 2022
  ident: ref142
  article-title: ViFi-Loc: Multi-modal pedestrian localization using GAN with camera-phone correspondences
  publication-title: arXiv:2211.12021
– ident: ref75
  doi: 10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00141
– ident: ref185
  doi: 10.1007/s11276-021-02781-1
– ident: ref236
  doi: 10.1162/NECO_a_00142
– ident: ref82
  doi: 10.1109/MILCOM47813.2019.9020907
– start-page: 29
  volume-title: Proc. 14th Int. Conf. Artif. Intell. Statist.
  ident: ref246
  article-title: The neural autoregressive distribution estimator
– ident: ref298
  doi: 10.1109/WCNC51071.2022.9771710
– ident: ref282
  doi: 10.1109/WACV51458.2022.00188
– ident: ref270
  doi: 10.18653/v1/W18-5446
– year: 2022
  ident: ref269
  article-title: Meaning without reference in large language models
  publication-title: arXiv:2208.02957
– ident: ref98
  doi: 10.1109/JSEN.2021.3105404
– ident: ref268
  doi: 10.1109/SNAMS60348.2023.10375400
– ident: ref50
  doi: 10.1145/3324921.3328782
– ident: ref153
  doi: 10.1109/TWC.2020.3039013
– ident: ref181
  doi: 10.1109/CCNC51644.2023.10060056
– volume: 35
  start-page: 23009
  volume-title: Proc. 35th Adv. Neural Inf. Process. Syst.
  ident: ref284
  article-title: Generative time series forecasting with diffusion, denoise, and disentanglement
– ident: ref13
  doi: 10.1109/MWC.001.1900534
– ident: ref32
  doi: 10.1109/CCAAW.2019.8904907
– year: 2017
  ident: ref210
  article-title: Progressive growing of GANs for improved quality, stability, and variation
  publication-title: arXiv:1710.10196
– start-page: 6309
  volume-title: Proc. 31st Int. Conf. Neural Inf. Process. Syst.
  ident: ref224
  article-title: Neural discrete representation learning
– year: 2023
  ident: ref67
  article-title: Generative ai-enabled vehicular networks: Fundamentals, framework, and case study
  publication-title: arXiv:2304.11098
– ident: ref217
  doi: 10.1109/TPAMI.2020.2970919
– ident: ref267
  doi: 10.1145/3331184.3331303
– ident: ref99
  doi: 10.1109/TCCN.2020.2970693
– ident: ref146
  doi: 10.1109/LNET.2022.3193766
– ident: ref96
  doi: 10.1109/WCNC.2019.8885548
– ident: ref140
  doi: 10.1109/ICPAI51961.2020.00012
– ident: ref255
  doi: 10.1162/neco.2006.18.7.1527
– ident: ref68
  doi: 10.1145/3269206.3269294
– ident: ref184
  doi: 10.1109/MVT.2020.3015184
– ident: ref182
  doi: 10.1109/twc.2023.3347419
– ident: ref256
  doi: 10.1109/LWC.2018.2843359
– ident: ref131
  doi: 10.1109/JSEN.2019.2958201
– start-page: 3483
  volume-title: Proc. 28th Int. Conf. Neural Inf. Process. Syst.
  ident: ref226
  article-title: Learning structured output representation using deep conditional generative models
– ident: ref43
  doi: 10.1109/JSAC.2023.3288243
– year: 2015
  ident: ref215
  article-title: Unsupervised and semi-supervised learning with categorical generative adversarial networks
  publication-title: arXiv:1511.06390
– ident: ref61
  doi: 10.1109/ICC.2019.8761755
– ident: ref122
  doi: 10.1109/LCOMM.2020.2988384
– ident: ref130
  doi: 10.1109/ECTI-CON54298.2022.9795409
– ident: ref289
  doi: 10.1609/aaai.v34i03.5659
– ident: ref15
  doi: 10.1109/COMST.2019.2904897
– ident: ref24
  doi: 10.1109/TCCN.2022.3153004
– ident: ref64
  doi: 10.1109/ICCNC.2019.8685527
– ident: ref16
  doi: 10.5555/2969033.2969125
– ident: ref78
  doi: 10.1016/j.comnet.2021.108535
– ident: ref42
  doi: 10.3390/s18113913
– volume-title: Orbital Debris and Near-Earth Environmental Management: A Chronology
  year: 1993
  ident: ref154
– ident: ref101
  doi: 10.1109/GLOBECOM42002.2020.9348244
– ident: ref132
  doi: 10.1109/GLOCOMW.2018.8644149
– ident: ref149
  doi: 10.1109/MCOM.2016.7470933
– ident: ref250
  doi: 10.48550/arXiv.1609.03499
– start-page: 1558
  volume-title: Proc. 33rd Int. Conf. Int. Conf. Mach. Learn.
