{"id":"https://openalex.org/W4414360335","doi":"https://doi.org/10.24963/ijcai.2025/1133","title":"Hallucination-Aware Prompt Optimization for Text-to-Video Synthesis","display_name":"Hallucination-Aware Prompt Optimization for Text-to-Video Synthesis","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360335","doi":"https://doi.org/10.24963/ijcai.2025/1133"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1133","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","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/A5115695120","display_name":"Jiapeng Wang","orcid":"https://orcid.org/0000-0003-1498-0305"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiapeng Wang","raw_affiliation_strings":["South China University of Technology"],"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":["Alibaba Cloud Computing"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059743923","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0001-9207-8953"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Cloud Computing"],"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology"],"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115695120"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26778451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10198","last_page":"10206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9291999936103821,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9291999936103821,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9275000095367432,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9272000193595886,"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/key","display_name":"Key (lock)","score":0.5914000272750854},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5054000020027161},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4417000114917755},{"id":"https://openalex.org/keywords/refining","display_name":"Refining (metallurgy)","score":0.3781000077724457},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3682999908924103},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769599974155426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5914000272750854},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5054000020027161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5004000067710876},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1133","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancements":[2],"in":[3,39],"AI-generated":[4],"content":[5],"(AIGC)":[6],"have":[7],"led":[8],"to":[9,41,90,112],"extensive":[10],"research":[11],"and":[12,32,84,103,130],"application":[13],"of":[14,49],"deep":[15],"text-to-video":[16],"(T2V)":[17],"synthesis":[18],"models,":[19,52],"such":[20],"as":[21],"OpenAI's":[22],"Sora.":[23],"These":[24],"models":[25],"typically":[26],"rely":[27],"on":[28,121],"high-quality":[29,43],"prompt-video":[30],"pairs":[31],"detailed":[33,70],"text":[34],"prompts":[35,71,77,89],"for":[36],"model":[37,60],"training":[38],"order":[40],"produce":[42],"videos.":[44],"To":[45],"boost":[46],"the":[47,105,114],"effectiveness":[48],"Sora-like":[50],"T2V":[51,62,92],"we":[53],"introduce":[54],"VidPrompter,":[55],"an":[56],"innovative":[57],"large":[58],"multi-modal":[59],"supporting":[61],"applications":[63],"with":[64,81],"three":[65],"key":[66],"functionalities:":[67],"(1)":[68],"generating":[69],"from":[72,78],"raw":[73],"videos,":[74],"(2)":[75],"enhancing":[76],"videos":[79],"grounded":[80],"short":[82],"descriptions,":[83],"(3)":[85],"refining":[86],"simple":[87],"user-provided":[88],"elevate":[91],"video":[93],"quality.":[94],"We":[95],"train":[96],"VidPrompter":[97],"using":[98],"a":[99],"hybrid":[100],"multi-task":[101,116],"paradigm":[102],"propose":[104],"hallucination-aware":[106],"direct":[107],"preference":[108],"optimization":[109,118],"(HDPO)":[110],"technique":[111],"improve":[113],"multi-modal,":[115],"prompt":[117],"process.":[119],"Experiments":[120],"various":[122],"tasks":[123],"show":[124],"our":[125],"method":[126],"surpasses":[127],"strong":[128],"baselines":[129],"other":[131],"competitors.":[132]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}