{"id":"https://openalex.org/W7163233026","doi":"https://doi.org/10.48550/arxiv.2606.00514","title":"Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation","display_name":"Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation","publication_year":2026,"publication_date":"2026-05-30","ids":{"openalex":"https://openalex.org/W7163233026","doi":"https://doi.org/10.48550/arxiv.2606.00514"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00514","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.2606.00514","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031116795","display_name":"Hugues Van Assel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Assel, Hugues","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013970475","display_name":"Edward De Brouwer","orcid":"https://orcid.org/0000-0003-0608-0155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Brouwer, Edward","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005413766","display_name":"Saeed Saremi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saremi, Saeed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020099374","display_name":"Gabriele Scalia","orcid":"https://orcid.org/0000-0003-3305-9220"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scalia, Gabriele","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137655314","display_name":"Aviv Regev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Regev, Aviv","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9627000093460083,"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":0.9627000093460083,"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":0.009700000286102295,"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/T11448","display_name":"Face recognition and analysis","score":0.009200000204145908,"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/feature","display_name":"Feature (linguistics)","score":0.6873999834060669},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6715999841690063},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6126000285148621},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5965999960899353},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.589900016784668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4966000020503998},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263000011444092},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6873999834060669},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6715999841690063},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6126000285148621},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5965999960899353},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.525600016117096},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4966000020503998},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4375},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3799000084400177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00514","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.2606.00514","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00514","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":{"Generative":[0],"modeling":[1,49],"and":[2,188,213],"self-supervised":[3],"representation":[4,60],"learning":[5],"(SSL)":[6],"optimize":[7],"structurally":[8],"different":[9],"objectives:":[10],"generative":[11,30,48],"training":[12,157],"rewards":[13,18],"distributional":[14],"fidelity,":[15],"while":[16,184],"SSL":[17,27,46,64,117,135,158,205],"semantic":[19,134],"coherence.":[20],"Yet":[21],"recent":[22],"work":[23],"repeatedly":[24],"finds":[25],"that":[26,81,105,137,174,215],"features":[28,65,136,159,164],"improve":[29,182],"training,":[31],"though":[32],"the":[33,43,51,57,77,89,92,155,163,167,178],"mechanism":[34],"of":[35,45,53,59,194],"this":[36,106,128],"synergy":[37],"remains":[38],"unclear.":[39],"Here,":[40],"we":[41,172,202],"study":[42],"benefits":[44],"in":[47,50,80,113,123],"framework":[52],"one-step":[54],"generation":[55,211],"where":[56],"role":[58],"is":[61,218,226],"explicit:":[62],"frozen":[63],"are":[66],"used":[67,165],"to":[68,72,131,209],"match":[69,162],"generated":[70],"samples":[71],"real":[73],"data.":[74],"We":[75,103,126],"use":[76],"Sinkhorn":[78],"divergence":[79],"feature":[82,118,179,206],"space,":[83],"providing":[84],"a":[85,114,143,153,192,219],"tractable":[86],"surrogate":[87],"for":[88,222],"Wasserstein":[90],"distance,":[91],"population-level":[93],"discrepancy":[94],"approximated":[95],"by":[96,166],"Fr\u00e9chet-style":[97],"evaluation":[98,168],"metrics":[99],"(such":[100],"as":[101,177],"FID).":[102,125],"find":[104],"objective":[107],"becomes":[108],"highly":[109],"effective":[110],"when":[111],"computed":[112],"semantically":[115],"structured":[116],"space":[119],"(a":[120],"39$\\times$":[121],"reduction":[122],"ImageNet":[124],"trace":[127],"behavior":[129],"primarily":[130],"matching":[132,149,186,216],"estimation:":[133],"suppress":[138],"nuisance":[139],"reconstruction":[140],"details":[141],"induce":[142],"more":[144,150],"compact":[145],"geometry,":[146],"making":[147],"distribution":[148],"tractable.":[151],"As":[152],"consequence,":[154],"best":[156,210],"need":[160],"not":[161],"metric.":[169],"In":[170],"particular,":[171],"show":[173,214],"using":[175],"Inception":[176],"extractor":[180],"can":[181],"FID":[183],"degrading":[185],"stability":[187,217],"sample":[189],"quality,":[190],"revealing":[191],"form":[193],"metric":[195],"hacking.":[196],"Using":[197],"extensive":[198],"experiments":[199],"on":[200],"ImageNet,":[201],"identify":[203],"which":[204],"families":[207],"lead":[208],"performance":[212],"quantitative":[220],"criterion":[221],"selecting":[223],"them.":[224],"Code":[225],"available":[227],"at":[228],"https://github.com/Genentech/semantic-transport-generation.":[229]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}