{"id":"https://openalex.org/W4405655761","doi":"https://doi.org/10.1109/iccv51701.2025.01740","title":"Prompt-A-Video: Prompt your Video Diffusion Model via Preference-Aligned LLM","display_name":"Prompt-A-Video: Prompt your Video Diffusion Model via Preference-Aligned LLM","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405655761","doi":"https://doi.org/10.1109/iccv51701.2025.01740"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01740","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/2412.15156","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054673981","display_name":"Yatai Ji","orcid":"https://orcid.org/0000-0001-5096-3604"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yatai Ji","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720453","display_name":"Jiacheng Zhang","orcid":"https://orcid.org/0000-0002-2311-7629"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiacheng Zhang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724763","display_name":"Jie Ying Wu","orcid":"https://orcid.org/0000-0002-7306-8140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643296","display_name":"Shilong Zhang","orcid":"https://orcid.org/0009-0000-8844-2273"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shilong Zhang","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007602724","display_name":"Shoufa Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shoufa Chen","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037739657","display_name":"Changsheng Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chongjian Ge","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002942097","display_name":"Peize Sun","orcid":"https://orcid.org/0000-0003-0636-2224"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peize Sun","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110810014","display_name":"Weifeng Chen","orcid":"https://orcid.org/0000-0001-5040-4618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weifeng Chen","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069991337","display_name":"Wenqi Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqi Shao","raw_affiliation_strings":["Shanghai AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101051966","display_name":"Xuefeng Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuefeng Xiao","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032069360","display_name":"Wei-Lin Huang","orcid":"https://orcid.org/0000-0002-8067-6822"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilin Huang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087037018","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0003-4728-2415"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18725","last_page":"18735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9541000127792358,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9541000127792358,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9347000122070312,"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/preference","display_name":"Preference","score":0.6947730779647827},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5879056453704834},{"id":"https://openalex.org/keywords/video-recording","display_name":"Video recording","score":0.46851611137390137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46400752663612366},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.44768691062927246},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.30373668670654297},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1416349709033966},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11327722668647766},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09527051448822021}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6947730779647827},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5879056453704834},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.46851611137390137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46400752663612366},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.44768691062927246},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30373668670654297},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1416349709033966},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11327722668647766},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09527051448822021},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01740","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:2412.15156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.15156","pdf_url":"https://arxiv.org/pdf/2412.15156","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.15156","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.15156","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:2412.15156","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.15156","pdf_url":"https://arxiv.org/pdf/2412.15156","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405655761.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2090624569","https://openalex.org/W4252225730","https://openalex.org/W4381329258","https://openalex.org/W2090638348","https://openalex.org/W2181148280","https://openalex.org/W2891635047","https://openalex.org/W2460166022","https://openalex.org/W2368374794","https://openalex.org/W322430648","https://openalex.org/W1245007219"],"abstract_inverted_index":{"Text-to-video":[0],"models":[1],"have":[2],"made":[3],"remarkable":[4],"advancements":[5],"through":[6],"optimization":[7,98,144],"on":[8],"high-quality":[9],"text-video":[10],"pairs,":[11],"where":[12],"the":[13,28,124,136,141,160,173],"textual":[14],"prompts":[15,47,84,114],"play":[16],"a":[17,94,105],"pivotal":[18],"role":[19],"in":[20,78],"determining":[21],"quality":[22],"of":[23,123,162,175],"output":[24,30],"videos.":[25],"However,":[26],"achieving":[27],"desired":[29],"often":[31],"entails":[32],"multiple":[33],"revisions":[34],"and":[35,54,82,99,116,155],"iterative":[36],"inference":[37],"to":[38,58,86,110,131,147,171],"refine":[39],"user-provided":[40],"prompts.":[41],"Current":[42],"automatic":[43],"methods":[44],"for":[45,119,135],"refining":[46],"encounter":[48],"challenges":[49],"such":[50],"as":[51,74],"Modality-Inconsistency,":[52],"Cost-Discrepancy,":[53],"Model-Unaware":[55],"when":[56],"applied":[57],"text-to-video":[59],"diffusion":[60,89],"models.":[61],"To":[62],"address":[63],"these":[64],"problem,":[65],"we":[66,103,158],"introduce":[67],"an":[68],"LLM-based":[69],"prompt":[70,107],"adaptation":[71],"framework,":[72],"termed":[73],"Prompt-A-Video,":[75],"which":[76],"excels":[77],"crafting":[79],"Video-Centric,":[80],"Labor-Free":[81],"Preference-Aligned":[83],"tailored":[85],"specific":[87],"video":[88,176],"model.":[90],"Our":[91],"approach":[92],"involves":[93],"meticulously":[95],"crafted":[96],"two-stage":[97],"alignment":[100],"system.":[101],"Initially,":[102],"conduct":[104],"reward-guided":[106],"evolution":[108],"pipeline":[109],"automatically":[111],"create":[112],"optimal":[113],"pool":[115],"leverage":[117],"them":[118],"supervised":[120],"fine-tuning":[121],"(SFT)":[122],"LLM.":[125],"Then":[126],"multi-dimensional":[127],"rewards":[128],"are":[129],"employed":[130],"generate":[132],"pairwise":[133],"data":[134],"SFT":[137],"model,":[138],"followed":[139],"by":[140],"direct":[142],"preference":[143,150],"(DPO)":[145],"algorithm":[146],"further":[148],"facilitate":[149],"alignment.":[151],"Through":[152],"extensive":[153],"experimentation":[154],"comparative":[156],"analyses,":[157],"validate":[159],"effectiveness":[161],"Prompt-A-Video":[163],"across":[164],"diverse":[165],"generation":[166],"models,":[167],"highlighting":[168],"its":[169],"potential":[170],"push":[172],"boundaries":[174],"generation.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-12-21T00:00:00"}
