{"id":"https://openalex.org/W7152479166","doi":"https://doi.org/10.1145/3774904.3792127","title":"Task-Aware Cloud-End Offloading for Vision-Language Model Serving via Dynamic Modality-Specific Adapter Scheduling","display_name":"Task-Aware Cloud-End Offloading for Vision-Language Model Serving via Dynamic Modality-Specific Adapter Scheduling","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152479166","doi":"https://doi.org/10.1145/3774904.3792127"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792127","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792127","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133279481","display_name":"Zian Wang","orcid":"https://orcid.org/0009-0008-6605-0920"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zian Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6605-0920","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441364","display_name":"Ziyi Wang","orcid":"https://orcid.org/0000-0001-8174-0593"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8174-0593","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Xing","orcid":"https://orcid.org/0009-0002-9747-8539"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Xing","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9747-8539","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057137480","display_name":"Yaya Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaya Wei","raw_affiliation_strings":["Omni-Channel Operation Center, China Telecommunications Corporation, 0009-0002-9747-8539, China"],"raw_orcid":"https://orcid.org/0009-0004-7117-4662","affiliations":[{"raw_affiliation_string":"Omni-Channel Operation Center, China Telecommunications Corporation, 0009-0002-9747-8539, China","institution_ids":["https://openalex.org/I4210136246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034902161","display_name":"Ziyan Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Zhong","raw_affiliation_strings":["Omni-Channel Operation Center, China Telecommunications Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-7362-8999","affiliations":[{"raw_affiliation_string":"Omni-Channel Operation Center, China Telecommunications Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210136246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049198139","display_name":"Lanshan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanshan Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0674-7864","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50615069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5021","last_page":"5030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2928999960422516,"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":0.2928999960422516,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08860000222921371,"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/T14347","display_name":"Big Data and Digital Economy","score":0.07919999957084656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5462999939918518},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.3019999861717224},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.2856999933719635},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.26339998841285706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367999911308289},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.22660000622272491}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792127","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792127","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792127","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2896180420","https://openalex.org/W4367047170","https://openalex.org/W4402713111","https://openalex.org/W4410357217","https://openalex.org/W4411447392","https://openalex.org/W4414648140"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"vision-language":[1,156],"models":[2,129],"enable":[3],"powerful":[4],"cross-modal":[5,89],"understanding":[6],"and":[7,27,39,140],"generation,":[8],"driving":[9],"rapidly":[10],"growing":[11],"demand":[12],"for":[13,102,154],"online":[14],"inference":[15],"services.":[16],"However,":[17],"cloud-centric":[18],"serving":[19,56],"often":[20],"suffers":[21],"from":[22],"high":[23,148],"latency,":[24],"rising":[25],"costs,":[26],"network":[28],"dependency,":[29],"while":[30,91,146],"purely":[31],"on-device":[32],"deployment":[33],"is":[34],"constrained":[35],"by":[36,136,142],"limited":[37],"memory":[38],"reduced":[40],"accuracy":[41],"on":[42,74],"complex":[43,95],"tasks.":[44],"To":[45],"address":[46],"this":[47],"accuracy\u2013latency\u2013cost":[48],"trilemma,":[49],"we":[50],"propose":[51],"ShiftVL,":[52],"a":[53,67,82,98,111],"task-aware":[54],"end\u2013cloud":[55],"framework":[57],"that":[58,87,115,131],"shifts":[59],"suitable":[60],"execution":[61],"to":[62,97,122,138,144],"the":[63],"end":[64],"device":[65,107],"with":[66,80,119,127],"cloud":[68,134],"fallback.":[69],"ShiftVL":[70,109,132],"serves":[71],"high-frequency":[72],"requests":[73,96],"an":[75],"end-side":[76],"small":[77],"VLM":[78,101],"enhanced":[79],"ViTexLoRA,":[81],"modality-disentangled":[83],"parameter-efficient":[84],"tuning":[85],"method":[86],"preserves":[88],"alignment,":[90],"routing":[92],"low-frequency":[93],"or":[94],"cloud-hosted":[99],"large":[100],"higher":[103],"accuracy.":[104],"Under":[105],"tight":[106],"budgets,":[108],"employs":[110],"predictive":[112],"adapter":[113],"scheduler":[114],"combines":[116],"LRU-style":[117],"caching":[118],"imitation":[120],"learning":[121],"pre-load":[123],"task-specific":[124],"adapters.":[125],"Experiments":[126],"InternVL":[128],"show":[130],"reduces":[133],"cost":[135],"up":[137,143],"76.3%":[139],"latency":[141],"42.9%":[145],"maintaining":[147],"multi-task":[149],"accuracy,":[150],"demonstrating":[151],"its":[152],"practicality":[153],"real-world":[155],"model":[157],"serving.":[158]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}
