A Survey on Generative Diffusion Models

Deep generative models have unlocked another profound realm of human creativity. By capturing and generalizing patterns within data, we have entered the epoch of all-encompassing Artificial Intelligence for General Creativity (AIGC). Notably, diffusion models, recognized as one of the paramount gene...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on knowledge and data engineering Jg. 36; H. 7; S. 2814 - 2830
Hauptverfasser: Cao, Hanqun, Tan, Cheng, Gao, Zhangyang, Xu, Yilun, Chen, Guangyong, Heng, Pheng-Ann, Li, Stan Z.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.07.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1041-4347, 1558-2191
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Deep generative models have unlocked another profound realm of human creativity. By capturing and generalizing patterns within data, we have entered the epoch of all-encompassing Artificial Intelligence for General Creativity (AIGC). Notably, diffusion models, recognized as one of the paramount generative models, materialize human ideation into tangible instances across diverse domains, encompassing imagery, text, speech, biology, and healthcare. To provide advanced and comprehensive insights into diffusion, this survey comprehensively elucidates its developmental trajectory and future directions from three distinct angles: the fundamental formulation of diffusion, algorithmic enhancements, and the manifold applications of diffusion. Each layer is meticulously explored to offer a profound comprehension of its evolution. Structured and summarized approaches are presented here.
AbstractList Deep generative models have unlocked another profound realm of human creativity. By capturing and generalizing patterns within data, we have entered the epoch of all-encompassing Artificial Intelligence for General Creativity (AIGC). Notably, diffusion models, recognized as one of the paramount generative models, materialize human ideation into tangible instances across diverse domains, encompassing imagery, text, speech, biology, and healthcare. To provide advanced and comprehensive insights into diffusion, this survey comprehensively elucidates its developmental trajectory and future directions from three distinct angles: the fundamental formulation of diffusion, algorithmic enhancements, and the manifold applications of diffusion. Each layer is meticulously explored to offer a profound comprehension of its evolution. Structured and summarized approaches are presented here.
Author Xu, Yilun
Heng, Pheng-Ann
Tan, Cheng
Cao, Hanqun
Li, Stan Z.
Chen, Guangyong
Gao, Zhangyang
Author_xml – sequence: 1
  givenname: Hanqun
  orcidid: 0000-0002-8104-1845
  surname: Cao
  fullname: Cao, Hanqun
  email: 1155141481@link.cuhk.edu.hk
  organization: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China
– sequence: 2
  givenname: Cheng
  orcidid: 0000-0002-8639-923X
  surname: Tan
  fullname: Tan, Cheng
  email: tancheng@westlake.edu.cn
  organization: AI Lab, School of Engineering, Westlake University, Hangzhou, Zhejiang, China
– sequence: 3
  givenname: Zhangyang
  orcidid: 0000-0003-1026-6083
  surname: Gao
  fullname: Gao, Zhangyang
  email: gaozhangyang@westlake.edu.cn
  organization: AI Lab, School of Engineering, Westlake University, Hangzhou, Zhejiang, China
– sequence: 4
  givenname: Yilun
  orcidid: 0000-0001-7194-9481
  surname: Xu
  fullname: Xu, Yilun
  email: ylxu@mit.edu
  organization: Massachusetts Institute of Technology, Cambridge, MA, USA
– sequence: 5
  givenname: Guangyong
  orcidid: 0000-0002-5892-8608
  surname: Chen
  fullname: Chen, Guangyong
  email: gychen@zhejianglab.com
  organization: Zhejiang Lab, Hangzhou, Zhejiang, China
– sequence: 6
  givenname: Pheng-Ann
  orcidid: 0000-0003-3055-5034
  surname: Heng
  fullname: Heng, Pheng-Ann
  email: pheng@cse.cuhk.edu.hk
  organization: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China
– sequence: 7
  givenname: Stan Z.
  orcidid: 0000-0002-2961-8096
  surname: Li
  fullname: Li, Stan Z.
  email: stan.zq.li@westlake.edu.cn
  organization: AI Lab, School of Engineering, Westlake University, Hangzhou, Zhejiang, China
BookMark eNp9kMFKAzEQhoNUsK0-gOBhwYOnrZkkm2yOpa1VrHiwnsNuMgspdbcmu4W-vVvag3jwECYM_zczfCMyqJsaCbkFOgGg-nH9Ol9MGGViwrkEocQFGUKW5SkDDYP-TwWkggt1RUYxbiilucphSB6myUcX9nhImjpZYo2haP0ek7mvqi76vvnWONzGa3JZFduIN-c6Jp9Pi_XsOV29L19m01VqmRZtylwJrOQ8E3mpc4u6AppnlULtuLOS2oKhctqCBFdStBm1THJmpchEIR3yMbk_zd2F5rvD2JpN04W6X2k4lUJRyXXep9QpZUMTY8DKWN_2hzd1Gwq_NUDN0Yo5WjFHK-ZspSfhD7kL_qsIh3-ZuxPjEfFXXoDuH_8B3TZtnQ
CODEN ITKEEH
CitedBy_id crossref_primary_10_1016_j_ress_2025_111177
crossref_primary_10_21833_ijaas_2025_08_024
crossref_primary_10_3390_electronics14061158
crossref_primary_10_7233_jksc_2024_74_6_069
crossref_primary_10_1016_j_ejrh_2025_102703
crossref_primary_10_1016_j_neunet_2025_108034
crossref_primary_10_1016_j_inffus_2024_102753
crossref_primary_10_1109_TGRS_2024_3464685
crossref_primary_10_1007_s10462_025_11223_9
crossref_primary_10_1137_24M1642202
crossref_primary_10_1007_s11263_025_02375_w
crossref_primary_10_3390_s24103087
crossref_primary_10_1016_j_compag_2025_110123
crossref_primary_10_3390_math13162584
crossref_primary_10_1145_3706058
crossref_primary_10_1109_JIOT_2025_3528955
crossref_primary_10_1007_s00122_025_04942_8
crossref_primary_10_3390_plants14030339
crossref_primary_10_1016_j_trc_2025_105152
crossref_primary_10_1007_s10462_025_11110_3
