{"id":"https://openalex.org/W7213243304","doi":"https://doi.org/10.48550/arxiv.2609.15863","title":"LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows","display_name":"LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows","publication_year":2026,"publication_date":"2026-09-14","ids":{"openalex":"https://openalex.org/W7213243304","doi":"https://doi.org/10.48550/arxiv.2609.15863"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.15863","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.15863","pdf_url":"https://arxiv.org/pdf/2609.15863","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.15863","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051298007","display_name":"Xiaofeng Mao","orcid":"https://orcid.org/0000-0003-4486-556X","observed_orcids":["https://orcid.org/0000-0003-4486-556X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Xiaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151734072","display_name":"Peijia Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Peijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120058216","display_name":"Shaohao Rui","orcid":"https://orcid.org/0009-0005-2991-9920","observed_orcids":["https://orcid.org/0009-0005-2991-9920"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui, Shaohao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151838018","display_name":"Yibo Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000079121","display_name":"Haibin Wan","orcid":"https://orcid.org/0000-0002-2560-0462","observed_orcids":["https://orcid.org/0000-0002-2560-0462"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Haibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5151763831","display_name":"Weijie Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Weijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/video-diffusion-models","display_name":"video diffusion models","score":0.9350000023841858},{"id":"https://openalex.org/keywords/3d-scene-editing","display_name":"3D scene editing","score":0.7059999704360962},{"id":"https://openalex.org/keywords/long-video-generation","display_name":"long video generation","score":0.7760000228881836},{"id":"https://openalex.org/keywords/real-time-video-generation","display_name":"real-time video generation","score":0.7390000224113464},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273000121116638},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6014999747276306},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5130000114440918},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4124000072479248},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3882000148296356},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.2953999936580658},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.15863","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.15863","pdf_url":"https://arxiv.org/pdf/2609.15863","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.15863","doi":"https://doi.org/10.48550/arxiv.2609.15863","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.15863","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.15863","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.15863","pdf_url":"https://arxiv.org/pdf/2609.15863","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213243304.pdf","grobid_xml":"https://content.openalex.org/works/W7213243304.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2962785568","https://openalex.org/W4312446817","https://openalex.org/W4323717348","https://openalex.org/W4366208220","https://openalex.org/W4392679398","https://openalex.org/W4402387301","https://openalex.org/W4402704721","https://openalex.org/W4403580037","https://openalex.org/W4403791714","https://openalex.org/W4405096483","https://openalex.org/W4409092337","https://openalex.org/W4414928226","https://openalex.org/W4415100190","https://openalex.org/W4415255153","https://openalex.org/W4415337140","https://openalex.org/W4415797645","https://openalex.org/W4417136857","https://openalex.org/W7118020094","https://openalex.org/W7118630684","https://openalex.org/W7118660679","https://openalex.org/W7150811503","https://openalex.org/W7160205379","https://openalex.org/W7162394427","https://openalex.org/W7162774592","https://openalex.org/W7163380451","https://openalex.org/W7204440733"],"related_works":["https://openalex.org/W7137945250","https://openalex.org/W7128618218","https://openalex.org/W7107877224","https://openalex.org/W7161843529","https://openalex.org/W7128509820","https://openalex.org/W7162079320","https://openalex.org/W4403990754","https://openalex.org/W7117701336","https://openalex.org/W7118934409","https://openalex.org/W4303440777"],"abstract_inverted_index":{"Video":[0],"diffusion":[1,82,133],"models":[2],"are":[3],"stochastic":[4],"and":[5,18,25,97,111,151,163,181,191,204,216,236],"hard":[6],"to":[7,116],"control:":[8],"precise":[9],"content":[10],"often":[11],"requires":[12],"repeated":[13],"sampling":[14],"without":[15],"guaranteed":[16],"success,":[17],"long-horizon":[19],"scenes":[20],"drift":[21],"in":[22],"appearance,":[23],"interactions,":[24],"temporal":[26,179],"coherence.":[27],"Agentic":[28],"visual":[29,103,118,177,241],"creation":[30],"provides":[31],"explicit":[32],"references,":[33,107],"editable":[34,108],"3D":[35,109],"scenes,":[36],"or":[37,52],"executable":[38],"game":[39,112],"states":[40],"for":[41,135,144,226,239],"stable":[42],"control,":[43,92],"but":[44],"does":[45],"not":[46],"by":[47],"itself":[48],"guarantee":[49],"high":[50],"object":[51],"character":[53],"fidelity.":[54],"Combining":[55],"the":[56],"two":[57],"can":[58],"enable":[59],"stable,":[60],"high-quality":[61],"generation.":[62,99],"To":[63],"realize":[64],"this":[65],"combination,":[66],"we":[67],"present":[68],"LynnReal-Omni,":[69],"a":[70,78,121,127,140,156,166,195,207,224,233],"native":[71],"multimodal":[72,81,132,149],"video":[73,95,145,210,229],"generation":[74,203],"framework":[75],"built":[76],"on":[77,199],"32B":[79],"shared":[80,131],"transformer":[83,134],"that":[84,171],"unifies":[85],"text-to-video,":[86],"image-conditioned":[87],"generation,":[88,90,230],"reference-guided":[89],"structural":[91],"editing,":[93],"degraded":[94],"restoration,":[96],"long-video":[98],"It":[100],"accepts":[101],"heterogeneous":[102],"inputs,":[104],"including":[105,194],"appearance":[106],"renders,":[110],"recordings,":[113],"allowing":[114],"agents":[115],"compose":[117],"conditions":[119],"within":[120],"unified":[122],"model.":[123],"We":[124,138],"also":[125],"train":[126],"dedicated":[128],"27B":[129],"Flash":[130],"real-time":[136,227],"rendering.":[137],"build":[139],"systematic":[141],"data":[142],"pipeline":[143],"cleaning,":[146],"subject":[147],"association,":[148],"annotation,":[150],"aligned":[152],"control":[153],"construction,":[154],"yielding":[155],"curated":[157],"corpus":[158],"of":[159,206],"multi-shot":[160],"audiovisual":[161],"segments,":[162],"introduce":[164],"MSAVP,":[165],"100-prompt,":[167],"20-metric":[168],"evaluation":[169],"design":[170],"separates":[172],"instruction":[173],"following,":[174],"generating":[175],"plausibility,":[176],"quality,":[178],"behavior,":[180],"audio":[182],"coordination.":[183],"LynnReal-Omni-Flash":[184],"further":[185],"reduces":[186],"inference":[187],"cost":[188],"through":[189],"model":[190],"decoding":[192,205],"acceleration,":[193],"lightweight":[196],"VAE":[197],"decoder;":[198],"one":[200],"H100,":[201],"warm":[202],"22-frame":[208],"540p":[209],"take":[211],"843":[212],"ms":[213,218],"with":[214,219],"LynnReal-Omni":[215,232],"377":[217],"Flash.":[220],"These":[221],"results":[222],"provide":[223],"foundation":[225],"streaming":[228],"making":[231],"unified,":[234],"controllable,":[235],"efficient":[237],"basis":[238],"agentic":[240],"creation.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-16T00:00:00"}