  ident: ref228
  article-title: Autoencoding beyond pixels using a learned similarity metric
– ident: ref56
  doi: 10.1109/GLOCOMW.2018.8644250
– ident: ref189
  doi: 10.1016/j.measurement.2021.108974
– start-page: 1747
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref248
  article-title: Pixel recurrent neural networks
– ident: ref294
  doi: 10.1109/TPAMI.2021.3116668
– ident: ref157
  doi: 10.1109/TWC.2019.2951416
– ident: ref278
  doi: 10.1109/TCDS.2022.3176977
– ident: ref92
  doi: 10.1109/TCCN.2018.2884910
– ident: ref141
  doi: 10.1007/978-981-15-8462-6_96
– volume: 33
  start-page: 6840
  year: 2020
  ident: ref234
  article-title: Denoising diffusion probabilistic models
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: ref59
  doi: 10.1109/GLOBECOM38437.2019.9014217
– ident: ref102
  doi: 10.1109/ACCESS.2021.3132127
– ident: ref54
  doi: 10.1109/TCOMM.2007.892447
– ident: ref296
  doi: 10.1109/OJCOMS.2023.3320646
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Represent.
  ident: ref221
  article-title: Beta-VAE: Learning basic visual concepts with a constrained variational framework
– ident: ref150
  doi: 10.1109/TCCN.2021.3105133
– volume: 20
  start-page: 1
  year: 2007
  ident: ref254
  article-title: Sparse deep belief net model for visual area V2
  publication-title: Proc. Adv. Neural Inf. Process. Syst.
– ident: ref57
  doi: 10.23919/EUSIPCO.2018.8553233
– ident: ref126
  doi: 10.1109/TETCI.2019.2892748
– ident: ref301
  doi: 10.1609/aaai.v33i01.3301541
– ident: ref8
  doi: 10.1109/TWC.2021.3124202
– ident: ref40
  doi: 10.1177/1548512921991245
– year: 2020
  ident: ref201
  article-title: Reinforcement learning through active inference
  publication-title: arXiv:2002.12636
– year: 2019
  ident: ref280
  article-title: LiDAR sensor modeling and data augmentation with GANs for autonomous driving
  publication-title: arXiv:1905.07290
– ident: ref65
  doi: 10.1109/LWC.2021.3075467
– ident: ref123
  doi: 10.1109/SPW.2018.00019
– ident: ref285
  doi: 10.1109/BigData47090.2019.9005997
– ident: ref53
  doi: 10.1016/j.adhoc.2020.102151
– ident: ref94
  doi: 10.1145/3324921.3329695
– ident: ref49
  doi: 10.1109/ICC.2018.8422223
– ident: ref159
  doi: 10.22331/q-2018-08-06-79
– ident: ref168
  doi: 10.1109/JIOT.2016.2579198
– ident: ref3
  doi: 10.1109/COMST.2023.3249835
– ident: ref128
  doi: 10.1109/ACCESS.2021.3095546
– ident: ref134
  doi: 10.1109/ICTC52510.2021.9621134
– ident: ref118
  doi: 10.1109/JIOT.2020.3024800
– ident: ref113
  doi: 10.1016/j.adhoc.2020.102177
– ident: ref286
  doi: 10.1007/978-3-031-19842-7_39
– ident: ref190
  doi: 10.1109/ACCESS.2022.3161511
– ident: ref63
  doi: 10.1109/LWC.2019.2947041
– ident: ref172
  doi: 10.1109/IOTM.001.2100209
– ident: ref47
  doi: 10.1109/JSAC.2021.3078489
– start-page: 4790
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref249
  article-title: Conditional image generation with pixelCNN decoders
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Represent.
