{"id":"https://openalex.org/W4417488195","doi":null,"title":"Improving Joint Embedding Predictive Architecture with Diffusion Noise","display_name":"Improving Joint Embedding Predictive Architecture with Diffusion Noise","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4417488195"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.15216","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15216","pdf_url":"https://arxiv.org/pdf/2507.15216","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.15216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qiu, Yuping","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiu, Yuping","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu, Rui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Rui","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101938761","display_name":"Ying-Cong Chen","orcid":"https://orcid.org/0000-0002-9565-8205","observed_orcids":["https://orcid.org/0000-0002-9565-8205"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Ying-cong","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.698199987411499,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.698199987411499,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.12520000338554382,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11330000311136246,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jepa","display_name":"JEPA","score":0.7900000214576721},{"id":"https://openalex.org/keywords/diffusion-noise","display_name":"diffusion noise","score":0.8050000071525574},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8730000257492065},{"id":"https://openalex.org/keywords/masked-image-modeling","display_name":"masked image modeling","score":0.9210000038146973},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7269999980926514},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.6330000162124634},{"id":"https://openalex.org/keywords/feature-augmentation","display_name":"feature augmentation","score":0.7350000143051147},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.8650000095367432},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.5339999794960022}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7799999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466999888420105},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7034000158309937},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.675599992275238},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6227999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5950000286102295},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5444999933242798},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4837999939918518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.37700000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2507.15216","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15216","pdf_url":"https://arxiv.org/pdf/2507.15216","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.15216","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.15216","pdf_url":"https://arxiv.org/pdf/2507.15216","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417488195.pdf","grobid_xml":"https://content.openalex.org/works/W4417488195.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W3092442149","https://openalex.org/W3110257065","https://openalex.org/W3170863103","https://openalex.org/W3213836217","https://openalex.org/W4221159371","https://openalex.org/W4287121759","https://openalex.org/W4292214275","https://openalex.org/W4380994510","https://openalex.org/W4386047807","https://openalex.org/W4390872010","https://openalex.org/W4391272976","https://openalex.org/W4394656839","https://openalex.org/W4403906558","https://openalex.org/W7214218271"],"related_works":["https://openalex.org/W4403928888","https://openalex.org/W4385775238","https://openalex.org/W4386804432","https://openalex.org/W4405901512","https://openalex.org/W4400065206","https://openalex.org/W4390872010","https://openalex.org/W4402716198","https://openalex.org/W4379184928","https://openalex.org/W4414383836","https://openalex.org/W4414634275"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"has":[2,18],"become":[3],"an":[4],"incredibly":[5],"successful":[6],"method":[7],"for":[8,22,45,93],"feature":[9,172],"learning,":[10],"widely":[11],"applied":[12],"to":[13,47,56,81,99,112,151,174,187],"many":[14],"downstream":[15,195],"tasks.":[16,95,196],"It":[17],"proven":[19],"especially":[20],"effective":[21],"discriminative":[23],"tasks,":[24],"surpassing":[25],"the":[26,59,73,86,101,105,158,177,192],"trending":[27],"generative":[28,31,54,65],"models.":[29,142],"However,":[30],"models":[32,55,66],"perform":[33,183],"better":[34],"in":[35,191,202],"image":[36,137],"generation":[37],"and":[38,53,140],"detail":[39],"enhancement.":[40],"Thus,":[41],"it":[42],"is":[43,91,168],"natural":[44],"us":[46,98],"find":[48],"a":[49,82,114,125,132,169,184],"connection":[50],"between":[51,135],"SSL":[52,111],"further":[57,175],"enhance":[58,176],"representation":[60],"capacity":[61],"of":[62,85,104,128,161,171,179,194],"SSL.":[63],"As":[64],"can":[67,121],"create":[68],"new":[69],"samples":[70],"by":[71,157],"approximating":[72],"data":[74],"distribution,":[75],"such":[76],"modeling":[77,138],"should":[78],"also":[79],"lead":[80],"semantic":[83],"understanding":[84],"raw":[87],"visual":[88],"data,":[89],"which":[90],"necessary":[92],"recognition":[94,116],"This":[96],"enlightens":[97],"combine":[100],"core":[102],"principle":[103],"diffusion":[106,108,119,141,153],"model:":[107],"noise,":[109],"with":[110],"learn":[113],"competitive":[115],"model.":[117,181],"Specifically,":[118],"noise":[120,154,166],"be":[122,199],"viewed":[123],"as":[124],"particular":[126],"state":[127],"mask":[129],"that":[130],"reveals":[131],"close":[133],"relationship":[134],"masked":[136,162],"(MIM)":[139],"In":[143],"this":[144],"paper,":[145],"we":[146],"propose":[147],"N-JEPA":[148],"(Noise-based":[149],"JEPA)":[150],"incorporate":[152],"into":[155],"MIM":[156],"position":[159],"embedding":[160],"tokens.":[163],"The":[164],"multi-level":[165],"schedule":[167],"series":[170],"augmentations":[173],"robustness":[178],"our":[180],"We":[182],"comprehensive":[185],"study":[186],"confirm":[188],"its":[189],"effectiveness":[190],"classification":[193],"Codes":[197],"will":[198],"released":[200],"soon":[201],"public.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2025-10-10T00:00:00"}