crossref_primary_10_1007_s10489_025_06602_2
crossref_primary_10_1109_TITS_2025_3557088
crossref_primary_10_3390_en17164132
crossref_primary_10_1016_j_cpc_2025_109777
crossref_primary_10_1515_nanoph_2025_0049
crossref_primary_10_1109_TGRS_2025_3545272
crossref_primary_10_1021_acsphotonics_4c02352
crossref_primary_10_1088_2632_2153_ad95dd
crossref_primary_10_1088_1361_6560_ad965c
crossref_primary_10_1016_j_isprsjprs_2024_08_017
crossref_primary_10_1109_TMC_2025_3526230
crossref_primary_10_3390_app15137363
crossref_primary_10_1002_adts_202500073
crossref_primary_10_1016_j_compchemeng_2024_108989
crossref_primary_10_1007_s10845_024_02559_0
crossref_primary_10_1038_s41401_024_01380_y
crossref_primary_10_1145_3663759
crossref_primary_10_3390_s25123745
crossref_primary_10_1109_TGRS_2025_3578927
crossref_primary_10_1109_TCSVT_2025_3533301
crossref_primary_10_1016_j_eswa_2025_129443
crossref_primary_10_1016_j_isprsjprs_2024_09_024
crossref_primary_10_1088_2632_2153_adf8b1
crossref_primary_10_1109_TPAMI_2025_3541625
crossref_primary_10_1007_s41060_025_00831_x
crossref_primary_10_1007_s11760_025_04007_9
crossref_primary_10_1126_sciadv_adv0778
crossref_primary_10_1088_1741_2552_ae0070
crossref_primary_10_1007_s00521_024_10843_6
crossref_primary_10_1016_j_saa_2025_126336
crossref_primary_10_1145_3721479
crossref_primary_10_1109_TIFS_2025_3607244
crossref_primary_10_1016_j_csbj_2024_06_021
crossref_primary_10_1109_TITS_2025_3559672
crossref_primary_10_3390_fi16090343
crossref_primary_10_1038_s41524_024_01280_z
crossref_primary_10_1109_ACCESS_2024_3467063
crossref_primary_10_1109_JSTARS_2025_3590446
crossref_primary_10_1007_s11831_025_10266_z
crossref_primary_10_1007_s40670_025_02332_9
crossref_primary_10_1109_TIFS_2025_3546845
crossref_primary_10_1038_s41529_025_00603_9
crossref_primary_10_1016_j_inffus_2024_102843
crossref_primary_10_1007_s11548_025_03333_0
crossref_primary_10_3390_app15063264
crossref_primary_10_3390_electronics13173353
crossref_primary_10_1109_TKDE_2025_3582767
crossref_primary_10_3390_batteries11070248
crossref_primary_10_3390_en18030503
crossref_primary_10_1109_TITS_2024_3520613
crossref_primary_10_3390_s24082642
crossref_primary_10_1109_TGRS_2024_3462414
crossref_primary_10_1016_j_buildenv_2025_113309
crossref_primary_10_3390_app142210640
crossref_primary_10_1109_JIOT_2024_3509029
crossref_primary_10_1109_TKDE_2024_3460051
crossref_primary_10_1016_j_ijepes_2025_110596
crossref_primary_10_1109_TVT_2025_3547866
crossref_primary_10_3389_fmed_2025_1551894
crossref_primary_10_1016_j_neunet_2025_107510
crossref_primary_10_1109_TGRS_2024_3485483
crossref_primary_10_1109_TIP_2024_3512365
crossref_primary_10_3390_su17177657
crossref_primary_10_1016_j_scs_2025_106826
crossref_primary_10_1007_s11432_024_4424_3
crossref_primary_10_1109_TCE_2024_3424780
crossref_primary_10_1021_acs_jpcc_4c08681
crossref_primary_10_1016_j_eja_2024_127423
crossref_primary_10_1002_mp_17328
crossref_primary_10_1016_j_ecoinf_2024_102733
crossref_primary_10_1016_j_cviu_2025_104470
crossref_primary_10_1109_TGRS_2025_3564959
crossref_primary_10_3390_s25020531
crossref_primary_10_1109_JIOT_2024_3495212
crossref_primary_10_1016_j_actphy_2025_100115
crossref_primary_10_1016_j_engappai_2025_111350
crossref_primary_10_1016_j_neunet_2024_106979
crossref_primary_10_1016_j_inffus_2024_102701
crossref_primary_10_1007_s10707_025_00558_8
crossref_primary_10_1186_s13321_025_01059_4
crossref_primary_10_1016_j_ipm_2025_104303
crossref_primary_10_1109_JIOT_2025_3570989
crossref_primary_10_1093_bib_bbae275
crossref_primary_10_1016_j_knosys_2024_112647
crossref_primary_10_1016_j_neunet_2024_107031
crossref_primary_10_1016_j_taml_2025_100604
crossref_primary_10_1109_TMC_2025_3574065
crossref_primary_10_1177_30504554241311182
crossref_primary_10_1016_j_patcog_2025_111934
crossref_primary_10_1109_JIOT_2024_3486725
crossref_primary_10_3390_photonics12090923
crossref_primary_10_1016_j_procs_2024_09_258
crossref_primary_10_1007_s00530_024_01651_y
crossref_primary_10_1016_j_patcog_2025_111935
crossref_primary_10_1016_j_aei_2024_102963
crossref_primary_10_1109_TAES_2025_3560611
crossref_primary_10_1109_TAI_2024_3454591
crossref_primary_10_1016_j_neucom_2024_128911
crossref_primary_10_1038_s41612_025_01157_y
crossref_primary_10_29220_CSAM_2025_32_2_235
crossref_primary_10_1039_D5TA00922G
crossref_primary_10_1016_j_infsof_2025_107805
crossref_primary_10_1007_s00521_025_11458_1
crossref_primary_10_1103_7qbv_4y2s
crossref_primary_10_1016_j_jmsy_2024_04_021
crossref_primary_10_1016_j_ascom_2024_100921
crossref_primary_10_1109_TASE_2025_3593296
crossref_primary_10_1109_TITS_2024_3438263
crossref_primary_10_1007_s12273_025_1279_x
crossref_primary_10_1016_j_advwatres_2024_104833
crossref_primary_10_1080_14626268_2025_2467087
crossref_primary_10_1016_j_csbj_2024_09_030
crossref_primary_10_1186_s40658_024_00706_3
crossref_primary_10_1016_j_compchemeng_2025_109328
crossref_primary_10_1016_j_ins_2025_122003
crossref_primary_10_1115_1_4065905
crossref_primary_10_1016_j_inffus_2025_102965
crossref_primary_10_1109_MWC_007_2400133
crossref_primary_10_1007_s10462_025_11116_x
crossref_primary_10_3390_rs16162927
crossref_primary_10_1103_dxp7_4hby
crossref_primary_10_1109_TGRS_2025_3583285
crossref_primary_10_1016_j_inffus_2025_103012
crossref_primary_10_1016_j_jobe_2024_109299
crossref_primary_10_1016_j_asoc_2025_113181
crossref_primary_10_1016_j_jmps_2025_106253
crossref_primary_10_1109_TMC_2025_3568248