  ident: ref223
  article-title: Variational autoencoder with arbitrary conditioning
– ident: ref25
  doi: 10.1109/ACCESS.2023.3296707
– ident: ref111
  doi: 10.1016/j.future.2022.01.026
– ident: ref129
  doi: 10.1109/ACCESS.2022.3187837
– ident: ref195
  doi: 10.1056/NEJMoa1210384
– ident: ref177
  doi: 10.1023/B:MACH.0000015881.36452.6e
– volume: 33
  start-page: 1
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref239
  article-title: Language models are few-shot learners
– year: 2021
  ident: ref194
  article-title: Learning disentangled representation by exploiting pretrained generative models: A contrastive learning view
  publication-title: arXiv:2102.10543
– ident: ref108
  doi: 10.1109/TCYB.2022.3163811
– ident: ref125
  doi: 10.1145/3468691.3468742
– ident: ref243
  doi: 10.1098/rsta.1927.0007
– year: 2016
  ident: ref211
  article-title: Adversarial feature learning
  publication-title: arXiv:1605.09782
– ident: ref103
  doi: 10.3390/s22218085
– ident: ref257
  doi: 10.1109/ICCWorkshops50388.2021.9473497
– ident: ref58
  doi: 10.1109/GLOBECOM48099.2022.10001178
– year: 2022
  ident: ref295
  article-title: A survey on generative diffusion model
  publication-title: arXiv:2209.02646
– ident: ref120
  doi: 10.1109/compsac48688.2020.0-218
– start-page: 1
  volume-title: Proc. 30th Conf. Neural Inf. Process. Syst.
  ident: ref203
  article-title: Generative adversarial imitation learning
– year: 2020
  ident: ref219
  article-title: Brainstorming generative adversarial networks (BGANs): Towards multi-agent generative models with distributed private datasets
  publication-title: arXiv:2002.00306
– year: 2022
  ident: ref242
  article-title: Using deepSpeed and Megatron to train Megatronturing NLG 530B, a large-scale generative language model
  publication-title: arXiv:2201.11990
– ident: ref11
  doi: 10.1109/TWC.2020.3046766
– ident: ref23
  doi: 10.1145/3459992
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Represent.
  ident: ref222
  article-title: Wasserstein auto-encoders
– year: 2014
  ident: ref231
  article-title: NICE: Non-linear independent components estimation
  publication-title: arXiv:1410.8516
– ident: ref166
  doi: 10.1109/access.2021.3130418
– ident: ref31
  doi: 10.1109/ICCNC.2019.8685573
– ident: ref51
  doi: 10.1109/RADAR.2018.8378737
– ident: ref138
  doi: 10.1109/IPIN54987.2022.9918146
– start-page: 4743
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref233
  article-title: Improved variational inference with inverse autoregressive flow
– ident: ref95
  doi: 10.1109/TCCN.2020.3010330
– start-page: 1743
  volume-title: Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.
  ident: ref121
  article-title: Attack-resilient connectivity game for UAV networks using generative adversarial learning
– ident: ref292
  doi: 10.1109/MCOM.001.2200866
– ident: ref105
  doi: 10.1109/MILCOM55135.2022.10017520
– ident: ref97
  doi: 10.3390/electronics12010084
– ident: ref127
  doi: 10.1109/BalkanCom53780.2021.9593240
– ident: ref104
  doi: 10.1109/WCNC51071.2022.9771754
– ident: ref136
  doi: 10.1109/ICC.2018.8423008
– ident: ref171
  doi: 10.1109/jiot.2021.3098028
– start-page: 1
  volume-title: Proc. ICLR
  ident: ref205
  article-title: Unrolled generative adversarial networks
– ident: ref287
  doi: 10.1109/TPAMI.2020.2992934
– ident: ref80
  doi: 10.1186/s13638-021-01950-2
– ident: ref70
  doi: 10.23919/JCC.2020.02.002
