{"id":"https://openalex.org/W7214799362","doi":"https://doi.org/10.48550/arxiv.2609.32250","title":"RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots","display_name":"RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214799362","doi":"https://doi.org/10.48550/arxiv.2609.32250"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32250","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32250","pdf_url":"https://arxiv.org/pdf/2609.32250","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.32250","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056230833","display_name":"Yu Zeng","orcid":"https://orcid.org/0000-0002-2604-9502","observed_orcids":["https://orcid.org/0000-0002-2604-9502","https://orcid.org/0009-0008-0508-2988"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeng, Yujia","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049686906","display_name":"Chensheng Peng","orcid":"https://orcid.org/0000-0001-9213-5970","observed_orcids":["https://orcid.org/0000-0001-9213-5970"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng, Chensheng","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153413166","display_name":"Yuxin Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Yuxin","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139321647","display_name":"Alex Shao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shao, Alex","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096277376","display_name":"Nathan Jew","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jew, Nathan","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125041902","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639","observed_orcids":["https://orcid.org/0000-0003-0206-6639"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomizuka, Masayoshi","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"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/T12290","display_name":"Human Motion and Animation","score":0.8823000192642212,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T12290","display_name":"Human Motion and Animation","score":0.8823000192642212,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.10440000146627426,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.0013000000035390258,"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/sign-language-translation","display_name":"sign language translation","score":0.9229999780654907},{"id":"https://openalex.org/keywords/humanoid-robots","display_name":"humanoid robots","score":0.796999990940094},{"id":"https://openalex.org/keywords/speech-to-sign-translation","display_name":"speech-to-sign translation","score":0.6430000066757202},{"id":"https://openalex.org/keywords/self-conditioning","display_name":"self-conditioning","score":0.628000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052000164985657},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.694599986076355},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5378999710083008},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5108000040054321},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4431999921798706},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C181605269","wikidata":"https://www.wikidata.org/wiki/Q497332","display_name":"Jerk","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32250","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32250","pdf_url":"https://arxiv.org/pdf/2609.32250","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"},{"id":"doi:10.48550/arxiv.2609.32250","doi":"https://doi.org/10.48550/arxiv.2609.32250","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32250","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.32250","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32250","pdf_url":"https://arxiv.org/pdf/2609.32250","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214799362.pdf","grobid_xml":"https://content.openalex.org/works/W7214799362.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402570923","https://openalex.org/W7168007726","https://openalex.org/W7165545866","https://openalex.org/W7106267102","https://openalex.org/W7169840418","https://openalex.org/W4311856230","https://openalex.org/W7203887896","https://openalex.org/W7164324034","https://openalex.org/W7135119671","https://openalex.org/W7117564461"],"abstract_inverted_index":{"Sign-language":[0],"interpretation":[1],"in":[2,104],"public":[3],"communication":[4],"relies":[5],"on":[6],"qualified":[7],"professional":[8],"interpreters":[9],"and":[10,69,101,123,144],"can":[11,40],"be":[12,41,73],"difficult":[13],"to":[14,72,128,149],"scale,":[15],"motivating":[16],"robotic":[17,44],"signing":[18],"as":[19],"a":[20,27,62,76],"complementary":[21],"accessibility":[22],"interface.":[23],"We":[24],"present":[25],"RoBoSTAR,":[26],"text-conditioned":[28],"sign":[29,37],"language":[30],"production":[31],"(SLP)":[32],"framework":[33],"for":[34,43,138],"generating":[35,90],"human-centric":[36],"motion":[38,60,91,119,134],"that":[39],"retargeted":[42,137],"execution,":[45],"with":[46,87],"speech":[47],"supported":[48],"optionally":[49],"through":[50],"an":[51],"external":[52],"ASR":[53],"front":[54],"end.":[55],"Conventional":[56],"autoregressive":[57],"approaches":[58],"flatten":[59],"into":[61],"single":[63],"full-resolution":[64],"token":[65],"sequence,":[66],"forcing":[67],"long-range":[68,114],"local":[70],"dependencies":[71],"modeled":[74],"at":[75],"uniform":[77],"temporal":[78,95],"granularity.":[79],"RoBoSTAR":[80],"instead":[81],"combines":[82],"part-wise":[83],"Finite":[84],"Scalar":[85],"Quantization":[86],"next-scale":[88],"autoregression,":[89],"over":[92],"progressively":[93,117],"finer":[94],"resolutions":[96],"while":[97,121],"predicting":[98],"synchronized":[99],"body":[100],"hand":[102],"tokens":[103],"parallel":[105],"within":[106],"each":[107],"step.":[108],"This":[109],"coarse-to-fine":[110],"formulation":[111],"provides":[112],"compact":[113],"context":[115,124],"before":[116],"refining":[118],"details,":[120],"self-conditioning":[122],"corruption":[125],"improve":[126],"robustness":[127],"cross-scale":[129],"prediction":[130],"errors.":[131],"The":[132],"generated":[133],"is":[135],"subsequently":[136],"physical":[139],"humanoid":[140],"execution.":[141],"Extensive":[142],"qualitative":[143],"quantitative":[145],"evaluations":[146],"are":[147],"conducted":[148],"demonstrate":[150],"the":[151],"effectiveness":[152],"of":[153],"RoBoSTAR.":[154]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-30T00:00:00"}