{"id":"https://openalex.org/W7162770382","doi":"https://doi.org/10.1145/3745756.3809243","title":"VLMCache: Efficient On-Device Vision-Language Model Inference","display_name":"VLMCache: Efficient On-Device Vision-Language Model Inference","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162770382","doi":"https://doi.org/10.1145/3745756.3809243"},"language":null,"primary_location":{"id":"doi:10.1145/3745756.3809243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809243","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3745756.3809243","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137392073","display_name":"Yinyuan Zhang","orcid":"https://orcid.org/0009-0008-7128-6188"},"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/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinyuan Zhang","raw_affiliation_strings":["Beijing Tongming Lake Information Technology Application Innovation Center (TLAIC), Beijing, China","Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","National Engineering Research Center of Software Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-7128-6188","affiliations":[{"raw_affiliation_string":"Beijing Tongming Lake Information Technology Application Innovation Center (TLAIC), Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Software Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034382142","display_name":"Daliang Xu","orcid":"https://orcid.org/0000-0002-6775-0688"},"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":"Daliang Xu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6775-0688","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137355003","display_name":"Zhiyang Chen","orcid":"https://orcid.org/0009-0006-8607-8539"},"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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyang Chen","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8607-8539","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137323832","display_name":"Chenghua Wang","orcid":"https://orcid.org/0009-0007-2589-6316"},"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":"Chenghua Wang","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2589-6316","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137364878","display_name":"Ying Zhang","orcid":"https://orcid.org/0009-0009-6924-2319"},"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/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Beijing Tongming Lake Information Technology Application Innovation Center (TLAIC), Beijing, China","Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","National Engineering Research Center of Software Engineering, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6924-2319","affiliations":[{"raw_affiliation_string":"Beijing Tongming Lake Information Technology Application Innovation Center (TLAIC), Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"National Engineering Research Center of Software Engineering, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089690212","display_name":"Mengwei Xu","orcid":"https://orcid.org/0000-0001-6271-6993"},"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":"Mengwei Xu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6271-6993","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology; School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137334966","display_name":"Gang Huang","orcid":"https://orcid.org/0000-0002-4686-3181"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Huang","raw_affiliation_strings":["Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4686-3181","affiliations":[{"raw_affiliation_string":"Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education; School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"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":0.87100504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"854","last_page":"867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.796500027179718,"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":0.796500027179718,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05590000003576279,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.01850000023841858,"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/exploit","display_name":"Exploit","score":0.6191999912261963},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5879999995231628},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5264000296592712},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4771000146865845},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4593000113964081},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3183000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6937000155448914},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5879999995231628},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5126000046730042},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3745756.3809243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809243","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3745756.3809243","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809243","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 24th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2889402930","https://openalex.org/W2900164285","https://openalex.org/W2903027626","https://openalex.org/W2963232127","https://openalex.org/W3147954149","https://openalex.org/W4214545909","https://openalex.org/W4284993062","https://openalex.org/W4382059335","https://openalex.org/W4387321091","https://openalex.org/W4389523832","https://openalex.org/W4390874575","https://openalex.org/W4396832403","https://openalex.org/W4399140776","https://openalex.org/W4399323584","https://openalex.org/W4401176373","https://openalex.org/W4402155831","https://openalex.org/W4402683905","https://openalex.org/W4402716114","https://openalex.org/W4402727764","https://openalex.org/W4403793633","https://openalex.org/W4406809220","https://openalex.org/W4407196790","https://openalex.org/W4408848702","https://openalex.org/W4409366450","https://openalex.org/W4411403197","https://openalex.org/W4411892026","https://openalex.org/W4412551677","https://openalex.org/W4412889917","https://openalex.org/W4413145892","https://openalex.org/W4413146008","https://openalex.org/W4413147666","https://openalex.org/W4414371540","https://openalex.org/W4414736038","https://openalex.org/W4416035984","https://openalex.org/W7160029499"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"are":[4],"foundational":[5],"for":[6],"low-latency,":[7],"privacy-preserving":[8],"on-device":[9],"AI":[10],"in":[11,76],"real-time":[12],"applications":[13],"like":[14],"UI":[15],"agents":[16],"and":[17,67],"VQA.":[18],"The":[19],"VLM":[20],"prefilling":[21],"phase,":[22],"which":[23],"processes":[24],"the":[25,30,47,62,69],"entire":[26],"visual-textual":[27],"input,":[28],"faces":[29],"critical":[31],"challenge":[32],"of":[33,65,73],"a":[34,79],"long":[35],"Time-to-First-Token":[36],"(TTFT).":[37],"One":[38],"promising":[39],"approach":[40],"to":[41,45],"reduce":[42],"TTFT":[43],"is":[44],"exploit":[46],"temporal":[48],"locality":[49],"by":[50],"reusing":[51],"block-level":[52],"computations":[53],"across":[54],"consecutive":[55],"frames.":[56],"Unfortunately,":[57],"current":[58],"Transformer-based":[59],"VLMs":[60],"break":[61],"spatial":[63],"invariance":[64],"CNNs":[66],"invalidate":[68],"strict-prefix":[70],"KV-cache":[71],"mechanism":[72],"decoder-only":[74],"LLMs;":[75],"practice,":[77],"even":[78],"single-pixel":[80],"mismatch":[81],"can":[82],"prevent":[83],"reuse.":[84]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}