– ident: ref147
  doi: 10.1109/LCOMM.2022.3172171
– ident: ref155
  doi: 10.1109/COMST.2015.2476474
– year: 2014
  ident: ref206
  article-title: Conditional generative adversarial nets
  publication-title: arXiv:1411.1784
– ident: ref85
  doi: 10.1109/JIOT.2022.3213593
– ident: ref17
  doi: 10.1109/MCOM.2019.1800635
– ident: ref114
  doi: 10.1109/INFOCOMWKSHPS51825.2021.9484569
– ident: ref264
  doi: 10.1109/GLOBECOM54140.2023.10437725
– ident: ref37
  doi: 10.1109/JSAC.2022.3191346
– ident: ref186
  doi: 10.1109/MTTW51045.2020.9245065
– ident: ref1
  doi: 10.1109/comst.2016.2532458
– year: 2018
  ident: ref192
  article-title: GAN augmentation: Augmenting training data using generative adversarial networks
  publication-title: arXiv:1810.10863
– ident: ref26
  doi: 10.1109/COMST.2021.3136132
– ident: ref145
  doi: 10.1109/COMST.2022.3223224
– ident: ref161
  doi: 10.1109/MNET.011.2000195
– year: 2018
  ident: ref193
  article-title: Missing value imputation based on deep generative models
  publication-title: arXiv:1808.01684
– ident: ref69
  doi: 10.1109/UkrMiCo43733.2018.9047611
– ident: ref110
  doi: 10.1109/PST.2018.8514157
– ident: ref183
  doi: 10.1109/MNET.2019.1800439
– ident: ref191
  doi: 10.1016/j.array.2022.100142
– ident: ref107
  doi: 10.1109/MWC.004.2100362
– ident: ref137
  doi: 10.1109/GLOBECOM42002.2020.9322456
– ident: ref275
  doi: 10.1145/3626235
– ident: ref251
  doi: 10.1162/089976602760128018
– ident: ref115
  doi: 10.1109/UEMCON.2018.8796769
– ident: ref258
  doi: 10.1109/TCOMM.2019.2927561
– ident: ref160
  doi: 10.1109/msp.2017.3151326
– start-page: 1339
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref253
  article-title: 3D object recognition with deep belief nets
– ident: ref271
  doi: 10.1109/CVPR.2017.632
– ident: ref72
  doi: 10.1109/ACCESS.2022.3177906
– ident: ref199
  doi: 10.1109/JPROC.2020.3004555
– year: 2016
  ident: ref204
  article-title: NIPS 2016 tutorial: Generative adversarial networks
  publication-title: arXiv:1701.00160
– ident: ref86
  doi: 10.1109/TCCN.2019.2948919
– ident: ref106
  doi: 10.1109/LWC.2018.2867459
SSID ssj0002511134
Score 2.555837
Snippet As we transition from the 5G epoch, a new horizon beckons with the advent of 6G, seeking a profound fusion with novel communication paradigms and emerging...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2433
SubjectTerms 6G mobile communication
adversarial ML
AI-generated content
Antenna arrays
Artificial intelligence
artificial intelligence (AI)
autoregressive generative models
Autoregressive models
Communication system security
Communications traffic
Data models
deep learning (DL)
Design optimization
diffusion models
Digital twins
discriminative AI
Edge computing
explainable AI
extremely large antenna arrays
Generative adversarial networks
generative AI
Generative artificial intelligence
generative models
generative pre-trained transformers
generative transformers
holographic beamforming
integrated sensing and communications
Large language models
Machine learning
machine learning (ML)
mMIMO
mmWave
Mobile computing
Near field communication
network function virtualization
Network management systems
normalizing flows
open RAN
semantic communications
software defined networks
Surveys
Taxonomy
Technical papers
terahertz
trustworthy AI
variational autoencoders
Wireless communication
zero-touch service management
