{"id":"https://openalex.org/W4415320170","doi":"https://doi.org/10.48550/arxiv.2505.12489","title":"Video-GPT via Next Clip Diffusion","display_name":"Video-GPT via Next Clip Diffusion","publication_year":2025,"publication_date":"2025-05-18","ids":{"openalex":"https://openalex.org/W4415320170","doi":"https://doi.org/10.48550/arxiv.2505.12489"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.12489","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12489","pdf_url":"https://arxiv.org/pdf/2505.12489","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":"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/2505.12489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051160520","display_name":"Shaobin Zhuang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Shaobin","raw_affiliation_strings":["University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595387","display_name":"Zhipeng Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Zhipeng","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Ying","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Ying","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106588135","display_name":"Fangyikang Wang","orcid":"https://orcid.org/0009-0005-2805-2093","observed_orcids":["https://orcid.org/0009-0005-2805-2093"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Fangyikang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086125857","display_name":"Canmiao Fu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu, Canmiao","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034555264","display_name":"Binxin Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Binxin","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101713677","display_name":"Chong Sun","orcid":"https://orcid.org/0000-0002-8299-9094","observed_orcids":["https://orcid.org/0000-0002-8299-9094"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Chong","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chen","raw_affiliation_strings":["WeChat Vision , Tencent Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeChat Vision , Tencent Inc","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100335705","display_name":"Yali Wang","orcid":"https://orcid.org/0000-0002-2999-7428","observed_orcids":["https://orcid.org/0000-0002-2999-7428"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yali","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology , Chinese Academy of Sciences Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology , Chinese Academy of Sciences Shanghai AI Laboratory","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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":0.8047000169754028,"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":0.8047000169754028,"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":0.19040000438690186,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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-prediction","display_name":"video prediction","score":0.5699999928474426},{"id":"https://openalex.org/keywords/video-generation","display_name":"video generation","score":0.5180000066757202},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.8349999785423279},{"id":"https://openalex.org/keywords/world-modeling","display_name":"world modeling","score":0.7570000290870667},{"id":"https://openalex.org/keywords/physics-reasoning","display_name":"physics reasoning","score":0.335999995470047},{"id":"https://openalex.org/keywords/long-term-forecasting","display_name":"long-term forecasting","score":0.5090000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192999720573425},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389999747276306},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5354999899864197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49639999866485596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.12489","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12489","pdf_url":"https://arxiv.org/pdf/2505.12489","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.12489","doi":"https://doi.org/10.48550/arxiv.2505.12489","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12489","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.12489","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12489","pdf_url":"https://arxiv.org/pdf/2505.12489","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415320170.pdf","grobid_xml":"https://content.openalex.org/works/W4415320170.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4399794740","https://openalex.org/W4415798317","https://openalex.org/W4361193613","https://openalex.org/W4414973400","https://openalex.org/W4391047144","https://openalex.org/W7164176742","https://openalex.org/W4388185106","https://openalex.org/W4417299455","https://openalex.org/W4416550773","https://openalex.org/W4393159976"],"abstract_inverted_index":{"GPT":[0],"has":[1],"shown":[2],"its":[3,156],"remarkable":[4],"success":[5],"in":[6,21,44,63,105,149,160],"natural":[7],"language":[8,12,52],"processing.":[9],"However,":[10],"the":[11,22,26,78,97,102,106,114,122],"sequence":[13,28],"is":[14,29,121,165],"not":[15],"sufficient":[16],"to":[17,59,86,101],"describe":[18],"spatial-temporal":[19],"details":[20],"visual":[23,54],"world.":[24],"Alternatively,":[25],"video":[27,49,118,147,151],"good":[30],"at":[31,166],"capturing":[32],"such":[33],"details.":[34],"Motivated":[35],"by":[36,47,94],"this":[37,45,81],"fact,":[38],"we":[39,65],"propose":[40],"a":[41,67],"concise":[42],"Video-GPT":[43,85,112,130],"paper":[46],"treating":[48],"as":[50],"new":[51],"for":[53,73],"world":[55,126],"modeling.":[56],"By":[57],"analogy":[58],"next":[60,69],"token":[61],"prediction":[62],"GPT,":[64],"introduce":[66],"novel":[68],"clip":[70,99],"diffusion":[71],"paradigm":[72,83],"pretraining":[74],"Video-GPT.":[75],"Different":[76],"from":[77],"previous":[79],"works,":[80],"distinct":[82],"allows":[84],"tackle":[87],"both":[88,150],"short-term":[89],"generation":[90,152],"and":[91,153],"long-term":[92],"prediction,":[93,119],"autoregressively":[95],"denoising":[96],"noisy":[98],"according":[100],"clean":[103],"clips":[104],"history.":[107],"Extensive":[108],"experiments":[109],"show":[110],"our":[111],"achieves":[113],"state-of-the-art":[115],"performance":[116],"on":[117,144],"which":[120],"key":[123],"factor":[124],"towards":[125],"modeling":[127],"(Physics-IQ":[128],"Benchmark:":[129],"34.97":[131],"vs.":[132,135],"Kling":[133],"23.64":[134],"Wan":[136],"20.89).":[137],"Moreover,":[138],"it":[139],"can":[140],"be":[141],"well":[142],"adapted":[143],"6":[145],"mainstream":[146],"tasks":[148],"understanding,":[154],"showing":[155],"great":[157],"generalization":[158],"capacity":[159],"downstream.":[161],"The":[162],"project":[163],"page":[164],"https://zhuangshaobin.github.io/Video-GPT.github.io/.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}