{"id":"https://openalex.org/W7158865827","doi":"https://doi.org/10.1145/3805712.3809728","title":"An Action-Aware Generative Sequence Modeling for Short Video Recommendation","display_name":"An Action-Aware Generative Sequence Modeling for Short Video Recommendation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7158865827","doi":"https://doi.org/10.1145/3805712.3809728"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809728","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134895483","display_name":"Wenhao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Li","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5428-258X","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134893930","display_name":"Zihan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Lin","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6877-4470","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134843745","display_name":"Zhengxiao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZhengXiao Guo","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-4680-5190","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134905970","display_name":"Jie Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2094-4255","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134877241","display_name":"Shukai Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shukai Liu","raw_affiliation_strings":["Unaffiliated, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-9492-9868","affiliations":[{"raw_affiliation_string":"Unaffiliated, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134893712","display_name":"Yongqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Liu","raw_affiliation_strings":["Kuaishou Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-2153-6722","affiliations":[{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134920305","display_name":"Chuan Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Luo","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5028-1064","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4544182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"958","last_page":"968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.6559000015258789,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.6559000015258789,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.07360000163316727,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04500000178813934,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5626000165939331},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5604000091552734},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5236999988555908},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5232999920845032},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4975000023841858},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4586000144481659},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4287000000476837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276000022888184},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4975000023841858},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48500001430511475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.45980000495910645},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4586000144481659},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.31700000166893005},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2778956030","wikidata":"https://www.wikidata.org/wiki/Q5142477","display_name":"Cold start (automotive)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3809728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809728","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.25834","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.25834","pdf_url":"https://arxiv.org/pdf/2604.25834","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809728","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,5,13,37,88,132,148,167,193,202,206,211],"rapid":[2],"development":[3],"of":[4,16,42,90,102,213,246],"Internet,":[6],"users":[7,33,274],"have":[8],"increasingly":[9],"higher":[10],"expectations":[11],"for":[12,140,189],"recommendation":[14,57],"accuracy":[15],"online":[17,220],"content":[18],"consumption":[19,79],"platforms":[20],"(e.g.,":[21,44,126],"short":[22,26],"video":[23,62],"platforms).":[24],"However,":[25],"videos":[27],"often":[28],"contain":[29],"diverse":[30,95],"segments,":[31],"and":[32,100,128,135,143,205,256],"may":[34,47],"not":[35,48],"hold":[36],"same":[38],"attitude":[39],"toward":[40],"all":[41,50,268],"them":[43,137],"music":[45],"enthusiasts":[46],"enjoy":[49],"songs":[51],"in":[52,70,235,248,253,258],"a":[53,61,64,81,111,187],"medley).":[54],"Traditional":[55],"binary-classification":[56],"models,":[58],"which":[59,122],"treat":[60],"as":[63],"single":[65],"holistic":[66],"entity,":[67],"face":[68],"limitations":[69],"accurately":[71],"capturing":[72],"such":[73],"nuanced":[74],"preferences.":[75],"Considering":[76],"that":[77,87],"user":[78,91,124,249,260],"is":[80],"temporal":[82,133,174],"process,":[83],"this":[84,107],"paper":[85],"demonstrates":[86],"timing":[89],"actions":[92,125],"can":[93],"represent":[94],"intentions":[96],"through":[97,182,218],"statistical":[98],"analysis":[99],"examination":[101],"action":[103,155,175,190],"patterns.":[104],"Based":[105],"on":[106,201,224],"insight,":[108],"we":[109,146,165,185],"propose":[110],"novel":[112],"modeling":[113],"paradigm:":[114],"Action-Aware":[115],"Gen":[116],"erative":[117],"Sequence":[118,169],"Network":[119],"(A2Gen":[120],"),":[121],"refines":[123],"Like":[127],"Follow,":[129],"etc.)":[130],"along":[131],"dimension":[134],"chains":[136],"into":[138],"sequences":[139,156],"unified":[141],"processing":[142],"prediction.":[144],"First,":[145],"introduce":[147],"Context-aware":[149],"Attention":[150],"Module":[151],"(CAM)":[152],"to":[153,172,264],"model":[154,228],"enriched":[157],"with":[158],"item-specific":[159],"contextual":[160],"features.":[161],"Building":[162],"upon":[163],"this,":[164],"develop":[166],"Hierarchical":[168],"Encoder":[170],"(HSE)":[171],"learn":[173],"patterns":[176],"from":[177],"users'":[178],"historical":[179],"actions.":[180],"Finally,":[181],"leveraging":[183,239],"CAM,":[184],"design":[186],"module":[188],"sequence":[191],"generation:":[192],"Action-seq":[194],"Autoregressive":[195],"Generator":[196],"(AAG).":[197],"Extensive":[198],"offline":[199],"experiments":[200],"Kuaishou's":[203,225],"dataset":[204,209],"Tmall":[207],"public":[208],"demonstrate":[210],"superiority":[212],"our":[214,227],"proposed":[215],"model.":[216],"Furthermore,":[217],"large-scale":[219],"A/B":[221],"testing":[222],"deployed":[223],"platform,":[226],"achieves":[229],"significant":[230],"improvements":[231],"over":[232,271],"baseline":[233],"methods":[234],"multi-task":[236],"prediction":[237],"by":[238],"sequential":[240],"information.":[241],"Specifically,":[242],"it":[243],"yields":[244],"increases":[245],"0.34%":[247],"watch":[250],"time,":[251],"8.1%":[252],"interaction":[254],"rate,":[255],"0.162%":[257],"overall":[259],"retention":[261],"(LifeTime-7),":[262],"leading":[263],"successful":[265],"deployment":[266],"across":[267],"traffic,":[269],"serving":[270],"400":[272],"million":[273],"every":[275],"day.":[276]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2026-05-01T00:00:00"}