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwELYQ4lAOqFAQ29JqDj024MSzeXDbUpZuxUsCJG6WX5GQIFvtC_XfdyYJqyAkuHCLLCdOZsafv0mcb4T4br23UqkiMia1EcYB6YiVEaVRLGFFSVft6dPs_Dy_vS0uO6W-eE9YIw_cGI631fjc0EIaB4UGieDkfYsupHGQRVn_QZ1QYyeZYgxm4hwrbGWGYlkcXPw5uji7ooQwwX1FqJ1k8bOlqFbsb0usvMDlerEZfhQbLUuEQXN3m2IlVFtivaMd-En4wQyIvMEv81jBuIRGP5rBCwYjOJ6YQxjANSsUUIRFbv4QXc0ni_APxhUQssGQlQu4DjbcVZCeAG-DvSfYg1FHpHNb3AyPr49-R23JhMhRojaLjCxTg0EFi954Yx3hR2LRZGhtYoP3JZkSHRaYeSxDv3Q1JSAOSPOyr7zaEavVuAq7AoIn5liqzJSORdWcMcQO80L2c5k5ZVxPJE_W067VE-eyFve6zitkoRuTaza5bk3eEz-WJ_1t5DRe7_6T3bLsylrYdQNFiG4jRL8VIT2xzU7tjId87bQn9p68rNuJO9X81RGJE8v083uM_UV84Odp3tnsidXZZB6-ijW3mN1NJ9_qmP0PrwLrwA
  priority: 102
  providerName: Directory of Open Access Journals
Title At the Dawn of Generative AI Era: A Tutorial-cum-Survey on New Frontiers in 6G Wireless Intelligence
URI https://ieeexplore.ieee.org/document/10422716
https://www.proquest.com/docview/3049497706
https://doaj.org/article/addd8a0631e34a408085b4ce61e09f31
Volume 5
WOSCitedRecordID wos001214542600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2644-125X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511134
  issn: 2644-125X
  databaseCode: DOA
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2644-125X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002511134
  issn: 2644-125X
  databaseCode: M~E
  dateStart: 20200101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwELZoxQEOPIu6UKo5cCTFib1xwm0pu1BEW6QWqTfLj4lUqcqi7W4RF347M467WoRA4hJZkZ04-ezxN358I8QrH6OXSrWFc7UvdImaUqyMKJ1iCStyuhLSn83JSXNx0X7Jh9XTWRhETJvP8ICTaS0_zsOKp8qoh-uqIoK_JbaMMcNhrfWECnPlUumsLFTK9s3pp8PT4zPyASt9oMhQV6b8bfRJIv05qsofpjiNL7OH_1mzR-JBJpIwGZB_LO5g_0Tc35AXfCriZAnE7-C9-97DvINBYprtG0yOYLpwb2EC5yxiQI2woHcUZ6vFDf6AeQ9k_GDG4gYcKhsue6g_AO-UvSLLCEcbOp474utsen74schRFYpAvtyycLKrnUaFXkcXnQ9kYiqvndHeVx5j7BzRlKBbbaLucNyFxBqIJlLXHauonontft7jrgCMRC47ZVwXWHctOEcEsmnluJEmKBdGorr92zZkyXGOfHFlk-shWztAZBkimyEaidfrQt8GxY1_Z3_HMK6zslx2ukH42Nz7LBnx2NBnqRKVdppYcjP2OmBdomw7RQ_ZYUw33jfAORJ7t63C5r59bXlhUhNtlvXzvxR7Ie5xFYeZmj2xvVys8KW4G26Wl9eL_eT20_X453Q_NeFf1gLrgQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bTxQxFG4QTNQHUcG4CNgHHx3sTM_ceFuRhdVlMWFJeGt6m4SEzJplF-O_95xO2awhkvjWTNppZ76e06-37zD20ThnhJR1onVhEkg9YIqUEYWWJGGFk66A9Kgcj6urq_pHvKwe7sJ478PhM39AybCX76Z2QUtlaOGQZUjwn7CNHCBLu-tayyUVYsuphKgtlIr68_m3o_OzC5wFZnAg0VVnZfrX-BNk-mNclQfOOIwwg83_bNsr9jJSSd7vsH_N1nz7hr1YERjcYq4_58jw-Ff9q-XThnci0-TheH_Ij2f6kPf5hGQMsBsmWEdysZjd-d982nJ0f3xA8gYULJtft7w44XRW9gZ9Ix-uKHlus8vB8eToNIlxFRKLs7l5okVTaPDSG3DaaWPRyWQGdAnGZMY712gkKhZqKB00Pm9s4A1IFNF4c-nkW7beTlv_jnHvkF42stSNJeU1qzVSyKoWeSVKK7Xtsez-bysbRccp9sWNCpMPUasOIkUQqQhRj31aFvrZaW48nv0LwbjMSoLZ4QHio6L9KXTjrsLPkqmXoAF5cpUbsL5IvagbiS_ZJkxX6uvg7LHd-16honXfKtqaBCTOotj5R7EP7Nnp5GykRsPx9_fsOTW3W7fZZevz2cLvsaf2bn59O9sPXfgPIODsog
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=At+the+Dawn+of+Generative+AI+Era%3A+A+Tutorial-cum-Survey+on+New+Frontiers+in+6G+Wireless+Intelligence&rft.jtitle=IEEE+open+journal+of+the+Communications+Society&rft.au=Celik%2C+Abdulkadir&rft.au=Eltawil%2C+Ahmed+M.&rft.date=2024&rft.pub=IEEE&rft.eissn=2644-125X&rft.volume=5&rft.spage=2433&rft.epage=2489&rft_id=info:doi/10.1109%2FOJCOMS.2024.3362271&rft.externalDocID=10422716
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2644-125X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2644-125X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2644-125X&client=summon