{"id":"https://openalex.org/W7224110337","doi":"https://doi.org/10.48550/arxiv.2610.36959","title":"Live-OPSD: On-Policy Self-Distillation for Proactive Streaming Large Video Models","display_name":"Live-OPSD: On-Policy Self-Distillation for Proactive Streaming Large Video Models","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224110337","doi":"https://doi.org/10.48550/arxiv.2610.36959"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36959","pdf_url":"https://arxiv.org/pdf/2610.36959","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,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018335911","display_name":"Kaixuan Du","orcid":"https://orcid.org/0000-0001-9117-9250","observed_orcids":["https://orcid.org/0000-0001-9117-9250"]},"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":"Du, Kaixuan","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160036110","display_name":"Xin Wan","orcid":null,"observed_orcids":[]},"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":"Wan, Xin","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130183062","display_name":"Dai Guan","orcid":null,"observed_orcids":[]},"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":"Guan, Dai","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160007486","display_name":"Ming Chen","orcid":null,"observed_orcids":[]},"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":"Chen, Ming","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160000555","display_name":"Xiaoxi Jiang","orcid":null,"observed_orcids":[]},"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":"Jiang, Xiaoxi","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136972120","display_name":"Guanjun Jiang","orcid":null,"observed_orcids":[]},"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":"Jiang, Guanjun","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5932999849319458,"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":0.5932999849319458,"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/T12031","display_name":"Speech and dialogue systems","score":0.27320000529289246,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.031199999153614044,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/on-policy-self-distillation","display_name":"on-policy self-distillation","score":0.9330000281333923},{"id":"https://openalex.org/keywords/response-timing","display_name":"response timing","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.78329998254776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6585000157356262},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36959","pdf_url":"https://arxiv.org/pdf/2610.36959","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,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.36959","doi":"https://doi.org/10.48550/arxiv.2610.36959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36959","pdf_url":null,"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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.36959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36959","pdf_url":"https://arxiv.org/pdf/2610.36959","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,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224110337.pdf","grobid_xml":"https://content.openalex.org/works/W7224110337.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160909810","https://openalex.org/W7203712272","https://openalex.org/W7164990029","https://openalex.org/W7162322277","https://openalex.org/W7214807600","https://openalex.org/W7117324130","https://openalex.org/W7223005890","https://openalex.org/W7214923470","https://openalex.org/W7216450763","https://openalex.org/W7214887446"],"abstract_inverted_index":{"Streaming":[0],"multimodal":[1],"assistants":[2],"must":[3],"make":[4],"response":[5,45],"decisions":[6],"while":[7],"events":[8],"are":[9],"still":[10],"unfolding.":[11],"They":[12],"need":[13],"to":[14,68],"recognize":[15],"when":[16,149],"the":[17,44,49,70,83,98,102,106,123,138],"available":[18,64],"evidence":[19],"warrants":[20],"a":[21,80,95,152],"response,":[22],"produce":[23],"an":[24,56,113],"appropriate":[25],"continuation,":[26],"and":[27,101,127,150],"remain":[28],"silent":[29],"otherwise.":[30],"Supervised":[31],"fine-tuning":[32],"learns":[33],"from":[34,82],"recorded":[35],"assistant":[36,154],"turns,":[37],"but":[38],"does":[39],"not":[40],"directly":[41],"train":[42],"on":[43,72,118,130,140],"prefixes":[46],"produced":[47],"by":[48],"evolving":[50],"policy":[51,71,77,139],"itself.":[52],"We":[53],"introduce":[54],"Live-OPSD,":[55],"on-policy":[57],"self-distillation":[58],"method":[59],"that":[60,92,136],"uses":[61],"privileged":[62,145],"hints":[63,146],"only":[65],"during":[66],"training":[67],"supervise":[69],"its":[73,141],"own":[74,142],"outputs.":[75],"The":[76,87],"first":[78],"generates":[79],"continuation":[81,93],"streaming":[84,153],"context":[85],"alone.":[86],"same":[88],"model":[89],"then":[90],"re-evaluates":[91],"with":[94,144],"hint":[96],"describing":[97],"relevant":[99],"evidence,":[100],"resulting":[103],"distributions":[104],"guide":[105],"unhinted":[107],"policy.":[108],"On":[109],"Qwen3-Omni-30B-A3B,":[110],"Live-OPSD":[111],"attains":[112],"average":[114],"score":[115],"of":[116],"59.64":[117],"LiveProBench,":[119],"5.26":[120],"points":[121],"above":[122],"strongest":[124],"continued-SFT":[125],"baseline,":[126],"stays":[128],"competitive":[129],"OVO-Bench":[131],"(65.84).":[132],"These":[133],"results":[134],"indicate":[135],"guiding":[137],"outputs":[143],"improves":[147],"both":[148],"how":[151],"responds.":[155]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-29T00:00:00"}