crossref_primary_10_1016_j_mtcomm_2025_113087
crossref_primary_10_1186_s13321_025_00985_7
crossref_primary_10_1007_s10462_024_10881_5
crossref_primary_10_1007_s11222_025_10665_z
crossref_primary_10_1088_2632_2153_adec3c
crossref_primary_10_1007_s13632_024_01130_w
crossref_primary_10_1109_JPHOT_2024_3434972
crossref_primary_10_1007_s11431_024_2917_8
crossref_primary_10_1016_j_compbiomed_2025_110996
Cites_doi 10.1038/s41586-023-06415-8
10.1109/ACCESS.2020.2975067
10.1007/s11263-021-01453-z
10.1145/3528233.3530757
10.1609/aaai.v36i10.21350
10.1007/springerreference_76776
10.1007/978-3-031-18576-2_12
10.1145/3589132.3625614
10.3997/2214-4609.201901607
10.1109/CVPRW56347.2022.00080
10.1002/wcms.1608
10.1109/ICCV48922.2021.01410
10.1038/s41467-024-45051-2
10.3390/e25101469
10.1126/science.153.3731.34
10.1007/978-3-031-43999-5_39
10.1109/iccv51070.2023.01816
10.1016/0304-4149(82)90051-5
10.1038/s41598-018-24760-x
10.1007/978-3-031-16452-1_4
10.1109/taslp.2023.3268730
10.1109/TPAMI.2020.2992934
10.1016/j.cviu.2021.103329
10.1117/12.2612235
10.1038/s41586-021-03819-2
10.1145/3503161.3547855
10.1109/ICCV51070.2023.00853
10.1109/ASRU51503.2021.9688219
10.21437/interspeech.2022-6
10.1109/ICCV51070.2023.00355
10.1109/ICCV48922.2021.00454
10.1007/978-3-031-43987-2_10
10.1109/CVPR52729.2023.00037
10.1007/978-3-031-20062-5_6
10.1007/978-3-031-34048-2_6
10.1007/978-3-031-19821-2_20
10.1093/bib/bbw068
10.1145/3588432.3591540
10.1109/iccv51070.2023.00713
10.1162/NECO_a_00142
10.18653/v1/2023.acl-long.248
10.1016/j.neucom.2022.01.029
10.1109/cvpr52729.2023.01766
10.1109/cvpr52729.2023.01374
10.1080/01691864.2017.1365009
10.1109/TNNLS.2020.2979670
10.1109/isbi53787.2023.10230346
10.1109/CVPR52688.2022.01117
10.1109/ICDM54844.2022.00030
10.1109/MSP.2017.2765202
10.1109/CVPR52729.2023.02155
10.1090/gsm/058
10.1109/TKDE.2021.3131584
10.1109/ICCV.2015.425
10.1109/ISACV.2018.8354080
10.1109/TPAMI.2023.3261988
10.18653/v1/2023.acl-long.526
10.1109/TMI.2022.3220681
10.1145/3065386
10.24963/ijcai.2023/750
10.1109/ICDE55515.2023.00150
10.3390/e25040633
10.1109/CVPR52729.2023.01764
10.1016/j.media.2023.102846
10.1109/CVPR52688.2022.01042
10.1016/j.cbpa.2021.08.004
10.1016/j.media.2022.102479
10.1145/960126.806879
10.1109/ICCV48922.2021.00577
10.21437/Interspeech.2022-301
10.3390/e22080802
10.1109/CVPR52688.2022.01043
10.21437/Interspeech.2021-469
10.1145/3422622
10.1109/CVPR46437.2021.00286
10.1038/s43588-023-00440-3
10.1007/978-3-031-43904-9_56
10.21437/Interspeech.2022-10045
10.1561/2200000056
10.48550/ARXIV.1706.03762
10.1109/tpami.2023.3344758
10.1109/icme55011.2023.00144
10.1109/CVPR52688.2022.01121
10.1109/CVPR52688.2022.01209
10.1109/CVPR52688.2022.00509
10.1145/3592116
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
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TKDE.2024.3361474
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1558-2191
EndPage 2830
ExternalDocumentID 10_1109_TKDE_2024_3361474
10419041
Genre orig-research
GrantInformation_xml – fundername: Hong Kong Special Administrative Region, China
  grantid: T45-401/22-N
– fundername: Natural Science Foundation of Guangdong Province
  grantid: 2022A1515011579
  funderid: 10.13039/501100003453
– fundername: National Natural Science Foundation of China
  grantid: 62376254; 32341018
  funderid: 10.13039/501100001809
– fundername: Science and Technology Innovation 2030 - Major Project
  grantid: 2021ZD0150100
– fundername: National Natural Science Foundation of China
  grantid: U21A20427
  funderid: 10.13039/501100001809
– fundername: Innovation and Technology Commission; Hong Kong Innovation and Technology Fund
  grantid: ITS/241/21
  funderid: 10.13039/501100007156
– fundername: National Key R&D Program of China
  grantid: 2022YFE0200700
GroupedDBID -~X
.DC
0R~
1OL
29I
4.4
5GY
5VS
6IK
97E
9M8
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RXW
RZB
TAE
TAF
TN5
UHB
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c294t-2db12b33548b98ce9f1085f7e9d3dc60ca2e7d9c161db0ec50c2632c6454a6de3
IEDL.DBID RIE
ISICitedReferencesCount 233
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001245017200020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1041-4347
IngestDate Mon Jun 30 05:15:28 EDT 2025
Sat Nov 29 02:36:08 EST 2025
Tue Nov 18 22:30:38 EST 2025
Wed Aug 27 02:06:32 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c294t-2db12b33548b98ce9f1085f7e9d3dc60ca2e7d9c161db0ec50c2632c6454a6de3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-2961-8096
0000-0002-8104-1845
0000-0003-3055-5034
0000-0001-7194-9481
0000-0003-1026-6083
0000-0002-8639-923X
0000-0002-5892-8608
PQID 3064706398
PQPubID 85438
PageCount 17
ParticipantIDs crossref_citationtrail_10_1109_TKDE_2024_3361474
crossref_primary_10_1109_TKDE_2024_3361474
proquest_journals_3064706398
ieee_primary_10419041
PublicationCentury 2000
PublicationDate 2024-07-01
PublicationDateYYYYMMDD 2024-07-01
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-07-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on knowledge and data engineering
PublicationTitleAbbrev TKDE
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 Kim (ref88) 2022
ref56
ref59
ref58
ref53
Karras (ref25) 2022
ref52
ref204
ref54
ref202
Xu (ref33) 2023
Fan (ref65) 2023
Luo (ref257) 2021; 34
Fahim Sikder (ref183) 2023
Amit (ref249) 2021
Song (ref26)
Aiello (ref66) 2023
ref211
ref51
ref50
Ho (ref10)
Guo (ref159) 2023
ref216
Song (ref11) 2020
ref217
