{"id":"https://openalex.org/W7225320182","doi":"https://doi.org/10.48550/arxiv.2611.06728","title":"Turns Matter: Advancing Streaming Video RL via Turn-Level Credit","display_name":"Turns Matter: Advancing Streaming Video RL via Turn-Level Credit","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225320182","doi":"https://doi.org/10.48550/arxiv.2611.06728"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.06728","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.06728","pdf_url":"https://arxiv.org/pdf/2611.06728","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.06728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160839792","display_name":"Shuai Dong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153530503","display_name":"Kanghui Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Kanghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160867409","display_name":"Linghan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Linghan","raw_affiliation_strings":["Fudan University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University ,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827257","display_name":"Wenqi Shao","orcid":"https://orcid.org/0000-0003-3781-4086","observed_orcids":["https://orcid.org/0000-0003-3781-4086"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao, Wenqi","raw_affiliation_strings":["JD.com ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159147215","display_name":"Hongrui Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wu, Hongrui","raw_affiliation_strings":["JD.com ,","Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068420027","display_name":"Haowen Hou","orcid":"https://orcid.org/0000-0003-3850-3722","observed_orcids":["https://orcid.org/0000-0003-3850-3722"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hou, Haowen","raw_affiliation_strings":["JD.com ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136482371","display_name":"Yongfu Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Yongfu","raw_affiliation_strings":["JD.com ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038141768","display_name":"Xuehui Wang","orcid":"https://orcid.org/0000-0002-6333-7773","observed_orcids":["https://orcid.org/0000-0002-6333-7773"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xuehui","raw_affiliation_strings":["JD.com ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160818613","display_name":"Ziyue Wang","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Ziyue","raw_affiliation_strings":["JD.com ,","Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136479148","display_name":"Wenpu Liu","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Wenpu","raw_affiliation_strings":["JD.com ,","Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160930163","display_name":"Weichu Xie","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Weichu","raw_affiliation_strings":["JD.com ,","Peking University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160868953","display_name":"Yuqi Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yuqi","raw_affiliation_strings":["JD.com ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160866794","display_name":"Congcong Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Congcong","raw_affiliation_strings":["JD.com ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119890623","display_name":"Kaiwen Tuo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Tuo, Kaiwen","raw_affiliation_strings":["JD.com ,","The Hong Kong University of Science and Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology ,","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160896583","display_name":"Caoyuan Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Ma, Caoyuan","raw_affiliation_strings":["JD.com ,","The University of Tokyo ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"The University of Tokyo ,","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074532565","display_name":"Taiqiang Wu","orcid":"https://orcid.org/0000-0002-3664-3513","observed_orcids":["https://orcid.org/0000-0002-3664-3513"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"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":["CN","HK"],"is_corresponding":false,"raw_author_name":"Wu, Taiqiang","raw_affiliation_strings":["JD.com ,","The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160841815","display_name":"Ji Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Ji","raw_affiliation_strings":["JD.com ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147103983","display_name":"Wenzheng Chang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang, Wenzheng","raw_affiliation_strings":["JD.com ,","Shanghai Artificial Intelligence Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory ,","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124944862","display_name":"Dianyi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Dianyi","raw_affiliation_strings":["Fudan University ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160839510","display_name":"Siyuan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wang, Siyuan","raw_affiliation_strings":["The Chinese University of Hong Kong ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong ,","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160952215","display_name":"Zhongyu Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Zhongyu","raw_affiliation_strings":["Fudan University ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University ,","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160895842","display_name":"Yu Qiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory ,","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160766061","display_name":"Jiaqi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jiaqi","raw_affiliation_strings":["JD.com ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com ,","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.8208000063896179,"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":0.8208000063896179,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09640000015497208,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.006599999964237213,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.5180000066757202},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.8820000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7671999931335449},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5120999813079834},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3050999939441681},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2993078247","wikidata":"https://www.wikidata.org/wiki/Q182076","display_name":"Bank credit","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.06728","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.06728","pdf_url":"https://arxiv.org/pdf/2611.06728","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.2611.06728","doi":"https://doi.org/10.48550/arxiv.2611.06728","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.06728","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.06728","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.06728","pdf_url":"https://arxiv.org/pdf/2611.06728","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225320182.pdf","grobid_xml":"https://content.openalex.org/works/W7225320182.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4391631327","https://openalex.org/W4406449463","https://openalex.org/W4407794264","https://openalex.org/W4414942698","https://openalex.org/W4416184586","https://openalex.org/W4416780398","https://openalex.org/W7075994024","https://openalex.org/W7136697772","https://openalex.org/W7161704811","https://openalex.org/W7163208102","https://openalex.org/W7166696640","https://openalex.org/W7214181560","https://openalex.org/W7216450763"],"related_works":["https://openalex.org/W7214923470","https://openalex.org/W7161708506","https://openalex.org/W4406786134","https://openalex.org/W7203712272","https://openalex.org/W7136697772","https://openalex.org/W7160909810","https://openalex.org/W7166313708","https://openalex.org/W7206214774","https://openalex.org/W7147613864","https://openalex.org/W7164827814"],"abstract_inverted_index":{"Streaming":[0],"video":[1,160],"understanding":[2],"requires":[3],"models":[4],"to":[5,9,23,95],"repeatedly":[6],"decide":[7],"whether":[8],"respond":[10],"or":[11,146],"continue":[12],"observing.":[13],"Recently,":[14],"Group":[15],"Relative":[16],"Policy":[17],"Optimization":[18],"(GRPO)":[19],"has":[20],"been":[21],"applied":[22],"this":[24],"setting,":[25],"with":[26,67],"existing":[27],"approaches":[28,157],"emphasizing":[29],"reward":[30],"design":[31],"while":[32],"retaining":[33],"a":[34,60,143],"single":[35],"trajectory-level":[36,76],"advantage":[37],"across":[38,122],"turns.":[39],"Such":[40],"shared":[41],"credit":[42,89],"can":[43],"reinforce":[44],"redundant":[45],"replies":[46],"after":[47,54],"earlier":[48,55,109],"successes":[49],"and":[50,78,84,120,126],"discourage":[51],"useful":[52],"follow-ups":[53],"failures.":[56],"We":[57],"propose":[58],"TurnWise,":[59],"turn-level":[61,79,88],"GRPO":[62],"framework":[63],"that":[64],"aligns":[65],"learning":[66,106,141],"individual":[68],"streaming":[69,139,159],"decisions.":[70],"TurnWise":[71],"addresses":[72],"the":[73],"mismatch":[74],"between":[75],"feedback":[77],"interaction,":[80],"promoting":[81],"informative":[82],"responses":[83],"reducing":[85],"redundancy.":[86],"Specifically,":[87],"assignment":[90],"uses":[91],"silence-completed":[92],"prefix":[93],"scoring":[94],"construct":[96],"group-relative":[97],"advantages":[98],"from":[99,108],"each":[100,118],"decision's":[101],"remaining":[102],"return,":[103],"separating":[104],"its":[105],"signal":[107],"rewards.":[110],"Turn-mean":[111],"policy":[112,140],"optimization":[113],"averages":[114],"token":[115],"losses":[116],"within":[117],"turn":[119],"then":[121],"turns,":[123],"giving":[124],"response":[125],"waiting":[127],"decisions":[128],"equal":[129],"weight":[130],"regardless":[131],"of":[132],"output":[133],"length.":[134],"These":[135],"complementary":[136],"designs":[137],"improve":[138],"without":[142],"learned":[144],"critic":[145],"additional":[147],"rollouts.":[148],"Extensive":[149],"experiments":[150],"show":[151],"our":[152],"method":[153],"outperforms":[154],"prior":[155],"RL":[156],"for":[158],"understanding.":[161]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-06T00:00:00"}
