{"id":"https://openalex.org/W7160140400","doi":"https://doi.org/10.1109/iccv51701.2025.01448","title":"The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation","display_name":"The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160140400","doi":"https://doi.org/10.1109/iccv51701.2025.01448"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.01448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01448","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077059859","display_name":"Aoxiong Yin","orcid":"https://orcid.org/0000-0002-1374-9016"},"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":"Aoxiong Yin","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/A5135119503","display_name":"Xu Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160977","display_name":"Health Decisions (United States)","ror":"https://ror.org/050ey5v22","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Moonshot AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Moonshot AI","institution_ids":["https://openalex.org/I4210160977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135118567","display_name":"Kai Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160977","display_name":"Health Decisions (United States)","ror":"https://ror.org/050ey5v22","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Shen","raw_affiliation_strings":["Moonshot AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Moonshot AI","institution_ids":["https://openalex.org/I4210160977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135138365","display_name":"Yichong Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160977","display_name":"Health Decisions (United States)","ror":"https://ror.org/050ey5v22","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yichong Leng","raw_affiliation_strings":["Moonshot AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Moonshot AI","institution_ids":["https://openalex.org/I4210160977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135242832","display_name":"Xinyu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160977","display_name":"Health Decisions (United States)","ror":"https://ror.org/050ey5v22","country_code":"US","type":"company","lineage":["https://openalex.org/I4210160977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyu Zhou","raw_affiliation_strings":["Moonshot AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Moonshot AI","institution_ids":["https://openalex.org/I4210160977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135099864","display_name":"Juncheng Li","orcid":null},"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":"Juncheng Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135222839","display_name":"Siliang Tang","orcid":null},"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":"Siliang Tang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4203999936580658,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4203999936580658,"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/T11439","display_name":"Video Analysis and Summarization","score":0.06909999996423721,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0551999993622303,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.373199999332428},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36890000104904175},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2766999900341034},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27410000562667847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26269999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.01448","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01448","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5196816921234131}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2115907784","https://openalex.org/W2476548250","https://openalex.org/W3094502228","https://openalex.org/W3180355996","https://openalex.org/W4312633146","https://openalex.org/W4385245566","https://openalex.org/W4386065764","https://openalex.org/W4388979610","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874575","https://openalex.org/W4402660110","https://openalex.org/W4402672068","https://openalex.org/W4402702927","https://openalex.org/W4402727359","https://openalex.org/W4402727536","https://openalex.org/W4402727736","https://openalex.org/W4402727910","https://openalex.org/W4403716358","https://openalex.org/W4405695475"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-05T00:00:00"}
