{"id":"https://openalex.org/W7220726942","doi":"https://doi.org/10.48550/arxiv.2610.05711","title":"From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model","display_name":"From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model","publication_year":2026,"publication_date":"2026-10-05","ids":{"openalex":"https://openalex.org/W7220726942","doi":"https://doi.org/10.48550/arxiv.2610.05711"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.05711","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05711","pdf_url":"https://arxiv.org/pdf/2610.05711","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.05711","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095912605","display_name":"Vicente Balmaseda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balmaseda, Vicente","raw_affiliation_strings":["Department of Computer Science and Engineering Texas A&M University College Station , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Texas A&M University College Station , TX , USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157751555","display_name":"Ching-Long Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Ching-Long","raw_affiliation_strings":["Mechanical Engineering University of Iowa Iowa City , IA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical Engineering University of Iowa Iowa City , IA , USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157679554","display_name":"Tianbao Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Tianbao","raw_affiliation_strings":["Department of Computer Science and Engineering Texas A&M University College Station , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Texas A&M University College Station , TX , USA","institution_ids":["https://openalex.org/I91045830"]}]}],"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":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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9984999895095825,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0006000000284984708,"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":0.0003000000142492354,"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/self-supervised-representation-learning","display_name":"self-supervised representation learning","score":0.9309999942779541},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.7990000247955322},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.9559999704360962},{"id":"https://openalex.org/keywords/scion","display_name":"scion","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7095999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938999891281128},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.638700008392334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5871999859809875},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5715000033378601},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4860999882221222},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35519999265670776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2621000111103058}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.05711","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05711","pdf_url":"https://arxiv.org/pdf/2610.05711","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.05711","doi":"https://doi.org/10.48550/arxiv.2610.05711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.05711","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.05711","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.05711","pdf_url":"https://arxiv.org/pdf/2610.05711","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W7220726942.pdf","grobid_xml":"https://content.openalex.org/works/W7220726942.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2047643928","https://openalex.org/W2117539524","https://openalex.org/W2125389028","https://openalex.org/W2785325870","https://openalex.org/W3006439205","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036982689","https://openalex.org/W3135058862","https://openalex.org/W3213836217","https://openalex.org/W4297808394","https://openalex.org/W4312933868","https://openalex.org/W4384648648","https://openalex.org/W4386071584","https://openalex.org/W4390872297","https://openalex.org/W4400337819","https://openalex.org/W4414698850","https://openalex.org/W4414830503","https://openalex.org/W4415202797","https://openalex.org/W4415795348","https://openalex.org/W4415798153","https://openalex.org/W4417160760","https://openalex.org/W6891821041","https://openalex.org/W6948626004","https://openalex.org/W7090942304","https://openalex.org/W7114769804","https://openalex.org/W7138068512"],"related_works":["https://openalex.org/W4415795348","https://openalex.org/W2902683495","https://openalex.org/W7214754041","https://openalex.org/W4386071584","https://openalex.org/W7214927435","https://openalex.org/W4414634275","https://openalex.org/W7222244424","https://openalex.org/W2953469440","https://openalex.org/W2920684403","https://openalex.org/W2953327099"],"abstract_inverted_index":{"Strong":[0],"image":[1,179],"generation":[2,22,56],"models":[3],"are":[4,68],"conditioned":[5,115],"on":[6,16,25,105,116,240],"class":[7],"labels,":[8],"aligned":[9],"to":[10,170,232],"frozen":[11],"pretrained":[12,37,60,210,233],"encoders,":[13],"or":[14,27,35,59,209],"built":[15],"separately":[17],"trained":[18,146],"autoencoders.":[19],"While":[20],"effective,":[21],"then":[23],"depends":[24],"supervision":[26],"pretraining:":[28],"labels":[29,58,208],"must":[30,88],"be":[31],"annotated,":[32],"and":[33,46,76,87,93,120,192,204,219,236,251],"encoders":[34],"autoencoders":[36],"for":[38],"the":[39,66,90,117,138,143,148,154,158,172,188,216,259],"target":[40],"domain.":[41],"We":[42,100],"study":[43],"joint":[44,196],"generative":[45,152],"self-supervised":[47,203],"representation":[48,124,145,221,254],"learning":[49,71,98],"in":[50,198],"a":[51,111,130,168,177,185],"single":[52,112],"model,":[53],"enabling":[54],"self-conditioned":[55],"without":[57,176,249],"models.":[61,211],"This":[62],"is":[63,110,129,157,202],"challenging":[64],"because":[65],"objectives":[67],"mismatched:":[69],"contrastive":[70,97,149],"consumes":[72,84],"clean":[73],"augmented":[74],"views":[75],"favors":[77],"coarse,":[78],"invariant":[79],"semantics,":[80],"while":[81,163],"flow":[82,118],"matching":[83],"noisy":[85],"images":[86],"preserve":[89],"fine":[91],"detail":[92],"spatial":[94],"layout":[95],"that":[96],"discards.":[99],"propose":[101],"SCION":[102,201,223,245],"(Self-conditioned":[103],"Generation":[104],"Self-supervised":[106],"representation),":[107],"whose":[108],"core":[109],"pixel-space":[113],"encoder":[114],"timestep":[119],"an":[121],"embedding.":[122,189],"For":[123,151],"learning,":[125],"this":[126],"conditioning":[127,155],"embedding":[128,156],"learned":[131],"global":[132],"vector":[133],"shared":[134],"across":[135],"images,":[136],"with":[137,206,215,253,258],"encoder's":[139],"[CLS]":[140,161],"token":[141],"yielding":[142],"semantic":[144],"by":[147],"loss.":[150],"training,":[153],"image's":[159],"own":[160],"representation,":[162],"patch":[164],"tokens":[165],"pass":[166],"through":[167],"decoder":[169],"predict":[171],"image.":[173],"To":[174],"sample":[175],"reference":[178],"at":[180],"inference,":[181],"we":[182],"jointly":[183],"learn":[184],"prior":[186],"over":[187],"Gradient-norm":[190],"balancing":[191],"stop-gradient":[193],"mechanisms":[194],"enable":[195],"optimization":[197],"one":[199],"run.":[200],"self-contained,":[205],"no":[207,220],"On":[212],"ImageNet":[213],"256x256,":[214],"JiT-B":[217],"recipe":[218,261],"guidance,":[222,255],"reaches":[224],"8.92":[225],"FID,":[226],"surpassing":[227],"class-unconditional":[228],"iREPA,":[229],"which":[230,238],"aligns":[231],"DINOv2":[234],"(46.44),":[235],"RCG,":[237],"conditions":[239],"it":[241],"(14.27).":[242],"With":[243],"JiT-L,":[244],"achieves":[246],"5.89":[247],"FID":[248],"guidance":[250],"3.47":[252],"outperforming":[256],"RCG":[257],"ADM":[260],"(6.24).":[262]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}