{"id":"https://openalex.org/W4415275428","doi":"https://doi.org/10.1109/iccv51701.2025.01909","title":"End-to-End Multi-Modal Diffusion Mamba","display_name":"End-to-End Multi-Modal Diffusion Mamba","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415275428","doi":"https://doi.org/10.1109/iccv51701.2025.01909"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.01909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.13253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102510409","display_name":"Chunhao Lu","orcid":"https://orcid.org/0009-0004-8024-4028"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhao Lu","raw_affiliation_strings":["China University of Petroleum-Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058644929","display_name":"Qiang L\u00fc","orcid":"https://orcid.org/0000-0001-8217-2305"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Lu","raw_affiliation_strings":["China University of Petroleum-Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Meichen Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meichen Dong","raw_affiliation_strings":["China University of Petroleum-Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum-Beijing","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075356940","display_name":"Jake Luo","orcid":"https://orcid.org/0000-0002-3900-643X"},"institutions":[{"id":"https://openalex.org/I43579087","display_name":"University of Wisconsin\u2013Milwaukee","ror":"https://ror.org/031q21x57","country_code":"US","type":"education","lineage":["https://openalex.org/I43579087"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jake Luo","raw_affiliation_strings":["University of Wisconsin-Milwaukee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Milwaukee","institution_ids":["https://openalex.org/I43579087"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20529","last_page":"20540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.32199999690055847,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.32199999690055847,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7141000032424927},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6973000168800354},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6615999937057495},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6432999968528748},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6341999769210815},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5669000148773193},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5519000291824341},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47690001130104065},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4293999969959259}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7141000032424927},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6973000168800354},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6615999937057495},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319000124931335},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544999837875366},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39309999346733093},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.32190001010894775},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2596000134944916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25769999623298645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01909","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01909","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.13253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.13253","pdf_url":"https://arxiv.org/pdf/2510.13253","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.13253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.13253","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.13253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.13253","pdf_url":"https://arxiv.org/pdf/2510.13253","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415275428.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"end-to-end":[1,111,148],"multi-modal":[2,27,137,149],"models":[3,112,123],"utilize":[4],"different":[5],"encoders":[6],"and":[7,12,50,62,82,102,115,118,128],"decoders":[8],"to":[9,47,69],"process":[10],"input":[11],"output":[13],"information.":[14],"This":[15,64],"separation":[16],"hinders":[17],"the":[18],"joint":[19],"representation":[20],"learning":[21],"of":[22],"various":[23],"modalities.":[24],"To":[25],"unify":[26],"processing,":[28],"we":[29],"propose":[30],"a":[31,41,55,144],"novel":[32],"architecture":[33],"called":[34],"MDM":[35,39,68,107],"(Multi-modal":[36],"Diffusion":[37],"Mamba).":[38],"utilizes":[40],"Mamba-based":[42],"multi-step":[43],"selection":[44],"diffusion":[45],"model":[46],"progressively":[48],"generate":[49],"refine":[51],"modality-specific":[52],"information":[53],"through":[54],"unified":[56],"variational":[57],"autoencoder":[58],"for":[59,147],"both":[60],"encoding":[61],"decoding.":[63],"innovative":[65],"approach":[66],"allows":[67],"achieve":[70],"superior":[71],"performance":[72],"when":[73],"processing":[74],"high-dimensional":[75],"data,":[76],"particularly":[77],"in":[78,89,135],"generating":[79],"high-resolution":[80],"images":[81],"extended":[83],"text":[84,100],"sequences":[85],"simultaneously.":[86],"Our":[87,130],"evaluations":[88],"areas":[90],"such":[91],"as":[92],"image":[93,95],"generation,":[94],"captioning,":[96],"visual":[97],"question":[98],"answering,":[99],"comprehension,":[101],"reasoning":[103],"tasks":[104],"demonstrate":[105],"that":[106],"significantly":[108],"outperforms":[109],"existing":[110],"(MonoFormer,":[113],"LlamaGen,":[114],"Chameleon":[116],"etc.)":[117],"competes":[119],"effectively":[120],"with":[121],"SOTA":[122],"like":[124],"GPT-4V,":[125],"Gemini":[126],"Pro,":[127],"Mistral.":[129],"results":[131],"validate":[132],"MDM's":[133],"effectiveness":[134],"unifying":[136],"processes":[138],"while":[139],"maintaining":[140],"computational":[141],"efficiency,":[142],"establishing":[143],"new":[145],"direction":[146],"architectures.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-17T00:00:00"}