ref42
Yan (ref18) 2021
ref41
ref44
ref213
Lopez Alcaraz (ref182) 2023
De Bortoli (ref240) 2021
Chen (ref45) 2018; 31
ref8
Harvey (ref156) 2022
Daras (ref74) 2022
Lyu (ref73) 2022
ref6
ref5
Luhman (ref61) 2021
ref222
ref220
Lu (ref28) 2022
ref36
Nichol (ref146) 2022
Kong (ref79) 2021
Lin (ref214) 2023
Xu (ref23)
Arnold (ref39) 1974
Lyu (ref144) 2021
Hoogeboom (ref92) 2021; 34
Um (ref207)
ref21
Huang (ref98) 2022
Kawar (ref242)
Li (ref15) 2022; 35
ref129
ref127
ref245
Albergo (ref38) 2022
ref246
Anand (ref135) 2022
ref133
ref255
ref131
ref94
ref132
ref250
ref130
Xiao (ref86) 2021
Kim (ref195) 2022
ref137
Ramesh (ref121) 2022
Dorjsembe (ref168)
ref136
Chen (ref19)
Chen (ref210) 2023
Tang (ref95) 2022
Han (ref248) 2022
Lu (ref105)
Song (ref251)
Zhang (ref89) 2022
ref142
ref143
Dockhorn (ref34) 2021
ref140
ref141
Watson (ref84) 2022
ref108
ref109
ref106
Guo (ref223) 2023
ref228
ref75
LeCun (ref3) 2006; 1
Watson (ref85) 2021
ref102
Chung (ref160) 2022; 35
Alamdari (ref219) 2023
Popov (ref20)
Nichol (ref49) 2021
ref112
ref233
Salimans (ref229) 2016; 29
Corso (ref218) 2023
ref68
Pandey (ref87) 2022
ref119
Su (ref70) 2022
Rasul (ref184)
Xu (ref32) 2022
Alcaraz (ref253) 2022
ref63
Kingma (ref77) 2021; 34
ref116
Liu (ref149) 2023
ref234
Lu (ref47) 2022
Lee (ref67) 2023
Cohen (ref125) 2022
Zhang (ref221) 2023
Poole (ref152) 2022
Leng (ref189) 2022
Voleti (ref155) 2022; 35
Campbell (ref96) 2022
Wu (ref191) 2021
Zou (ref212) 2023
Hoogeboom (ref198)
ref122
ref243
ref123
ref241
Wu (ref209)
Niu (ref22)
Kong (ref186)
Hoogeboom (ref72) 2022
ref169
Theis (ref244) 2022
Austin (ref16) 2021; 34
Liu (ref37) 2022
Lopes (ref107) 2017
Bansal (ref90) 2022
Berthelot (ref60) 2023
Sohl-Dickstein (ref9)
Xu (ref43) 2023
ref170
Lipman (ref91) 2022
Corso (ref203) 2022
Xu (ref30) 2023
Giannone (ref247) 2022
ref174
ref171
Zhang (ref224) 2023
Dhariwal (ref27) 2021; 34
Salimans (ref31) 2022
Gong (ref175)
Park (ref254)
Luo (ref24)
Weinbach (ref128) 2022
Singer (ref154) 2022
Yuan (ref172) 2022
Song (ref227)
Saharia (ref138) 2022
ref181
Lin (ref134) 2022
Zhang (ref237)
Watson (ref113)
ref188
Wu (ref176) 2023
ref187
ref185
Ho (ref12) 2022
ref148
Huang (ref104)
Jolicoeur-Martineau (ref111) 2021
ref147
Khrulkov (ref76) 2022
Chen (ref101) 2022
Nichol (ref78)
Zheng (ref110) 2020
Liu (ref69) 2023
Xie (ref126) 2022
ref153
Razavi (ref231) 2019; 32
ref151
ref150
Gao (ref177) 2022
Huang (ref115)
ref157
Popov (ref215)
Vignac (ref206) 2022
Hoogeboom (ref93) 2021
Chen (ref252) 2022
Ngiam (ref4)
Liu (ref117) 2023
ref166
Kim (ref196)
ref167
Baranchuk (ref55) 2021
ref164
Kim (ref114) 2021
ref165
ref162
Zheng (ref71) 2022
Zhang (ref81) 2022
ref163
ref161
Zhang (ref29) 2022
Bao (ref82) 2022
ref14
Gao (ref238) 2020
Chen (ref208) 2023
Liu (ref64)
Ye (ref179) 2023
Chao (ref57) 2022
Song (ref236)
Van Den Oord (ref124) 2017; 30
Tashiro (ref17) 2021; 34
Batzolis (ref13) 2021
Kullback (ref230) 1997
Oksendal (ref40) 2013
De Bortoli (ref97) 2022
Xie (ref258)
Koo (ref226) 2023
Devlin (ref120) 2018
Jun (ref145) 2023
Liu (ref46) 2022
Krizhevsky (ref232) 2009
Song (ref235)
Rezende (ref7)
Vahdat (ref35) 2021; 34
Jing (ref200)
San-Roman (ref80) 2021
Luzi (ref99) 2022
Song (ref103) 2021; 34
Yim (ref201) 2023
ref2
ref1
Höppe (ref158) 2022
Fan (ref225) 2023
Zheng (ref62) 2022
ref192
ref190
Lim (ref180) 2023
ref199
ref197
Rissanen (ref118) 2022
Lin (ref173)
Ho (ref48) 2022
ref193
ref194
Shi (ref256)
Hertz (ref139) 2022
Strudel (ref178) 2022
Song (ref239) 2021
Lisanza (ref205) 2023
Bao (ref83) 2022
Cheng (ref100) 2022
References_xml – ident: ref204
  doi: 10.1038/s41586-023-06415-8
– volume: 1
  start-page: 1
  year: 2006
  ident: ref3
  article-title: A tutorial on energy-based learning
  publication-title: Predicting Struct. Data
– start-page: 11918
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref227
  article-title: Generative modeling by estimating gradients of the data distribution
– year: 2022
  ident: ref126
  article-title: Vector quantized diffusion model with codeunet for text-to-sign pose sequences generation
– volume: 34
  start-page: 24 804
  year: 2021
  ident: ref17
  article-title: CSDI: Conditional score-based diffusion models for probabilistic time series imputation
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2022
  ident: ref48
  article-title: Classifier-free diffusion guidance
– ident: ref133
  doi: 10.1109/ACCESS.2020.2975067
– year: 2018
  ident: ref120
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
– year: 2021
  ident: ref18
  article-title: Scoregrad: Multivariate probabilistic time series forecasting with continuous energy-based generative models
– year: 2023
  ident: ref221
  article-title: Audio diffusion model for speech synthesis: A survey on text to speech and speech enhancement in generative AI
– start-page: 4
  volume-title: Proc. NeurIPS 2022 Workshop Score-Based Methods
  ident: ref64
  article-title: Flow straight and fast: Learning to generate and transfer data with rectified flow
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref23
  article-title: GeoDiff: A geometric diffusion model for molecular conformation generation
– start-page: 1530
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref7
  article-title: Variational inference with normalizing flows
– year: 2021
  ident: ref61
  article-title: Knowledge distillation in iterative generative models for improved sampling speed
– year: 2022
  ident: ref89
  article-title: Dimensionality-varying diffusion process
