{"id":"https://openalex.org/W7133316736","doi":"https://doi.org/10.48550/arxiv.2603.00182","title":"Embedding Morphology into Transformers for Cross-Robot Policy Learning","display_name":"Embedding Morphology into Transformers for Cross-Robot Policy Learning","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7133316736","doi":"https://doi.org/10.48550/arxiv.2603.00182"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00182","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127995784","display_name":"Kei Suzuki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzuki, Kei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127957461","display_name":"Jing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127938454","display_name":"Ye Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hori, Chiori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013617347","display_name":"Matthew Brand","orcid":"https://orcid.org/0000-0001-7698-4884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brand, Matthew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062272788","display_name":"Diego Romeres","orcid":"https://orcid.org/0000-0002-8603-2438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romeres, Diego","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023338067","display_name":"Toshiaki Koike\u2013Akino","orcid":"https://orcid.org/0000-0002-2578-5372"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koike-Akino, Toshiaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3441999852657318,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3441999852657318,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.21549999713897705,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.07490000128746033,"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/kinematics","display_name":"Kinematics","score":0.7404999732971191},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6873999834060669},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.675599992275238},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5001000165939331},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4867999851703644},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42410001158714294}],"concepts":[{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.7404999732971191},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6873999834060669},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.675599992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6069999933242798},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4867999851703644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453000009059906},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.34880000352859497},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00182","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00182","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.4084957540035248,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-robot":[0],"policy":[1,7,59],"learning":[2],"--":[3,14],"training":[4],"a":[5,16,51,82,118,129],"single":[6,52],"to":[8,112],"perform":[9],"well":[10],"across":[11,44,72,142],"multiple":[12],"embodiments":[13,45],"remains":[15],"central":[17],"challenge":[18],"in":[19,94],"robot":[20],"learning.":[21],"Transformer-based":[22],"policies,":[23],"such":[24],"as":[25,90],"vision-language-action":[26],"(VLA)":[27],"models,":[28],"are":[29],"typically":[30],"embodiment-agnostic":[31],"and":[32,46,74,102,141],"must":[33],"infer":[34],"kinematic":[35,67,88,100],"structure":[36],"purely":[37],"from":[38],"observations,":[39],"which":[40],"can":[41],"reduce":[42],"robustness":[43,136],"even":[47],"limit":[48],"performance":[49,127],"within":[50,138],"embodiment.":[53],"We":[54],"propose":[55],"an":[56,91,139],"embodiment-aware":[57],"transformer":[58],"that":[60,69,86,106],"injects":[61],"morphology":[62],"via":[63],"three":[64],"mechanisms:":[65],"(1)":[66],"tokens":[68],"factorize":[70],"actions":[71],"joints":[73],"compress":[75],"time":[76],"through":[77],"per-joint":[78,110],"temporal":[79],"chunking;":[80],"(2)":[81],"topology-aware":[83],"attention":[84],"bias":[85,93],"encodes":[87],"topology":[89,108],"inductive":[92],"self-attention,":[95],"encouraging":[96],"message":[97],"passing":[98],"along":[99],"edges;":[101],"(3)":[103],"joint-attribute":[104],"conditioning":[105],"augments":[107],"with":[109],"descriptors":[111],"capture":[113],"semantics":[114],"beyond":[115],"connectivity.":[116],"Across":[117],"range":[119],"of":[120],"embodiments,":[121],"this":[122],"structured":[123],"integration":[124],"consistently":[125],"improves":[126],"over":[128],"vanilla":[130],"pi0.5":[131],"VLA":[132],"baseline,":[133],"indicating":[134],"improved":[135],"both":[137],"embodiment":[140],"embodiments.":[143]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}