{"id":"https://openalex.org/W7165858938","doi":"https://doi.org/10.48550/arxiv.2606.26095","title":"Learning Action Priors for Cross-embodiment Robot Manipulation","display_name":"Learning Action Priors for Cross-embodiment Robot Manipulation","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7165858938","doi":"https://doi.org/10.48550/arxiv.2606.26095"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26095","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26095","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.26095","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079531300","display_name":"Dong Jing","orcid":"https://orcid.org/0000-0001-9550-9595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139373978","display_name":"Tianqi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tianqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139326622","display_name":"Jiaqi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139308089","display_name":"Jinman Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jinman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139322321","display_name":"Zelong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zelong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139387337","display_name":"Li Erran Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Li Erran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139325106","display_name":"Zhiwu Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Zhiwu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139380433","display_name":"Mingyu Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Mingyu","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.972100019454956,"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":0.972100019454956,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.005900000222027302,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7243000268936157},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6123999953269958},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6040999889373779},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5701000094413757},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4300999939441681},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.38429999351501465},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3635999858379364},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.3273000121116638},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.32659998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473000288009644},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7243000268936157},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6123999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104000210762024},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6040999889373779},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.32249999046325684},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26095","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26095","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.26095","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26095","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.42697009444236755}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Most":[0],"Vision-Language-Action":[1],"(VLA)":[2],"models":[3],"build":[4],"on":[5,200,231],"a":[6,46,67,94,114,174,182,244],"Vision-Language":[7],"Model":[8],"(VLM)":[9],"backbone":[10],"by":[11],"attaching":[12],"an":[13,51],"action":[14,36,62,82,101,118,128,158,217,239,247],"module":[15,37,83,102,119],"and":[16,27,64,149,203,227],"optimizing":[17],"the":[18,31,35,48,81,100,157,169,207,238],"full":[19],"policy":[20,49,165],"jointly.":[21],"This":[22],"design":[23],"inherits":[24],"strong":[25],"visual":[26,132],"linguistic":[28],"priors":[29,86],"from":[30,43,126],"VLM,":[32],"but":[33],"leaves":[34],"to":[38,58,79,143],"learn":[39],"physical":[40],"motion":[41,53,85,106,123],"almost":[42],"scratch.":[44],"As":[45],"result,":[47],"lacks":[50],"explicit":[52],"prior,":[54],"forcing":[55],"early":[56],"optimization":[57],"simultaneously":[59],"discover":[60],"temporal":[61,105,122,184],"dynamics":[63],"cross-modal":[65,88],"alignment,":[66],"challenge":[68],"further":[69],"amplified":[70],"in":[71,241],"cross-embodiment":[72,104,198],"settings.":[73],"In":[74,112,136,167],"this":[75,138],"work,":[76],"we":[77,92],"propose":[78],"pretrain":[80],"with":[84,103,156,213],"before":[87,108],"VLA":[89,109,144,214,253],"alignment.":[90],"Specifically,":[91],"introduce":[93],"two-stage":[95],"training":[96,110,145,215],"framework":[97],"that":[98,249],"equips":[99],"structure":[107,124],"begins.":[111],"Stage~1,":[113],"lightweight":[115],"flow-matching-based":[116],"encoder-decoder":[117],"efficiently":[120],"learns":[121],"solely":[125],"unconditioned":[127],"trajectories,":[129],"without":[130,216],"processing":[131],"or":[133],"language":[134],"tokens.":[135],"Stage~2,":[137],"learned":[139],"prior":[140,248],"is":[141],"transferred":[142],"through":[146],"decoder":[147],"reuse":[148],"early-stage":[150],"latent":[151],"distillation,":[152],"aligning":[153],"visual-language":[154],"features":[155],"embedding":[159],"space":[160],"while":[161],"still":[162],"allowing":[163],"end-to-end":[164],"refinement.":[166],"addition,":[168],"trained":[170],"encoder":[171],"serves":[172],"as":[173],"compact":[175],"history":[176],"compressor,":[177],"summarizing":[178],"state-action":[179],"histories":[180],"into":[181],"single":[183],"context":[185],"token":[186],"for":[187],"history-aware":[188],"modeling":[189],"at":[190],"negligible":[191],"cost.":[192],"Extensive":[193],"experiments":[194],"across":[195],"13":[196],"diverse":[197],"tasks":[199],"both":[201],"simulated":[202],"real-world":[204,233],"platforms":[205],"validate":[206],"effectiveness":[208],"of":[209],"our":[210,219],"approach.":[211],"Compared":[212],"priors,":[218],"model":[220],"achieves":[221],"faster":[222],"convergence,":[223],"higher":[224],"success":[225],"rates,":[226],"substantially":[228],"stronger":[229],"performance":[230],"data-scarce":[232],"tasks.":[234],"Moreover,":[235],"scaling":[236],"up":[237],"data":[240],"Stage~1":[242],"yields":[243],"more":[245],"generalizable":[246],"directly":[250],"improves":[251],"downstream":[252],"performance.":[254]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-26T00:00:00"}