– ident: ref108
  doi: 10.1007/s11263-021-01453-z
– ident: ref243
  doi: 10.1145/3528233.3530757
– year: 2022
  ident: ref38
  article-title: Building normalizing flows with stochastic interpolants
– volume: 35
  start-page: 4328
  year: 2022
  ident: ref15
  article-title: Diffusion-LM improves controllable text generation
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2021
  ident: ref144
  article-title: A conditional point diffusion-refinement paradigm for 3D point cloud completion
– volume: 35
  start-page: 25 683
  year: 2022
  ident: ref160
  article-title: Improving diffusion models for inverse problems using manifold constraints
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 12438
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref236
  article-title: Improved techniques for training score-based generative models
– year: 2022
  ident: ref252
  article-title: Analog bits: Generating discrete data using diffusion models with self-conditioning
– start-page: 11 119
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref196
  article-title: Guided-TTS: A diffusion model for text-to-speech via classifier guidance
– ident: ref187
  doi: 10.1609/aaai.v36i10.21350
– ident: ref137
  doi: 10.1007/springerreference_76776
– volume: 34
  start-page: 1415
  year: 2021
  ident: ref103
  article-title: Maximum likelihood training of score-based diffusion models
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: ref170
  doi: 10.1007/978-3-031-18576-2_12
– ident: ref185
  doi: 10.1145/3589132.3625614
– ident: ref131
  doi: 10.3997/2214-4609.201901607
– ident: ref164
  doi: 10.1109/CVPRW56347.2022.00080
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref19
  article-title: WaveGrad: Estimating gradients for waveform generation
– ident: ref217
  doi: 10.1002/wcms.1608
– ident: ref59
  doi: 10.1109/ICCV48922.2021.01410
– year: 2022
  ident: ref83
  article-title: Estimating the optimal covariance with imperfect mean in diffusion probabilistic models
– year: 2020
  ident: ref11
  article-title: Score-based generative modeling through stochastic differential equations
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref209
  article-title: DIFFormer: Scalable (graph) transformers induced by energy constrained diffusion
– ident: ref202
  doi: 10.1038/s41467-024-45051-2
– ident: ref157
  doi: 10.3390/e25101469
– ident: ref112
  doi: 10.1126/science.153.3731.34
– volume-title: Stochastic Differential Equations: An Introduction With Applications
  year: 2013
  ident: ref40
– ident: ref116
  doi: 10.1007/978-3-031-43999-5_39
– year: 2023
  ident: ref224
  article-title: A survey on graph diffusion models: Generative AI in science for molecule, protein and material
– year: 2022
  ident: ref32
  article-title: Poisson flow generative models
– ident: ref54
  doi: 10.1109/iccv51070.2023.01816
– ident: ref41
  doi: 10.1016/0304-4149(82)90051-5
– year: 2021
  ident: ref55
  article-title: Label-efficient semantic segmentation with diffusion models
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref215
  article-title: Diffusion-based voice conversion with fast maximum likelihood sampling scheme
– start-page: 4474
  volume-title: Proc. Int. Conf. Artif. Intell. Statist.
  ident: ref22
  article-title: Permutation invariant graph generation via score-based generative modeling
– ident: ref132
  doi: 10.1038/s41598-018-24760-x
– start-page: 4
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref254
  article-title: Neural Markov controlled SDE: Stochastic optimization for continuous-time data
– year: 2022
  ident: ref118
  article-title: Generative modelling with inverse heat dissipation
– year: 2023
  ident: ref210
  article-title: D4explainer: In-distribution GNN explanations via discrete denoising diffusion
– year: 2022
  ident: ref72
  article-title: Blurring diffusion models
– ident: ref52
  doi: 10.1007/978-3-031-16452-1_4
– start-page: 21 051
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref173
  article-title: Text generation with diffusion language models: A pre-training approach with continuous paragraph denoise
– ident: ref197
  doi: 10.1109/taslp.2023.3268730
– year: 2023
  ident: ref66
  article-title: Fast inference in denoising diffusion models via MMD finetuning
– ident: ref8
  doi: 10.1109/TPAMI.2020.2992934
– volume: 29
  start-page: 2234
  year: 2016
  ident: ref229
  article-title: Improved techniques for training GANs
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref186
  article-title: DiffWave: A versatile diffusion model for audio synthesis
– year: 2021
  ident: ref239
  article-title: How to train your energy-based models
– year: 2021
  ident: ref249
  article-title: SegDiff: Image segmentation with diffusion probabilistic models
– year: 2022
  ident: ref73
  article-title: Accelerating diffusion models via early stop of the diffusion process
– ident: ref228
  doi: 10.1016/j.cviu.2021.103329
– ident: ref163
  doi: 10.1117/12.2612235
– start-page: 8867
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref198
  article-title: Equivariant diffusion for molecule generation in 3D
– year: 2022
  ident: ref146
  article-title: Point-E: A system for generating 3D point clouds from complex prompts
– year: 2022
  ident: ref99
  article-title: Boomerang: Local sampling on image manifolds using diffusion models
– start-page: 1
  volume-title: Proc. Med. Imag. Deep Learn. Conf.
