{"id":"https://openalex.org/W7163510034","doi":"https://doi.org/10.48550/arxiv.2606.04448","title":"Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation Learning","display_name":"Bridging Short Videos and Live Streams: Reasoning-Guided Multimodal LLMs for Cross-Domain Representation Learning","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163510034","doi":"https://doi.org/10.48550/arxiv.2606.04448"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04448","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.04448","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137894794","display_name":"Le Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137844711","display_name":"Xiaolan Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xiaolan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137859487","display_name":"Yuchen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137871192","display_name":"Shilong Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Shilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025589970","display_name":"Jiaqi Xue","orcid":"https://orcid.org/0000-0002-7893-6656"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137823721","display_name":"Xiaoyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137899645","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0003-4977-2717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120318217","display_name":"Yalong Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Yalong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137903858","display_name":"Xiangyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137866496","display_name":"Shijun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137810532","display_name":"Lantao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Lantao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137842240","display_name":"Kun Gai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gai, Kun","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":false,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.44519999623298645,"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":0.44519999623298645,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1428000032901764,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.1185000017285347,"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/bridging","display_name":"Bridging (networking)","score":0.6812999844551086},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5471000075340271},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49000000953674316},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4009999930858612},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.37229999899864197},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.37130001187324524},{"id":"https://openalex.org/keywords/live-streaming","display_name":"Live streaming","score":0.30090001225471497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950000166893005},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6812999844551086},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4587000012397766},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4287000000476837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205000102519989},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3560999929904938},{"id":"https://openalex.org/C2776741261","wikidata":"https://www.wikidata.org/wiki/Q3027665","display_name":"Live streaming","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2778956030","wikidata":"https://www.wikidata.org/wiki/Q5142477","display_name":"Cold start (automotive)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2540999948978424},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04448","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.04448","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4136334955692291,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"live":[1,11,27,49,60,112,192],"streaming":[2,28,50,193],"services":[3],"grow,":[4],"many":[5],"platforms":[6],"offer":[7],"short":[8,46,57,109],"videos":[9,18,47,58,110],"and":[10,22,59,66,83,119,144,162,172,209,219],"streams":[12,61],"to":[13,48,87,111],"meet":[14],"diverse":[15],"needs.":[16],"Short":[17],"carry":[19],"substantial":[20],"traffic":[21],"rich":[23],"behavior":[24,36],"signals,":[25],"whereas":[26],"is":[29,216],"a":[30,102,135,148],"core":[31,203],"conversion":[32],"scenario":[33],"with":[34],"sparse":[35],"data,":[37],"making":[38],"cold":[39],"start":[40],"severe.":[41],"Transferring":[42],"user":[43],"interests":[44],"from":[45,108],"recommendation":[51,71,89,107,194],"can":[52],"alleviate":[53],"these":[54],"issues.":[55],"Meanwhile,":[56],"are":[62,169],"complex":[63],"multimodal":[64,68,81],"items,":[65],"integrating":[67],"signals":[69],"improves":[70],"performance.":[72],"Although":[73],"Multimodal":[74],"Large":[75],"Language":[76],"Models":[77],"(MLLMs)":[78],"show":[79,198],"strong":[80],"understanding":[82],"reasoning,":[84],"their":[85],"application":[86],"cross-domain":[88,106,141,154],"remains":[90],"underexplored.":[91],"To":[92],"this":[93],"end,":[94],"we":[95],"propose":[96],"Reasoning-Guided":[97],"Cross-Domain":[98],"Representation":[99],"Learning":[100],"(RGCD-Rep),":[101],"reasoning-guided":[103],"framework":[104],"for":[105],"streams.":[113],"RGCD-Rep":[114,215],"introduces":[115],"MLLM":[116,138],"reasoning":[117,142],"resource-efficiently":[118],"learns":[120],"transferable":[121,161],"item":[122,158],"representations":[123,159,168],"guided":[124],"by":[125],"behavioral":[126],"collaboration":[127],"via":[128],"two-stage":[129],"training.":[130],"First,":[131],"reasoning-aware":[132],"distillation":[133],"lets":[134],"frozen":[136],"teacher":[137],"generate":[139],"structured":[140],"knowledge":[143],"distills":[145],"it":[146],"into":[147,160,174],"lightweight":[149],"student":[150],"MLLM.":[151],"Second,":[152],"transferability-guided":[153],"representation":[155],"learning":[156],"decomposes":[157],"domain":[163],"residual":[164],"representations.":[165],"The":[166],"resulting":[167],"computed":[170],"offline":[171,183],"integrated":[173],"downstream":[175],"retrieval":[176],"tasks,":[177],"enabling":[178],"low-cost":[179],"industrial":[180,213],"deployment.":[181],"Extensive":[182],"experiments":[184],"demonstrate":[185],"RGCD-Rep's":[186],"superiority.":[187],"After":[188],"deployment":[189],"in":[190,211],"Kuaishou's":[191],"system,":[195],"A/B":[196],"tests":[197],"significant":[199],"gains":[200],"across":[201],"multiple":[202],"business":[204],"metrics,":[205],"confirming":[206],"its":[207],"effectiveness":[208],"practicality":[210],"real":[212],"scenarios.":[214],"fully":[217],"deployed":[218],"serves":[220],"over":[221],"400":[222],"million":[223],"users":[224],"daily.":[225]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}