{"id":"https://openalex.org/W7161688487","doi":"https://doi.org/10.48550/arxiv.2605.16743","title":"LACE: Latent Visual Representation for Cross-Embodiment Learning","display_name":"LACE: Latent Visual Representation for Cross-Embodiment Learning","publication_year":2026,"publication_date":"2026-05-16","ids":{"openalex":"https://openalex.org/W7161688487","doi":"https://doi.org/10.48550/arxiv.2605.16743"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16743","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.16743","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012348513","display_name":"Yoo Sung Jang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jang, Yoo Sung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022250650","display_name":"Kanchana Ranasinghe","orcid":"https://orcid.org/0000-0003-2374-7804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranasinghe, Kanchana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136457560","display_name":"Cristina Mata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mata, Cristina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136483361","display_name":"Yichi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yichi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136457810","display_name":"Jorge Mendez-Mendez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mendez-Mendez, Jorge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084829008","display_name":"Michael S. Ryoo","orcid":"https://orcid.org/0000-0002-5452-8332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryoo, Michael S.","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":0.3337000012397766,"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":0.3337000012397766,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.25209999084472656,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08860000222921371,"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/leverage","display_name":"Leverage (statistics)","score":0.7792999744415283},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.675000011920929},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6301000118255615},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6100999712944031},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5982000231742859},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.43050000071525574}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7792999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7282000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143999934196472},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.675000011920929},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6301000118255615},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5982000231742859},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5364000201225281},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.43050000071525574},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4050999879837036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2619999945163727},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16743","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.16743","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16743","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,"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"},"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":{"Cross-embodiment":[0],"learning":[1,18],"from":[2],"human":[3,12,36,47,122],"demonstrations":[4,126],"is":[5,84],"hindered":[6],"by":[7,59,97,139],"the":[8,53,88],"visual":[9,50],"gap":[10],"between":[11,35,62],"and":[13,37,48,80,150],"robot":[14,38,49,82,117,125],"embodiments.":[15],"While":[16],"self-supervised":[17],"(SSL)":[19],"backbones":[20,58],"encode":[21],"rich":[22],"inter-class":[23],"semantics":[24],"of":[25,56],"general":[26],"objects,":[27],"we":[28],"show":[29],"they":[30],"fail":[31],"to":[32,86,103,119],"establish":[33],"correspondence":[34],"hands.":[39],"We":[40],"propose":[41],"LACE,":[42],"a":[43,107,140],"framework":[44],"that":[45],"aligns":[46],"representations":[51],"in":[52,129,147],"latent":[54],"space":[55],"these":[57],"leveraging":[60],"correspondences":[61],"shared":[63],"body":[64],"parts":[65],"across":[66],"embodiments":[67],"as":[68],"sparse":[69],"supervision.":[70],"These":[71],"annotations":[72],"can":[73],"be":[74],"automatically":[75],"obtained":[76],"via":[77],"forward":[78],"kinematics,":[79],"single":[81],"demonstration":[83],"sufficient":[85],"train":[87],"model.":[89],"Our":[90],"semantic":[91],"alignment":[92,115],"loss":[93,109],"matches":[94],"distributions":[95],"incurred":[96],"corresponding":[98],"features,":[99],"lifting":[100],"patch-level":[101],"supervision":[102],"semantic-level":[104],"alignment,":[105],"while":[106],"Gram":[108],"preserves":[110],"pretrained":[111],"feature":[112],"quality.":[113],"This":[114],"enables":[116],"policies":[118,132],"leverage":[120],"abundant":[121],"data":[123],"when":[124],"are":[127],"scarce:":[128],"zero-shot":[130],"transfer,":[131],"using":[133,137],"LACE-DINO":[134],"outperform":[135],"those":[136],"DINO":[138],"large":[141],"margin":[142],"(65\\%),":[143],"with":[144],"consistent":[145],"gains":[146],"low-data":[148],"regimes":[149],"out-of-distribution":[151],"environments.":[152]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-20T00:00:00"}