  ident: ref168
  article-title: Three-dimensional medical image synthesis with denoising diffusion probabilistic models
– ident: ref122
  doi: 10.1038/s41586-021-03819-2
– year: 2022
  ident: ref91
  article-title: Flow matching for generative modeling
– ident: ref188
  doi: 10.1145/3503161.3547855
– year: 2021
  ident: ref34
  article-title: Score-based generative modeling with critically-damped langevin diffusion
– year: 2022
  ident: ref96
  article-title: A continuous time framework for discrete denoising models
– ident: ref148
  doi: 10.1109/ICCV51070.2023.00853
– ident: ref190
  doi: 10.1109/ASRU51503.2021.9688219
– start-page: 2023
  year: 2023
  ident: ref219
  article-title: Protein generation with evolutionary diffusion: Sequence is all you need
  publication-title: bioRxiv
– year: 2022
  ident: ref189
  article-title: BinauralGrad: A two-stage conditional diffusion probabilistic model for binaural audio synthesis
– ident: ref192
  doi: 10.21437/interspeech.2022-6
– ident: ref143
  doi: 10.1109/ICCV51070.2023.00355
– ident: ref150
  doi: 10.1109/ICCV48922.2021.00454
– year: 2022
  ident: ref97
  article-title: Riemannian score-based generative modeling
– start-page: 4
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref200
  article-title: Torsional diffusion for molecular conformer generation
– ident: ref162
  doi: 10.1007/978-3-031-43987-2_10
– year: 2022
  ident: ref206
  article-title: Digress: Discrete denoising diffusion for graph generation
– year: 2022
  ident: ref37
  article-title: Flow straight and fast: Learning to generate and transfer data with rectified flow
– year: 2022
  ident: ref244
  article-title: Lossy compression with gaussian diffusion
– year: 2023
  ident: ref214
  article-title: Diffusion models for time series applications: A survey
– ident: ref153
  doi: 10.1109/CVPR52729.2023.00037
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref207
  article-title: Confidence-based feature imputation for graphs with partially known features
– year: 2023
  ident: ref176
  article-title: AR-Diffusion: Auto-regressive diffusion model for text generation
– ident: ref250
  doi: 10.1007/978-3-031-20062-5_6
– start-page: 9754
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref24
  article-title: Antigen-specific antibody design and optimization with diffusion-based generative models for protein structures
– volume: 34
  start-page: 21 696
  year: 2021
  ident: ref77
  article-title: Variational diffusion models
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2021
  ident: ref13
  article-title: Conditional image generation with score-based diffusion models
– ident: ref169
  doi: 10.1007/978-3-031-34048-2_6
– year: 2020
  ident: ref110
  article-title: ACT: Asymptotic conditional transport
– start-page: 1105
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref4
  article-title: Learning deep energy models
– start-page: 1
  year: 2023
  ident: ref182
  article-title: Diffusion-based time series imputation and forecasting with structured atate apace models
  publication-title: Trans. Mach. Learn. Res.
– ident: ref166
  doi: 10.1007/978-3-031-19821-2_20
– year: 2023
  ident: ref179
  article-title: Diffusion language models can perform many tasks with scaling and instruction-finetuning
– ident: ref216
  doi: 10.1093/bib/bbw068
– start-page: 6840
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref10
  article-title: Denoising diffusion probabilistic models
– ident: ref106
  doi: 10.1145/3588432.3591540
– start-page: 8857
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref184
  article-title: Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting
– ident: ref129
  doi: 10.1109/iccv51070.2023.00713
– year: 2022
  ident: ref74
  article-title: Soft diffusion: Score matching for general corruptions
– year: 2022
  ident: ref248
  article-title: CARD: Classification and regression diffusion models
– year: 2023
  ident: ref65
  article-title: Optimizing DDPM sampling with shortcut fine-tuning
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref251
  article-title: Solving inverse problems in medical imaging with score-based generative models
– ident: ref42
  doi: 10.1162/NECO_a_00142
– year: 2023
  ident: ref69
  article-title: I2SB: Image-to-image schrödinger bridge
– year: 2022
  ident: ref195
  article-title: Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data
– year: 2022
  ident: ref152
  article-title: Dreamfusion: Text-to-3D using 2D diffusion
– ident: ref171
  doi: 10.18653/v1/2023.acl-long.248
– year: 2022
  ident: ref87
  article-title: DiffuseVAE: Efficient, controllable and high-fidelity generation from low-dimensional latents
– year: 2023
  ident: ref223
  article-title: Diffusion models in bioinformatics: A new wave of deep learning revolution in action
– ident: ref245
  doi: 10.1016/j.neucom.2022.01.029
– ident: ref56
  doi: 10.1109/cvpr52729.2023.01766
– ident: ref68
  doi: 10.1109/cvpr52729.2023.01374
– ident: ref130
  doi: 10.1080/01691864.2017.1365009
– year: 2022
  ident: ref101
  article-title: NVDiff: Graph generation through the diffusion of node vectors
– year: 2022
  ident: ref95
  article-title: Improved vector quantized diffusion models
– ident: ref211
  doi: 10.1109/TNNLS.2020.2979670
– start-page: 22863
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref104
  article-title: A variational perspective on diffusion-based generative models and score matching
– ident: ref50
  doi: 10.1109/cvpr52729.2023.01374
– ident: ref53
  doi: 10.1109/isbi53787.2023.10230346
– year: 2017
  ident: ref107
  article-title: Data-free knowledge distillation for deep neural networks
– year: 2023
  ident: ref208
  article-title: Efficient and degree-guided graph generation via discrete diffusion modeling
– ident: ref246
  doi: 10.1109/CVPR52688.2022.01117
– volume: 34
  start-page: 12 454
  year: 2021
  ident: ref92
  article-title: Argmax flows and multinomial diffusion: Learning categorical distributions
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: ref21
  doi: 10.1109/ICDM54844.2022.00030
– ident: ref6
  doi: 10.1109/MSP.2017.2765202
– start-page: 8599
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref20
  article-title: Grad-TTS: A diffusion probabilistic model for text-to-speech
– year: 2021
  ident: ref86
  article-title: Tackling the generative learning trilemma with denoising diffusion GANs
– year: 2023
  ident: ref145
  article-title: Shap-E: Generating conditional 3d implicit functions
– ident: ref140
  doi: 10.1109/CVPR52729.2023.02155
– year: 2022
  ident: ref178
  article-title: Self-conditioned embedding diffusion for text generation
– ident: ref109
  doi: 10.1090/gsm/058
– year: 2022
  ident: ref172
  article-title: SeqDiffuSeq: Text diffusion with encoder-decoder transformers
– start-page: 8162
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref78
  article-title: Improved denoising diffusion probabilistic models
– ident: ref136
  doi: 10.1109/TKDE.2021.3131584
– ident: ref234
  doi: 10.1109/ICCV.2015.425
– start-page: 2
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref175
