Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding Article Swipe

PDF

Xin Yi , Qi Qin , Simin Luo , K. S. Zhu , Juncheng Yan , Y.-W. Tai , Jiayi Lei , Yuewen Cao , Keqi Wang , Yibin Wang , Junhong Bai , Qian Yu , Du Jiang , Y. N. Pu , Haoxing Chen , Le Zhuo , Junjun He , Gen Luo , Tianbin Li , Ming Hu , Ye Jin , Shenglong Ye , Bo Zhang , Chang Xu , Wenhai Wang , Hongsheng Li , Guangtao Zhai , Tianfan Xue , Bin Fu , Xiaohong Liu , Yu Qiao , Yihao Liu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.06308

We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs and outputs across various modalities. This innovative approach allows Lumina-DiMOO to achieve higher sampling efficiency compared to previous autoregressive (AR) or hybrid AR-Diffusion paradigms and adeptly support a broad spectrum of multi-modal tasks, including text-to-image generation, image-to-image generation (e.g., image editing, subject-driven generation, and image inpainting, etc.), as well as image understanding. Lumina-DiMOO achieves state-of-the-art performance on multiple benchmarks, surpassing existing open-source unified multi-modal models. To foster further advancements in multi-modal and discrete diffusion model research, we release our code and checkpoints to the community. Project Page: https://synbol.github.io/Lumina-DiMOO.

Related Topics

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2510.06308
PDF: https://arxiv.org/pdf/2510.06308
OA Status: green
OpenAlex ID: https://openalex.org/W4415314506

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415314506

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2510.06308

Digital Object Identifier
Title: Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-10-07

Full publication date if available
Authors: Xin Yi, Qi Qin, Simin Luo, K. S. Zhu, Juncheng Yan, Y.-W. Tai, Jiayi Lei, Yuewen Cao, Keqi Wang, Yibin Wang, Junhong Bai, Qian Yu, Du Jiang, Y. N. Pu, Haoxing Chen, Le Zhuo, Junjun He, Gen Luo, Tianbin Li, Ming Hu, Ye Jin, Shenglong Ye, Bo Zhang, Chang Xu, Wenhai Wang, Hongsheng Li, Guangtao Zhai, Tianfan Xue, Bin Fu, Xiaohong Liu, Yu Qiao, Yihao Liu

