{"id":"https://openalex.org/W7220697288","doi":"https://doi.org/10.48550/arxiv.2610.04400","title":"XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions","display_name":"XTurnix: Large-Scale Self-Supervised Turn Control through Two-State Binary Decisions","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7220697288","doi":"https://doi.org/10.48550/arxiv.2610.04400"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04400","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04400","pdf_url":"https://arxiv.org/pdf/2610.04400","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/2610.04400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157736277","display_name":"Zhanxun Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhanxun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157777412","display_name":"Yifan Duan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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":"Duan, Yifan","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, X-LANCE Lab , Shanghai Jiao Tong University ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, X-LANCE Lab , Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019065742","display_name":"Hengtao Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Hengtao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, X-LANCE Lab , Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, X-LANCE Lab , Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157693914","display_name":"Chen Yang","orcid":null,"observed_orcids":[]},"institutions":[{"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":"Yang, Chen","raw_affiliation_strings":["MOSI Intelligence ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOSI Intelligence ,","institution_ids":[]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004651932","display_name":"Qinyuan Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"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":"Cheng, Qinyuan","raw_affiliation_strings":["MOSI Intelligence ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOSI Intelligence ,","institution_ids":[]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157713973","display_name":"Kun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Kun","raw_affiliation_strings":["SenseTime Group Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Group Inc. ,","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157708073","display_name":"Xingyu Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405255904","display_name":"Shenzhen University of Advanced Technology","ror":"https://ror.org/03hz5th67","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405255904"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Xingyu","raw_affiliation_strings":["Shenzhen University of Advanced Technology Code Demo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University of Advanced Technology Code Demo","institution_ids":["https://openalex.org/I4405255904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157729417","display_name":"Xipeng Qiu","orcid":null,"observed_orcids":[]},"institutions":[{"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":"Qiu, Xipeng","raw_affiliation_strings":["MOSI Intelligence ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOSI Intelligence ,","institution_ids":[]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050188515","display_name":"Chaochao Lu","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Chaochao","raw_affiliation_strings":["Shanghai AI Laboratory ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory ,","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157675314","display_name":"Xie Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"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":"Chen, Xie","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, X-LANCE Lab , Shanghai Jiao Tong University ,","Shanghai Innovation Institute ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, X-LANCE Lab , Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Innovation Institute ,","institution_ids":["https://openalex.org/I4405279436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0010000000474974513,"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/T10383","display_name":"Language, Discourse, Communication Strategies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.7419999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417999863624573},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04400","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04400","pdf_url":"https://arxiv.org/pdf/2610.04400","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.2610.04400","doi":"https://doi.org/10.48550/arxiv.2610.04400","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04400","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:2610.04400","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04400","pdf_url":"https://arxiv.org/pdf/2610.04400","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/W7220697288.pdf","grobid_xml":"https://content.openalex.org/works/W7220697288.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7202274428","https://openalex.org/W3094393093","https://openalex.org/W7134816979","https://openalex.org/W7140972194","https://openalex.org/W2067097374","https://openalex.org/W7215000145","https://openalex.org/W7143447782","https://openalex.org/W7222667870","https://openalex.org/W4372260277","https://openalex.org/W7101032468"],"abstract_inverted_index":{"General":[0],"turn-taking":[1],"behavior":[2],"in":[3,208],"real-time":[4],"dialogue":[5,92],"systems":[6],"requires":[7],"deciding":[8],"whether":[9,19],"to":[10,20,49],"keep":[11],"listening":[12,79],"or":[13,22,41,80],"start":[14],"responding":[15],"while":[16,24,187],"listening,":[17],"and":[18,34,83,131,148,159,193,204],"continue":[21],"stop":[23],"speaking.":[25],"Existing":[26],"turn":[27,68,206],"detectors":[28],"use":[29,50],"heterogeneous,":[30],"task-specific":[31],"label":[32],"spaces":[33],"are":[35],"often":[36],"trained":[37],"on":[38,43,75,97,111,127,145,156,165],"limited":[39],"annotations":[40],"evaluated":[42],"isolated":[44],"utterances,":[45],"making":[46],"them":[47],"difficult":[48],"as":[51,70],"a":[52,62,85,116,132,209],"unified":[53,202],"causal":[54,100],"controller":[55],"with":[56,115,218],"comprehensive":[57],"context.":[58],"We":[59,124],"propose":[60],"XTurnix,":[61],"compact":[63,211],"text-based":[64],"model":[65,155],"that":[66],"formulates":[67],"control":[69,87,207],"two":[71],"binary":[72],"decisions":[73],"conditioned":[74],"the":[76,90,120,137,142,152,161,168,181],"AI's":[77],"current":[78],"speaking":[81],"state":[82],"predicts":[84],"single":[86,210],"token":[88],"from":[89,105],"complete":[91],"history.":[93],"XTurnix":[94,126,140],"is":[95,214],"pretrained":[96],"5.5":[98],"million":[99],"action":[101],"examples":[102,114],"automatically":[103],"derived":[104],"timestamped":[106],"two-speaker":[107],"transcripts,":[108],"then":[109],"fine-tuned":[110],"synthetic":[112],"multi-turn":[113],"flatter":[117],"distribution":[118],"across":[119,195],"four":[121,128,197],"state-action":[122],"labels.":[123],"evaluate":[125],"public":[129,138],"benchmarks":[130],"balanced":[133],"self-curated":[134,169],"benchmark.":[135],"Across":[136],"benchmarks,":[139],"achieves":[141,160],"best":[143],"results":[144,200],"all":[146,196],"SemanticVAD":[147],"LiveKit":[149],"splits,":[150],"ties":[151],"native":[153],"Smart-Turn":[154,157],"Bench,":[158],"highest":[162],"incomplete-turn":[163],"accuracy":[164],"Easy-Turn.":[166],"On":[167],"benchmark,":[170],"it":[171],"reaches":[172],"89.06%":[173],"accuracy,":[174],"more":[175],"than":[176],"20":[177],"percentage":[178],"points":[179],"above":[180],"strongest":[182],"third-party":[183],"baseline":[184],"at":[185,216,222],"68.75%,":[186],"maintaining":[188],"F1":[189],"scores":[190],"between":[191],"84.21%":[192],"90.63%":[194],"categories.":[198],"These":[199],"demonstrate":[201],"listening-":[203],"speaking-state":[205],"model.":[212],"Code":[213],"available":[215],"https://github.com/xcc-zach/xturnix,":[217],"an":[219],"interactive":[220],"demo":[221],"https://huggingface.co/spaces/xcczach/xturnix-demo.":[223]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-07T00:00:00"}