{"id":"https://openalex.org/W7171939208","doi":"https://doi.org/10.1145/3770854.3780230","title":"PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers","display_name":"PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7171939208","doi":"https://doi.org/10.1145/3770854.3780230"},"language":null,"primary_location":{"id":"doi:10.1145/3770854.3780230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780230","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770854.3780230","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144128789","display_name":"Yibo Zhong","orcid":"https://orcid.org/0009-0006-3697-2698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibo Zhong","raw_affiliation_strings":["Independent Researcher, Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0006-3697-2698","affiliations":[{"raw_affiliation_string":"Independent Researcher, Chengdu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144120529","display_name":"Haoxiang Jiang","orcid":"https://orcid.org/0009-0002-5631-2559"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoxiang Jiang","raw_affiliation_strings":["University at Albany, Albany, USA"],"raw_orcid":"https://orcid.org/0009-0002-5631-2559","affiliations":[{"raw_affiliation_string":"University at Albany, Albany, USA","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005362290","display_name":"Lincan Li","orcid":"https://orcid.org/0000-0003-3797-4055"},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lincan Li","raw_affiliation_strings":["Florida State University, Tallahassee, USA"],"raw_orcid":"https://orcid.org/0000-0003-3797-4055","affiliations":[{"raw_affiliation_string":"Florida State University, Tallahassee, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088508553","display_name":"Ryumei Nakada","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryumei Nakada","raw_affiliation_strings":["Rutgers University, New Brunswick, USA"],"raw_orcid":"https://orcid.org/0009-0006-9888-7472","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035373409","display_name":"T. Liu","orcid":"https://orcid.org/0000-0002-8396-8564"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianci Liu","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-8396-8564","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925773","display_name":"Linjun Zhang","orcid":"https://orcid.org/0000-0002-8309-7164"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linjun Zhang","raw_affiliation_strings":["Rutgers University, New Brunswick, USA"],"raw_orcid":"https://orcid.org/0000-0002-8309-7164","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051534896","display_name":"Huaxiu Yao","orcid":"https://orcid.org/0000-0002-8691-9629"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaxiu Yao","raw_affiliation_strings":["University of North Carolina at Chapel Hill, Chapel Hill, USA"],"raw_orcid":"https://orcid.org/0000-0002-8691-9629","affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018990800","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0001-7485-6213"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["University at Albany, Albany, USA"],"raw_orcid":"https://orcid.org/0000-0001-7485-6213","affiliations":[{"raw_affiliation_string":"University at Albany, Albany, USA","institution_ids":["https://openalex.org/I392282"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":"2054","last_page":"2065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5748000144958496},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4690000116825104},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43070000410079956},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3901999890804291},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.3314000070095062},{"id":"https://openalex.org/keywords/linear-model","display_name":"Linear model","score":0.289900004863739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730400025844574},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5627999901771545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4830000102519989},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770854.3780230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780230","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3770854.3780230","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770854.3780230","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1575834508","https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2138011018","https://openalex.org/W2592962403","https://openalex.org/W2964194231","https://openalex.org/W2984452801","https://openalex.org/W3145185940","https://openalex.org/W4206727248","https://openalex.org/W4224310605","https://openalex.org/W4312868944","https://openalex.org/W4322766882","https://openalex.org/W4396680888","https://openalex.org/W4402716038","https://openalex.org/W4402716409","https://openalex.org/W4404783091","https://openalex.org/W4413145530"],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"pre-trained":[2,68],"foundation":[3],"models":[4],"often":[5],"yields":[6],"excellent":[7],"downstream":[8],"performance":[9],"but":[10],"is":[11],"prohibitively":[12],"expensive":[13],"when":[14],"updating":[15],"all":[16],"parameters.":[17,105],"Parameter-efficient":[18],"fine-tuning":[19],"(PEFT)":[20],"methods":[21,100],"such":[22],"as":[23],"LoRA":[24],"alleviate":[25],"this":[26,44],"by":[27],"introducing":[28],"lightweight":[29],"update":[30,80],"modules,":[31],"yet":[32,74],"they":[33],"commonly":[34],"rely":[35],"on":[36,66],"weight-agnostic":[37],"linear":[38,98],"approximations,":[39],"limiting":[40],"their":[41],"expressiveness.":[42],"In":[43],"work,":[45],"we":[46],"propose":[47],"PEANuT,":[48],"a":[49,72],"novel":[50],"PEFT":[51,99],"framework":[52],"that":[53,61,89,116],"introduces":[54],"weight-aware":[55],"neural":[56,59],"tweakers,":[57],"compact":[58],"modules":[60],"generate":[62],"task-adaptive":[63],"updates":[64],"conditioned":[65],"frozen":[67],"weights.":[69],"PEANuT":[70,90,117],"provides":[71],"flexible":[73],"efficient":[75],"way":[76],"to":[77],"capture":[78],"complex":[79],"patterns":[81],"without":[82],"full":[83],"model":[84],"tuning.":[85],"We":[86],"theoretically":[87],"show":[88],"achieves":[91],"equivalent":[92],"or":[93,103],"greater":[94],"expressivity":[95],"than":[96],"existing":[97],"with":[101,111],"comparable":[102],"fewer":[104],"Extensive":[106],"experiments":[107],"across":[108],"four":[109],"benchmarks":[110],"over":[112],"twenty":[113],"datasets":[114],"demonstrate":[115],"consistently":[118],"outperforms":[119],"strong":[120],"baselines":[121],"in":[122],"both":[123],"NLP":[124],"and":[125],"vision":[126],"tasks,":[127],"while":[128],"maintaining":[129],"low":[130],"computational":[131],"overhead.":[132]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}