{"id":"https://openalex.org/W7161691484","doi":"https://doi.org/10.48550/arxiv.2605.16412","title":"SCAR: Self-Supervised Continuous Action Representation Learning","display_name":"SCAR: Self-Supervised Continuous Action Representation Learning","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161691484","doi":"https://doi.org/10.48550/arxiv.2605.16412"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16412","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16412","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.2605.16412","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121811272","display_name":"Hongjia Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hongjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136458907","display_name":"Fan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136501457","display_name":"Minghao Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136499006","display_name":"Xinyue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005721418","display_name":"Haofei Lu","orcid":"https://orcid.org/0009-0001-6333-9533"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Haofei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071784683","display_name":"Biwei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Biwei","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":0.27230000495910645,"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":0.27230000495910645,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.2615000009536743,"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":0.0763000026345253,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6431999802589417},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6262999773025513},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43959999084472656},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4300000071525574},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4023999869823456},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.35760000348091125},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560999751091003},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6431999802589417},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6262999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834000110626221},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4300000071525574},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2939000129699707},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16412","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16412","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.2605.16412","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16412","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":{"Despite":[0],"the":[1,49,112,124,151,158],"central":[2],"role":[3],"of":[4,199],"action":[5,11,34,69,126,162,191],"in":[6],"embodied":[7],"intelligence,":[8],"learning":[9,67],"transferable":[10,115,209],"representations":[12,70],"from":[13,52,73,93],"visual":[14,74,120,136],"transitions":[15],"remains":[16],"a":[17,43,61,78,98,118,129,166,196],"fundamental":[18],"challenge,":[19],"particularly":[20],"when":[21],"world":[22,171,212],"models":[23],"must":[24],"generalize":[25],"across":[26,71,202],"embodiments":[27,72],"under":[28],"limited":[29],"data.":[30],"We":[31],"argue":[32],"that":[33,47,157,190],"is":[35],"not":[36],"merely":[37],"an":[38,84,205],"auxiliary":[39],"conditioning":[40,168],"signal,":[41],"but":[42],"distinct":[44],"representational":[45],"factor":[46],"decouples":[48],"controllable":[50,200],"change":[51,201],"embodiment-specific":[53,174],"actuation.":[54],"In":[55],"this":[56],"work,":[57],"we":[58,122],"propose":[59],"SCAR,":[60],"joint":[62],"inverse-forward":[63],"dynamics":[64,86,100,106],"framework":[65],"for":[66,170,207],"unified":[68,160],"transitions.":[75],"Built":[76],"on":[77,108,150],"pretrained":[79],"generative":[80],"backbone,":[81],"SCAR":[82],"uses":[83],"inverse":[85],"model":[87,101],"(IDM)":[88],"to":[89,103,133,142],"infer":[90],"latent":[91,94,113,125,161],"actions":[92],"observation":[95],"pairs":[96],"and":[97,138,145,153,182,210],"forward":[99],"(FDM)":[102],"predict":[104],"future":[105],"conditioned":[107],"them.":[109],"To":[110],"make":[111],"space":[114],"rather":[116],"than":[117,173],"generic":[119],"bottleneck,":[121],"regularize":[123],"posterior":[127],"toward":[128],"standard":[130],"Gaussian":[131],"prior":[132],"limit":[134],"arbitrary":[135],"encoding,":[137],"introduce":[139],"adversarial":[140],"invariance":[141],"suppress":[143],"embodiment-":[144],"environment-specific":[146],"nuisance":[147],"factors.":[148],"Experiments":[149],"Procgen":[152],"Robotwin":[154],"dataset":[155],"show":[156],"learned":[159,194],"representation":[163,198],"serves":[164],"as":[165,195],"stronger":[167],"interface":[169,206],"modeling":[172],"raw":[175],"actions,":[176],"yielding":[177],"improved":[178],"cross-embodiment":[179],"low-data":[180],"adaptation":[181],"cross-task":[183],"transfer.":[184],"Taken":[185],"together,":[186],"these":[187],"results":[188],"suggest":[189],"can":[192],"be":[193],"shared":[197],"embodiments,":[203],"providing":[204],"more":[208],"generalizable":[211],"models.":[213]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}