{"id":"https://openalex.org/W7135059222","doi":"https://doi.org/10.48550/arxiv.2603.10090","title":"A Survey of Weight Space Learning: Understanding, Representation, and Generation","display_name":"A Survey of Weight Space Learning: Understanding, Representation, and Generation","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7135059222","doi":"https://doi.org/10.48550/arxiv.2603.10090"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10090","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.2603.10090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128855389","display_name":"Xiaolong Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Xiaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128829970","display_name":"Zehong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zehong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128833120","display_name":"Bo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128877548","display_name":"Binchi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Binchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128827937","display_name":"Jundong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jundong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065722787","display_name":"Damian Borth","orcid":"https://orcid.org/0000-0002-4660-2627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Borth, Damian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057778679","display_name":"Rose Yu","orcid":"https://orcid.org/0000-0002-8491-7937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Rose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050312737","display_name":"Haggai Maron","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maron, Haggai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128884965","display_name":"Yanfang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yanfang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128896119","display_name":"Lu Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063214931","display_name":"Ferrante Neri","orcid":"https://orcid.org/0000-0002-6100-6532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neri, Ferrante","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/T10569","display_name":"Bariatric Surgery and Outcomes","score":0.04430000111460686,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10569","display_name":"Bariatric Surgery and Outcomes","score":0.04430000111460686,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.03449999913573265,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.03240000084042549,"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/categorization","display_name":"Categorization","score":0.6908000111579895},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5910999774932861},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5297999978065491},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5289000272750854},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.34599998593330383},{"id":"https://openalex.org/keywords/homogeneous-space","display_name":"Homogeneous space","score":0.33730000257492065}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6908000111579895},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644999742507935},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5289000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5170000195503235},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38339999318122864},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33000001311302185},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10090","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.2603.10090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10090","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"network":[1],"weights":[2,97,153],"are":[3,66],"typically":[4],"viewed":[5],"as":[6,90,98,194],"the":[7,28,109,129],"end":[8],"product":[9],"of":[10,30,113,133],"training,":[11],"while":[12],"most":[13],"deep":[14],"learning":[15],"research":[16,84],"focuses":[17],"on":[18,62,71],"data,":[19],"features,":[20],"and":[21,48,68,70,104,131,145,172,178,206],"architectures.":[22],"However,":[23],"recent":[24],"advances":[25],"show":[26,161],"that":[27],"set":[29],"all":[31],"possible":[32],"weight":[33,192,207],"values":[34],"(weight":[35],"space)":[36],"itself":[37],"contains":[38],"rich":[39],"structure:":[40],"pretrained":[41],"models":[42],"form":[43],"organized":[44],"distributions,":[45],"exhibit":[46],"symmetries,":[47],"can":[49],"be":[50],"embedded,":[51],"compared,":[52,69],"or":[53,156],"even":[54],"generated.":[55],"Understanding":[56,125],"such":[57],"structures":[58],"has":[59],"tremendous":[60],"impact":[61,201],"how":[63,72,162],"neural":[64,96,175],"networks":[65],"analyzed":[67],"knowledge":[73],"is":[74],"transferred":[75],"across":[76,202],"models,":[77],"beyond":[78],"individual":[79],"training":[80],"instances.":[81],"This":[82,106],"emerging":[83],"direction,":[85],"which":[86,127,139,150],"we":[87],"refer":[88],"to":[89],"Weight":[91,123,135,146],"Space":[92,124,136,147],"Learning":[93],"(WSL),":[94],"treats":[95],"a":[99,186,195],"meaningful":[100],"domain":[101,198],"for":[102],"analysis":[103],"modeling.":[105],"survey":[107,190],"provides":[108],"first":[110],"unified":[111],"taxonomy":[112],"WSL.":[114],"We":[115,159,209],"categorize":[116],"existing":[117],"methods":[118],"into":[119],"three":[120],"core":[121],"dimensions:":[122],"(WSU),":[126],"studies":[128],"geometry":[130],"symmetries":[132],"weights;":[134,144],"Representation":[137],"(WSR),":[138],"learns":[140],"embeddings":[141],"over":[142],"model":[143,169,203],"Generation":[148],"(WSG),":[149],"synthesizes":[151],"new":[152],"through":[154],"hypernetworks":[155],"generative":[157],"models.":[158],"further":[160],"these":[163],"developments":[164],"enable":[165],"practical":[166],"applications,":[167],"including":[168],"retrieval,":[170],"continual":[171],"federated":[173],"learning,":[174],"architecture":[176],"search,":[177],"data-free":[179],"reconstruction.":[180],"By":[181],"consolidating":[182],"fragmented":[183],"progress":[184],"under":[185],"coherent":[187],"framework,":[188],"this":[189],"highlights":[191],"space":[193],"learnable,":[196],"structured":[197],"with":[199],"growing":[200],"analysis,":[204],"transferring,":[205],"generation.":[208],"release":[210],"an":[211],"accompanying":[212],"resource":[213],"at":[214],"https://github.com/Zehong-Wang/Awesome-Weight-Space-Learning.":[215]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-13T00:00:00"}