  article-title: DiffuSeq: Sequence to sequence text generation with diffusion models
– year: 2020
  ident: ref238
  article-title: Learning energy-based models by diffusion recovery likelihood
– year: 2022
  ident: ref100
  article-title: Theory and algorithms for diffusion processes on Riemannian manifolds
– year: 2023
  ident: ref201
  article-title: Se (3) diffusion model with application to protein backbone generation
– year: 2022
  ident: ref121
  article-title: Hierarchical text-conditional image generation with clip latents
– year: 2021
  ident: ref191
  article-title: ItôTTS and itôWave: Linear stochastic differential equation is all you need for audio generation
– year: 2022
  ident: ref98
  article-title: Riemannian diffusion models
– volume: 32
  start-page: 14866
  year: 2019
  ident: ref231
  article-title: Generating diverse high-fidelity images with VQ-VAE-2
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 35
  start-page: 23 371
  year: 2022
  ident: ref155
  article-title: Mcvd-masked conditional video diffusion for prediction, generation, and interpolation
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: ref183
  article-title: TransFusion: Generating long, high fidelity time series using diffusion models with transformers
– ident: ref2
  doi: 10.1109/ISACV.2018.8354080
– ident: ref220
  doi: 10.1109/TPAMI.2023.3261988
– year: 2022
  ident: ref31
  article-title: Progressive distillation for fast sampling of diffusion models
– year: 2022
  ident: ref12
  article-title: Video diffusion models
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref113
  article-title: Learning fast samplers for diffusion models by differentiating through sample quality
– volume-title: Information Theory and Statistics
  year: 1997
  ident: ref230
– start-page: 14429
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref105
  article-title: Maximum likelihood training for score-based diffusion odes by high-order denoising score matching
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref26
  article-title: Denoising diffusion implicit models
– year: 2022
  ident: ref177
  article-title: Difformer: Empowering diffusion model on embedding space for text generation
– year: 2022
  ident: ref47
  article-title: DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps
– ident: ref174
  doi: 10.18653/v1/2023.acl-long.526
– year: 2022
  ident: ref156
  article-title: Flexible diffusion modeling of long videos
– year: 2023
  ident: ref159
  article-title: AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning
– year: 2022
  ident: ref90
  article-title: Cold diffusion: Inverting arbitrary image transforms without noise
– year: 2022
  ident: ref128
  article-title: M-VADER: A model for diffusion with multimodal context
– year: 2021
  ident: ref93
  article-title: Autoregressive diffusion models
– year: 2023
  ident: ref30
  article-title: Restart sampling for improving generative processes
– volume: 34
  start-page: 11 287
  year: 2021
  ident: ref35
  article-title: Score-based generative modeling in latent space
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2022
  ident: ref139
  article-title: Prompt-to-prompt image editing with cross attention control
– ident: ref167
  doi: 10.1109/TMI.2022.3220681
– ident: ref233
  doi: 10.1145/3065386
– year: 2022
  ident: ref247
  article-title: Few-shot diffusion models
– ident: ref213
  doi: 10.24963/ijcai.2023/750
– year: 2022
  ident: ref28
  article-title: DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models
– year: 2022
  ident: ref138
  article-title: Photorealistic text-to-image diffusion models with deep language understanding
– ident: ref181
  doi: 10.1109/ICDE55515.2023.00150
– ident: ref75
  doi: 10.3390/e25040633
– year: 2022
  ident: ref154
  article-title: Make-a-video: Text-to-video generation without text-video data
– start-page: 4
  volume-title: Proc. Int. Conf. Learn. Representations
  ident: ref258
  article-title: Crystal diffusion variational autoencoder for periodic material generation
– year: 2022
  ident: ref71
  article-title: Truncated diffusion probabilistic models
– year: 2022
  ident: ref62
  article-title: Fast sampling of diffusion models via operator learning
– year: 2021
  ident: ref49
  article-title: Glide: Towards photorealistic image generation and editing with text-guided diffusion models
– year: 2009
  ident: ref232
  article-title: Learning multiple layers of features from tiny images
– ident: ref142
  doi: 10.1109/CVPR52729.2023.01764
– volume: 34
  start-page: 17 981
  year: 2021
  ident: ref16
  article-title: Structured denoising diffusion models in discrete state-spaces
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 34
  start-page: 8780
  year: 2021
  ident: ref27
  article-title: Diffusion models beat GANs on image synthesis
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: ref222
  doi: 10.1016/j.media.2023.102846
– year: 2022
  ident: ref25
  article-title: Elucidating the design space of diffusion-based generative models
– ident: ref36
  doi: 10.1109/CVPR52688.2022.01042
– start-page: 2023
  year: 2023
  ident: ref205
  article-title: Joint generation of protein sequence and structure with rosettafold sequence space diffusion
  publication-title: bioRxiv
– year: 2022
  ident: ref134
  article-title: DiffBP: Generative diffusion of 3D molecules for target protein binding
– ident: ref123
  doi: 10.1016/j.cbpa.2021.08.004
– year: 2021
  ident: ref114
  article-title: Maximum likelihood training of parametrized diffusion model
– year: 2022
  ident: ref57
  article-title: Quasi-conservative score-based generative models
– year: 2023
  ident: ref60
  article-title: Tract: Denoising diffusion models with transitive closure time-distillation
– year: 2023
  ident: ref149
  article-title: One-2–3-45: Any single image to 3D mesh in 45 seconds without per-shape optimization
– ident: ref161
  doi: 10.1016/j.media.2022.102479
– ident: ref14
  doi: 10.1145/960126.806879
– year: 2022
  ident: ref70
  article-title: Dual diffusion implicit bridges for image-to-image translation
– year: 2023
  ident: ref225
  article-title: Generative diffusion models on graphs: Methods and applications
– year: 2022
  ident: ref81
  article-title: GDDIM: Generalized denoising diffusion implicit models
– year: 2021
  ident: ref111
  article-title: Gotta go fast when generating data with score-based models
– volume: 30
  start-page: 6309
  year: 2017
  ident: ref124
  article-title: Neural discrete representation learning
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations MLDD Workshop
  ident: ref115
  article-title: PF-ABGen: A reliable and efficient antibody generator via poisson flow
– year: 2022
  ident: ref29
  article-title: Fast sampling of diffusion models with exponential integrator
– year: 2021
  ident: ref79
  article-title: On fast sampling of diffusion probabilistic models
– year: 2022
  ident: ref84
  article-title: Learning fast samplers for diffusion models by differentiating through sample quality
– year: 2023
  ident: ref180