List of authors in order
Landing page: https://arxiv.org/abs/2510.06308

Publisher landing page
PDF URL: https://arxiv.org/pdf/2510.06308

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2510.06308

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415314506
doi	https://doi.org/10.48550/arxiv.2510.06308
ids.doi	https://doi.org/10.48550/arxiv.2510.06308
ids.openalex	https://openalex.org/W4415314506
fwci
type	preprint
title	Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10181
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9868000149726868
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Natural Language Processing Techniques
topics[1].id	https://openalex.org/T10028
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9812999963760376
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Topic Modeling
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2510.06308
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2510.06308
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2510.06308
locations[1].id	doi:10.48550/arxiv.2510.06308
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2510.06308
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5046852308
authorships[0].author.orcid	https://orcid.org/0000-0002-4726-5765
authorships[0].author.display_name	Xin Yi
authorships[0].author_position	first
authorships[0].raw_author_name	Xin, Yi
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5068500219
authorships[1].author.orcid	https://orcid.org/0000-0002-8181-2291
authorships[1].author.display_name	Qi Qin
authorships[1].author_position	middle
authorships[1].raw_author_name	Qin, Qi
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5110541253
authorships[2].author.orcid
authorships[2].author.display_name	Simin Luo
authorships[2].author_position	middle
authorships[2].raw_author_name	Luo, Siqi
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100707317
authorships[3].author.orcid	https://orcid.org/0009-0008-8493-0067
authorships[3].author.display_name	K. S. Zhu
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhu, Kaiwen
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100835903
authorships[4].author.orcid
authorships[4].author.display_name	Juncheng Yan
authorships[4].author_position	middle
authorships[4].raw_author_name	Yan, Juncheng
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5007550194
authorships[5].author.orcid
authorships[5].author.display_name	Y.-W. Tai
authorships[5].author_position	middle
authorships[5].raw_author_name	Tai, Yan
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5063898335
authorships[6].author.orcid	https://orcid.org/0009-0006-6811-7602
authorships[6].author.display_name	Jiayi Lei
authorships[6].author_position	middle
authorships[6].raw_author_name	Lei, Jiayi
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5013296368
authorships[7].author.orcid	https://orcid.org/0000-0002-1432-161X
authorships[7].author.display_name	Yuewen Cao
authorships[7].author_position	middle
authorships[7].raw_author_name	Cao, Yuewen
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5102957216
authorships[8].author.orcid	https://orcid.org/0000-0003-3175-5089
authorships[8].author.display_name	Keqi Wang
authorships[8].author_position	middle
authorships[8].raw_author_name	Wang, Keqi
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5100710570
authorships[9].author.orcid	https://orcid.org/0000-0003-0852-0767
authorships[9].author.display_name	Yibin Wang
authorships[9].author_position	middle
authorships[9].raw_author_name	Wang, Yibin
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5039083155
authorships[10].author.orcid	https://orcid.org/0000-0003-4059-6809
authorships[10].author.display_name	Junhong Bai
authorships[10].author_position	middle
authorships[10].raw_author_name	Bai, Jinbin
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5100687223
authorships[11].author.orcid	https://orcid.org/0000-0001-9217-5120
authorships[11].author.display_name	Qian Yu
authorships[11].author_position	middle
authorships[11].raw_author_name	Yu, Qian
authorships[11].is_corresponding	False
authorships[12].author.id	https://openalex.org/A5110373151
authorships[12].author.orcid
authorships[12].author.display_name	Du Jiang
authorships[12].author_position	middle
authorships[12].raw_author_name	Jiang, Dengyang
authorships[12].is_corresponding	False
authorships[13].author.id	https://openalex.org/A5103810405
authorships[13].author.orcid	https://orcid.org/0009-0004-6272-3543
authorships[13].author.display_name	Y. N. Pu
authorships[13].author_position	middle
authorships[13].raw_author_name	Pu, Yuandong
authorships[13].is_corresponding	False
