{"id":"https://openalex.org/W7138428164","doi":"https://doi.org/10.1609/aaai.v40i15.38285","title":"VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning","display_name":"VQ-Insight: Teaching VLMs for AI-Generated Video Quality Understanding via Progressive Visual Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138428164","doi":"https://doi.org/10.1609/aaai.v40i15.38285"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i15.38285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38285/42247","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38285/42247","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129734541","display_name":"Xuanyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuanyu Zhang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University\nByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University\nByteDance Inc","institution_ids":["https://openalex.org/I111483173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745085","display_name":"Weiqi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqi Li","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735201","display_name":"Shijie Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijie Zhao","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745467","display_name":"Junlin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junlin Li","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129732734","display_name":"Li Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["ByteDance Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129680065","display_name":"Jian Dong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"12870","last_page":"12878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.5685999989509583,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.5685999989509583,"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":0.12359999865293503,"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":0.10350000113248825,"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/generalization","display_name":"Generalization","score":0.6933000087738037},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.6450999975204468},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6381000280380249},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.47540000081062317},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.3944999873638153},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.375},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.34049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141000270843506},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6933000087738037},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.6450999975204468},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6381000280380249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303999781608582},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3944999873638153},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.375},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C114227958","wikidata":"https://www.wikidata.org/wiki/Q7631422","display_name":"Subjective video quality","level":4,"score":0.3393999934196472},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2988634675","wikidata":"https://www.wikidata.org/wiki/Q34508","display_name":"Video recording","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i15.38285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38285/42247","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38285","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i15.38285","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38285/42247","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4080508351325989,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G822965519","display_name":null,"funder_award_id":"62372016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138428164.pdf","grobid_xml":"https://content.openalex.org/works/W7138428164.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,138,151],"AI-generated":[3],"content":[4],"(AIGC)":[5],"have":[6],"led":[7],"to":[8,28,69,132],"the":[9,20,42,114,119],"emergence":[10],"of":[11,22,32,44,57,121],"powerful":[12],"text-to-video":[13],"generation":[14,48,116,165],"models.":[15,49],"Despite":[16],"these":[17,76],"successes,":[18],"evaluating":[19],"quality":[21,89,98,104,140],"AIGC-generated":[23],"videos":[24],"remains":[25],"challenging":[26],"due":[27],"limited":[29],"generalization,":[30],"lack":[31,43],"temporal":[33,108,129],"awareness,":[34],"heavy":[35],"reliance":[36],"on":[37,54],"large-scale":[38,64],"annotated":[39,65],"datasets,":[40],"and":[41,67,72,110,128,136,156],"effective":[45],"interaction":[46],"with":[47,113],"Most":[50],"current":[51],"approaches":[52],"rely":[53],"supervised":[55],"fine-tuning":[56],"vision-language":[58],"models":[59],"(VLMs),":[60],"which":[61],"often":[62],"require":[63],"datasets":[66],"tend":[68],"decouple":[70],"understanding":[71],"generation.":[73],"To":[74],"address":[75],"shortcomings,":[77],"we":[78],"propose":[79],"VQ-Insight,":[80],"a":[81,95],"novel":[82],"reasoning-style":[83],"VLM":[84],"framework":[85],"for":[86,163],"AIGC":[87],"video":[88,97,115,139,158,164],"assessment.":[90],"Our":[91],"approach":[92],"features:":[93],"(1)":[94],"progressive":[96],"learning":[99],"scheme":[100],"that":[101,145],"combines":[102],"image":[103],"warm-up,":[105],"general":[106],"task-specific":[107],"learning,":[109],"joint":[111],"optimization":[112],"model;":[117],"(2)":[118],"design":[120],"multi-dimension":[122,154],"scoring":[123],"rewards,":[124,127],"preference":[125,152],"comparison":[126],"modeling":[130],"rewards":[131],"enhance":[133],"both":[134],"generalization":[135],"specialization":[137],"evaluation.":[141],"Extensive":[142],"experiments":[143],"demonstrate":[144],"VQ-Insight":[146],"consistently":[147],"outperforms":[148],"state-of-the-art":[149],"baselines":[150],"comparison,":[153],"scoring,":[155,159],"natural":[157],"bringing":[160],"significant":[161],"improvements":[162],"tasks.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}