{"id":"https://openalex.org/W7133199121","doi":"https://doi.org/10.52202/075280-2577","title":"Towards Optimal Caching and Model Selection for Large Model Inference","display_name":"Towards Optimal Caching and Model Selection for Large Model Inference","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W7133199121","doi":"https://doi.org/10.52202/075280-2577"},"language":"en","primary_location":{"id":"doi:10.52202/075280-2577","doi":"https://doi.org/10.52202/075280-2577","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-2577","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127837283","display_name":"Banghua Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Banghua Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083402013","display_name":"Ying Sheng","orcid":"https://orcid.org/0000-0002-1883-2126","observed_orcids":["https://orcid.org/0000-0002-1883-2126"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Sheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061339425","display_name":"Lianmin Zheng","orcid":"https://orcid.org/0000-0001-5812-731X","observed_orcids":["https://orcid.org/0000-0001-5812-731X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianmin Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026961968","display_name":"Clark Barrett","orcid":"https://orcid.org/0000-0002-9522-3084","observed_orcids":["https://orcid.org/0000-0002-9522-3084"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clark Barrett","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049812527","display_name":"Michael I. Jordan","orcid":"https://orcid.org/0000-0001-8935-817X","observed_orcids":["https://orcid.org/0000-0001-8935-817X","https://orcid.org/0000-0002-2177-0405","https://orcid.org/0000-0002-5776-2626"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Jordan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034192173","display_name":"Jiantao Jiao","orcid":"https://orcid.org/0000-0003-3766-8031","observed_orcids":["https://orcid.org/0000-0003-3766-8031"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiantao Jiao","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":0.7846,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73525037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"59062","last_page":"59094"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.21410000324249268,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.21410000324249268,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.20669999718666077,"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/T11478","display_name":"Caching and Content Delivery","score":0.07900000363588333,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/large-language-model-inference","display_name":"large language model inference","score":0.6380000114440918},{"id":"https://openalex.org/keywords/caching","display_name":"caching","score":0.6740000247955322},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.9869999885559082},{"id":"https://openalex.org/keywords/inference-optimization","display_name":"inference optimization","score":0.49399998784065247},{"id":"https://openalex.org/keywords/prompt-caching","display_name":"prompt caching","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6486999988555908},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5077000260353088},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.52202/075280-2577","doi":"https://doi.org/10.52202/075280-2577","is_oa":false,"landing_page_url":"https://doi.org/10.52202/075280-2577","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 36","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133239641","https://openalex.org/W7169571641","https://openalex.org/W4416035908","https://openalex.org/W7196953932","https://openalex.org/W7133204253","https://openalex.org/W4415798907","https://openalex.org/W7106288924","https://openalex.org/W7221513536","https://openalex.org/W7197051966","https://openalex.org/W2403140033"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-03T00:00:00"}