authorships[14].author.id	https://openalex.org/A5045279290
authorships[14].author.orcid	https://orcid.org/0000-0001-6637-8741
authorships[14].author.display_name	Haoxing Chen
authorships[14].author_position	middle
authorships[14].raw_author_name	Chen, Haoxing
authorships[14].is_corresponding	False
authorships[15].author.id	https://openalex.org/A5100310256
authorships[15].author.orcid
authorships[15].author.display_name	Le Zhuo
authorships[15].author_position	middle
authorships[15].raw_author_name	Zhuo, Le
authorships[15].is_corresponding	False
authorships[16].author.id	https://openalex.org/A5100860922
authorships[16].author.orcid
authorships[16].author.display_name	Junjun He
authorships[16].author_position	middle
authorships[16].raw_author_name	He, Junjun
authorships[16].is_corresponding	False
authorships[17].author.id	https://openalex.org/A5046378812
authorships[17].author.orcid	https://orcid.org/0000-0002-5297-6756
authorships[17].author.display_name	Gen Luo
authorships[17].author_position	middle
authorships[17].raw_author_name	Luo, Gen
authorships[17].is_corresponding	False
authorships[18].author.id	https://openalex.org/A5082365525
authorships[18].author.orcid	https://orcid.org/0000-0003-2167-586X
authorships[18].author.display_name	Tianbin Li
authorships[18].author_position	middle
authorships[18].raw_author_name	Li, Tianbin
authorships[18].is_corresponding	False
authorships[19].author.id	https://openalex.org/A5034776433
authorships[19].author.orcid	https://orcid.org/0000-0002-2744-6294
authorships[19].author.display_name	Ming Hu
authorships[19].author_position	middle
authorships[19].raw_author_name	Hu, Ming
authorships[19].is_corresponding	False
authorships[20].author.id	https://openalex.org/A5106454325
authorships[20].author.orcid	https://orcid.org/0000-0002-3969-5474
authorships[20].author.display_name	Ye Jin
authorships[20].author_position	middle
authorships[20].raw_author_name	Ye, Jin
authorships[20].is_corresponding	False
authorships[21].author.id	https://openalex.org/A5114653165
authorships[21].author.orcid
authorships[21].author.display_name	Shenglong Ye
authorships[21].author_position	middle
authorships[21].raw_author_name	Ye, Shenglong
authorships[21].is_corresponding	False
authorships[22].author.id	https://openalex.org/A5106513223
authorships[22].author.orcid	https://orcid.org/0000-0002-5027-892X
authorships[22].author.display_name	Bo Zhang
authorships[22].author_position	middle
authorships[22].raw_author_name	Zhang, Bo
authorships[22].is_corresponding	False
authorships[23].author.id	https://openalex.org/A5001529504
authorships[23].author.orcid	https://orcid.org/0000-0002-4756-0609
authorships[23].author.display_name	Chang Xu
authorships[23].author_position	middle
authorships[23].raw_author_name	Xu, Chang
authorships[23].is_corresponding	False
authorships[24].author.id	https://openalex.org/A5101827340
authorships[24].author.orcid	https://orcid.org/0000-0002-2418-3134
authorships[24].author.display_name	Wenhai Wang
authorships[24].author_position	middle
authorships[24].raw_author_name	Wang, Wenhai
authorships[24].is_corresponding	False
authorships[25].author.id	https://openalex.org/A5100732450
authorships[25].author.orcid	https://orcid.org/0000-0002-2664-7975
authorships[25].author.display_name	Hongsheng Li
authorships[25].author_position	middle
authorships[25].raw_author_name	Li, Hongsheng
authorships[25].is_corresponding	False
authorships[26].author.id	https://openalex.org/A5064168853
authorships[26].author.orcid	https://orcid.org/0000-0001-8165-9322
authorships[26].author.display_name	Guangtao Zhai
authorships[26].author_position	middle
authorships[26].raw_author_name	Zhai, Guangtao
authorships[26].is_corresponding	False
authorships[27].author.id	https://openalex.org/A5100552155
authorships[27].author.orcid
authorships[27].author.display_name	Tianfan Xue
authorships[27].author_position	middle
authorships[27].raw_author_name	Xue, Tianfan
authorships[27].is_corresponding	False
authorships[28].author.id	https://openalex.org/A5101784533
authorships[28].author.orcid	https://orcid.org/0000-0002-1526-8654
authorships[28].author.display_name	Bin Fu
authorships[28].author_position	middle
authorships[28].raw_author_name	Fu, Bin
authorships[28].is_corresponding	False
authorships[29].author.id	https://openalex.org/A5100321200
authorships[29].author.orcid
authorships[29].author.display_name	Xiaohong Liu
authorships[29].author_position	middle
authorships[29].raw_author_name	Liu, Xiaohong
authorships[29].is_corresponding	False
authorships[30].author.id	https://openalex.org/A5100748135
authorships[30].author.orcid	https://orcid.org/0000-0002-1889-2567
authorships[30].author.display_name	Yu Qiao
