{"id":"https://openalex.org/W7204094902","doi":"https://doi.org/10.48550/arxiv.2608.20958","title":"TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming","display_name":"TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204094902","doi":"https://doi.org/10.48550/arxiv.2608.20958"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20958","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20958","pdf_url":"https://arxiv.org/pdf/2608.20958","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/2608.20958","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143836858","display_name":"Yibo Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147942146","display_name":"Yu Qian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045029972","display_name":"Mao Gu","orcid":"https://orcid.org/0000-0002-3996-8399","observed_orcids":["https://orcid.org/0000-0002-3996-8399"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Mao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052649471","display_name":"Yingfan Tao","orcid":"https://orcid.org/0000-0001-5460-6110","observed_orcids":["https://orcid.org/0000-0001-5460-6110"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Yingfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148037547","display_name":"Yuhao Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112987153","display_name":"Yongdong Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yongdong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102856119","display_name":"Zhuoqun Liu","orcid":"https://orcid.org/0000-0001-7576-3537","observed_orcids":["https://orcid.org/0000-0001-7576-3537"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhuoqun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046381970","display_name":"Meiguang Jin","orcid":"https://orcid.org/0000-0003-3796-2310","observed_orcids":["https://orcid.org/0000-0003-3796-2310"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Meiguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5147380945","display_name":"Junfeng Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Junfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":1.0,"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":1.0,"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/T12032","display_name":"Multisensory perception and integration","score":0.0,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/live-streaming-e-commerce","display_name":"live streaming e-commerce","score":0.9800000190734863},{"id":"https://openalex.org/keywords/temporal-alignment","display_name":"temporal alignment","score":0.6930000185966492},{"id":"https://openalex.org/keywords/reinforcement-fine-tuning","display_name":"reinforcement fine-tuning","score":0.7260000109672546},{"id":"https://openalex.org/keywords/answer-faithfulness","display_name":"answer faithfulness","score":0.9539999961853027},{"id":"https://openalex.org/keywords/temporal-grounding","display_name":"temporal grounding","score":0.7770000100135803},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.5960000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220000267028809},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6164000034332275},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5357000231742859},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3684999942779541},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20958","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20958","pdf_url":"https://arxiv.org/pdf/2608.20958","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.2608.20958","doi":"https://doi.org/10.48550/arxiv.2608.20958","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20958","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:2608.20958","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20958","pdf_url":"https://arxiv.org/pdf/2608.20958","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/W7204094902.pdf","grobid_xml":"https://content.openalex.org/works/W7204094902.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7162397893","https://openalex.org/W7213356450","https://openalex.org/W7104693225","https://openalex.org/W7124452862","https://openalex.org/W7166811638","https://openalex.org/W7139991753","https://openalex.org/W7165644115","https://openalex.org/W7170095331","https://openalex.org/W7164990029","https://openalex.org/W7161676630"],"abstract_inverted_index":{"E-commerce":[0],"live":[1,53,218],"streaming":[2,54,219],"requires":[3],"omni-modal":[4,31,94,177],"understanding":[5,32],"of":[6],"noisy,":[7],"temporally":[8,70],"extended":[9],"streams,":[10],"where":[11],"product":[12,20,166],"facts":[13],"are":[14],"distributed":[15],"across":[16,193,224],"speech,":[17],"video":[18,66,156,173],"frames,":[19],"images,":[21],"overlaid":[22],"text,":[23],"and":[24,43,112,144,155,176],"user":[25],"queries.":[26],"We":[27,81,99],"present":[28],"TLive-Omni,":[29],"an":[30],"model":[33],"tailored":[34],"to":[35,77,96,208],"live-commerce":[36,91,152,225],"scenarios.":[37],"It":[38],"maps":[39],"image,":[40,154],"video,":[41],"audio,":[42,153],"text":[44,169],"inputs":[45],"into":[46,158],"a":[47,59,83,103,139,145,183,196],"unified":[48],"representation":[49],"space.":[50],"For":[51,180],"long-form":[52],"analysis,":[55,165],"we":[56],"introduce":[57],"Per-vGrid,":[58],"timestamped":[60],"token":[61],"organization":[62],"that":[63,88,107,150],"groups":[64,203],"each":[65],"grid":[67],"with":[68,123,204,229],"its":[69],"corresponding":[71],"audio":[72],"within":[73],"explicit":[74],"boundary":[75],"tokens":[76],"facilitate":[78],"temporal":[79,171],"alignment.":[80],"design":[82],"three-stage":[84],"supervised":[85],"training":[86,159],"recipe":[87],"progressively":[89],"develops":[90],"understanding,":[92],"from":[93],"perception":[95],"instruction-following":[97],"responses.":[98],"then":[100],"propose":[101],"Faithful-RFT,":[102],"reinforcement":[104],"fine-tuning":[105],"stage":[106],"further":[108],"improves":[109],"answer":[110],"faithfulness":[111],"expression":[113],"quality":[114],"while":[115,189,195],"meeting":[116],"real-time":[117],"demands,":[118],"scoring":[119],"final":[120],"responses":[121],"directly":[122],"task-verifiable":[124],"feedback":[125],"rather":[126],"than":[127],"optimizing":[128],"for":[129,161,213],"reasoning-style":[130],"exploration":[131],"during":[132],"rollout.":[133],"Moreover,":[134],"TLive-Omni":[135],"is":[136],"supported":[137],"by":[138],"scenario-oriented":[140],"atomic":[141],"capability":[142],"taxonomy":[143],"compact":[146],"data":[147],"production":[148],"engine":[149],"converts":[151],"streams":[157],"signals":[160],"speech":[162],"recognition,":[163,170],"speaker":[164],"visual":[167],"grounding,":[168,172],"dense":[174],"caption,":[175],"QA,":[178],"etc.":[179],"scalable":[181],"training,":[182],"synchronized":[184],"length-grouped":[185],"sampler":[186],"reduces":[187],"padding":[188],"preserving":[190],"comparable":[191],"workloads":[192],"workers,":[194],"lightweight":[197],"dynamic":[198],"sampling":[199],"strategy":[200],"regenerates":[201],"rollout":[202],"near-zero":[205],"reward":[206],"variance":[207],"maintain":[209],"meaningful":[210],"relative":[211],"advantages":[212],"GRPO.":[214],"Experiments":[215],"on":[216,232],"e-commerce":[217],"benchmarks":[220],"demonstrate":[221],"strong":[222],"performance":[223],"domain":[226],"tasks,":[227],"together":[228],"excellent":[230],"generalization":[231],"general":[233],"benchmarks.":[234]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-25T00:00:00"}