  article-title: Regular time-series generation using SGM
– year: 2021
  ident: ref240
  article-title: Simulating diffusion bridges with score matching
– volume: 34
  start-page: 19 784
  year: 2021
  ident: ref257
  article-title: Predicting molecular conformation via dynamic graph score matching
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2022
  ident: ref253
  article-title: Diffusion-based time series imputation and forecasting with structured state space models
– ident: ref147
  doi: 10.1109/ICCV48922.2021.00577
– year: 2022
  ident: ref135
  article-title: Protein structure and sequence generation with equivariant denoising diffusion probabilistic models
– year: 2023
  ident: ref67
  article-title: Minimizing trajectory curvature of ODE-based generative models
– ident: ref194
  doi: 10.21437/Interspeech.2022-301
– ident: ref44
  doi: 10.3390/e22080802
– year: 2021
  ident: ref80
  article-title: Noise estimation for generative diffusion models
– year: 2023
  ident: ref117
  article-title: Genphys: From physical processes to generative models
– ident: ref94
  doi: 10.1109/CVPR52688.2022.01043
– year: 2022
  ident: ref125
  article-title: Diffusion bridges vector quantized variational autoencoders
– year: 2022
  ident: ref88
  article-title: Maximum likelihood training of implicit nonlinear diffusion models
– volume: 31
  start-page: 6572
  year: 2018
  ident: ref45
  article-title: Neural ordinary differential equations
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: ref193
  doi: 10.21437/Interspeech.2021-469
– ident: ref5
  doi: 10.1145/3422622
– ident: ref241
  doi: 10.1109/ICCV48922.2021.00577
– ident: ref151
  doi: 10.1109/CVPR46437.2021.00286
– year: 2023
  ident: ref43
  article-title: Stable target field for reduced variance score estimation in diffusion models
– year: 2023
  ident: ref33
  article-title: PFGM++: Unlocking the potential of physics-inspired generative models
– year: 2022
  ident: ref203
  article-title: DiffDock: Diffusion steps, twists, and turns for molecular docking
– year: 2023
  ident: ref226
  article-title: Acomprehensive survey on generative diffusion models for structured data
– year: 2022
  ident: ref158
  article-title: Diffusion models for video prediction and infilling
– ident: ref199
  doi: 10.1038/s43588-023-00440-3
– ident: ref165
  doi: 10.1007/978-3-031-43904-9_56
– ident: ref255
  doi: 10.21437/Interspeech.2022-10045
– ident: ref1
  doi: 10.1561/2200000056
– year: 2022
  ident: ref76
  article-title: Understanding DDPM latent codes through optimal transport
– year: 2023
  ident: ref218
  article-title: Particle guidance: Non-IID diverse sampling with diffusion models
– year: 2023
  ident: ref212
  article-title: Diffusion models in NLP: A survey
– ident: ref119
  doi: 10.48550/ARXIV.1706.03762
– start-page: 3
  volume-title: Proc. Int. Conf. Learn. Representations Workshop
  ident: ref242
  article-title: Denoising diffusion restoration models
– ident: ref102
  doi: 10.1109/tpami.2023.3344758
– ident: ref63
  doi: 10.1109/icme55011.2023.00144
– start-page: 9558
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref256
  article-title: Learning gradient fields for molecular conformation generation
– year: 2022
  ident: ref82
  article-title: Analytic-DPM: An analytic estimate of the optimal reverse variance in diffusion probabilistic models
– ident: ref51
  doi: 10.1109/CVPR52688.2022.01121
– ident: ref58
  doi: 10.1109/CVPR52688.2022.01209
– ident: ref127
  doi: 10.1109/CVPR52688.2022.00509
– start-page: 16280
  volume-title: Proc. Int. Conf. Neural Inf. Process. Syst.
  ident: ref237
  article-title: Diffusion normalizing flow
– start-page: 2256
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref9
  article-title: Deep unsupervised learning using nonequilibrium thermodynamics
– ident: ref141
  doi: 10.1145/3592116
– volume-title: Stochastic Differential Equations
  year: 1974
  ident: ref39
– year: 2022
  ident: ref46
  article-title: Pseudo numerical methods for diffusion models on manifolds
– year: 2021
  ident: ref85
  article-title: Learning to efficiently sample from diffusion probabilistic models
– start-page: 574
  volume-title: Proc. Conf. Uncertainty Artif. Intell.
  ident: ref235
  article-title: Sliced score matching: A scalable approach to density and score estimation
SSID ssj0008781
Score 2.7493002
Snippet Deep generative models have unlocked another profound realm of human creativity. By capturing and generalizing patterns within data, we have entered the epoch...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2814
SubjectTerms Artificial intelligence
Computational modeling
Creativity
deep generative model
diffusion algorithm
diffusion applications
Diffusion layers
Diffusion model
Kernel
Markov processes
Mathematical models
Noise reduction
Surveys
Training
Title A Survey on Generative Diffusion Models
URI https://ieeexplore.ieee.org/document/10419041
https://www.proquest.com/docview/3064706398
Volume 36
WOSCitedRecordID wos001245017200020&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: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2191
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008781
  issn: 1041-4347
  databaseCode: RIE
  dateStart: 19890101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1RS8MwEA46fNAHp3PidEoeBEHIbJu0SR6H2xCEIThhb6VNUhiMTrZ14L83l2YyEQXf-nA5yiV3l0ty34fQrY35TNjMRwzVEWFWhkiRhSTTKixoHCqdCUc2wcdjMZ3KF9-s7nphjDHu8Znpwae7y9cLVcFRmfVwZvMXtKnvc87rZq2vsCu4YyQFGcIo4_4KMwzkw-R5MLSlYMR6lNp0xNm3JORYVX6EYpdfRs1__tkJOvYbSdyvZ_4U7ZmyhZpbkgbsfbaFjnYQB8_QXR-_VsuN-cCLEteQ0xDv8GBWFBUcnGEgR5uv2uhtNJw8PhHPlUBUJNmaRDoPo5xSW4DkUigjC2grKLiRmmqVBCqLDNdS2Q2ezgOj4kABUrsCQK8s0Yaeo0a5KM0FwpHmgU5EEhcOxVzlzCqLc219N06s5g4KtsZLlQcSBz6LeeoKikCmYO8U7J16e3fQ_deQ9xpF4y_hNhh4R7C2bQd1t1OUekdbpVBAcdhmictfhl2hQ9BeP7HtosZ6WZlrdKA269lqeePW0CfQUMEE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH-ICurB6Zw4ndqDIAidbZN-5DjcxmRzCE7YrbRJCoPRybYO_O_NS7MxEQVvPbyk5aXvK8n7_QDulM-nkYp8tiTCs6mSsVmUuHYiuJsR3-UiiTTZRDgcRuMxezXN6roXRkqpL5_JJj7qs3wx4wVulSkLpyp-YZv6nk-p55btWhvHG4WakxSlbEpoaA4xXYc9jvrtjioGPdokRAWkkH4LQ5pX5Ycz1hGmW_nnt53AsUklrVa59qewI_MqVNY0DZax2iocbWEOnsF9y3or5iv5ac1yqwSdRo9ntSdZVuDWmYX0aNNFDd67ndFTzzZsCTb3GF3ankhdLyVElSApi7hkGTYWZKFkgggeODzxZCgYVymeSB3JfYcjVjtHSK8kEJKcw24-y-UFWJ4IHRFEgZ9pHHOeUjWZnwplvX6gZq6Ds1ZezA2UODJaTGNdUjgsRn3HqO_Y6LsOD5shHyWOxl_CNVTwlmCp2zo01ksUG1NbxFhChZhoRZe_DLuFg97oZRAPnof9KzjEN5UXbhuwu5wX8hr2-Wo5Wcxv9P_0BQqdxEs
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=A+Survey+on+Generative+Diffusion+Models&rft.jtitle=IEEE+transactions+on+knowledge+and+data+engineering&rft.au=Cao%2C+Hanqun&rft.au=Tan%2C+Cheng&rft.au=Gao%2C+Zhangyang&rft.au=Xu%2C+Yilun&rft.date=2024-07-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1041-4347&rft.eissn=1558-2191&rft.volume=36&rft.issue=7&rft.spage=2814&rft_id=info:doi/10.1109%2FTKDE.2024.3361474&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1041-4347&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1041-4347&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1041-4347&client=summon