authorships[30].author_position	middle
authorships[30].raw_author_name	Qiao, Yu
authorships[30].is_corresponding	False
authorships[31].author.id	https://openalex.org/A5107946409
authorships[31].author.orcid
authorships[31].author.display_name	Yihao Liu
authorships[31].author_position	last
authorships[31].raw_author_name	Liu, Yihao
authorships[31].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2510.06308
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-18T00:00:00
display_name	Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10181
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9868000149726868
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Natural Language Processing Techniques
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2510.06308
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2510.06308
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2510.06308
primary_location.id	pmh:oai:arXiv.org:2510.06308
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2510.06308
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2510.06308
publication_date	2025-10-07
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	23, 58
abstract_inverted_index.To	96
abstract_inverted_index.We	0
abstract_inverted_index.an	3
abstract_inverted_index.as	78, 80
abstract_inverted_index.by	21
abstract_inverted_index.in	100
abstract_inverted_index.of	61
abstract_inverted_index.on	87
abstract_inverted_index.or	51
abstract_inverted_index.to	28, 41, 47, 113
abstract_inverted_index.we	107
abstract_inverted_index.and	11, 31, 55, 74, 102, 111
abstract_inverted_index.for	7
abstract_inverted_index.our	109
abstract_inverted_index.the	114
abstract_inverted_index.(AR)	50
abstract_inverted_index.This	36
abstract_inverted_index.code	110
abstract_inverted_index.from	17
abstract_inverted_index.sets	14
abstract_inverted_index.well	79
abstract_inverted_index.Page:	117
abstract_inverted_index.apart	16
abstract_inverted_index.broad	59
abstract_inverted_index.fully	24
abstract_inverted_index.image	70, 75, 81
abstract_inverted_index.model	6, 105
abstract_inverted_index.prior	18
abstract_inverted_index.(e.g.,	69
abstract_inverted_index.across	33
abstract_inverted_index.allows	39
abstract_inverted_index.etc.),	77
abstract_inverted_index.foster	97
abstract_inverted_index.handle	29
abstract_inverted_index.higher	43
abstract_inverted_index.hybrid	52
abstract_inverted_index.inputs	30
abstract_inverted_index.itself	15
abstract_inverted_index.models	20
abstract_inverted_index.tasks,	63
abstract_inverted_index.Project	116
abstract_inverted_index.achieve	42
abstract_inverted_index.adeptly	56
abstract_inverted_index.further	98
abstract_inverted_index.models.	95
abstract_inverted_index.outputs	32
abstract_inverted_index.release	108
abstract_inverted_index.support	57
abstract_inverted_index.unified	19, 93
abstract_inverted_index.various	34
abstract_inverted_index.achieves	84
abstract_inverted_index.approach	38
abstract_inverted_index.compared	46
abstract_inverted_index.discrete	25, 103
abstract_inverted_index.editing,	71
abstract_inverted_index.existing	91
abstract_inverted_index.modeling	27
abstract_inverted_index.multiple	88
abstract_inverted_index.previous	48
abstract_inverted_index.sampling	44
abstract_inverted_index.seamless	8
abstract_inverted_index.spectrum	60
abstract_inverted_index.diffusion	26, 104
abstract_inverted_index.including	64
abstract_inverted_index.introduce	1
abstract_inverted_index.paradigms	54
abstract_inverted_index.research,	106
abstract_inverted_index.utilizing	22
abstract_inverted_index.community.	115
abstract_inverted_index.efficiency	45
abstract_inverted_index.generation	10, 68
abstract_inverted_index.innovative	37
abstract_inverted_index.surpassing	90
abstract_inverted_index.benchmarks,	89
abstract_inverted_index.checkpoints	112
abstract_inverted_index.generation,	66, 73
abstract_inverted_index.inpainting,	76
abstract_inverted_index.modalities.	35
abstract_inverted_index.multi-modal	9, 62, 94, 101
abstract_inverted_index.open-source	4, 92
abstract_inverted_index.performance	86
abstract_inverted_index.AR-Diffusion	53
abstract_inverted_index.Lumina-DiMOO	13, 40, 83
abstract_inverted_index.advancements	99
abstract_inverted_index.foundational	5
abstract_inverted_index.Lumina-DiMOO,	2
abstract_inverted_index.text-to-image	65
abstract_inverted_index.autoregressive	49
abstract_inverted_index.image-to-image	67
abstract_inverted_index.subject-driven	72
abstract_inverted_index.understanding.	12, 82
abstract_inverted_index.state-of-the-art	85
abstract_inverted_index.https://synbol.github.io/Lumina-DiMOO.	118
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	32
citation_normalized_percentile