{"id":"https://openalex.org/W7164987922","doi":"https://doi.org/10.48550/arxiv.2606.17408","title":"Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies","display_name":"Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policies","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7164987922","doi":"https://doi.org/10.48550/arxiv.2606.17408"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17408","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17408","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.2606.17408","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101297291","display_name":"Meipo Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Meipo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071276694","display_name":"Qiyuan Zhuang","orcid":"https://orcid.org/0000-0001-5937-5024"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Qiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409301","display_name":"Heyang Xu","orcid":"https://orcid.org/0009-0007-3924-2639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, He-Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138825003","display_name":"Ying-Jie Shuai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai, Ying-Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138797703","display_name":"Yijun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138780140","display_name":"Qi Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138814840","display_name":"Xiu-Shen Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xiu-Shen","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6690999865531921,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6690999865531921,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07150000333786011,"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":0.07000000029802322,"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/generator","display_name":"Generator (circuit theory)","score":0.6148999929428101},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5170999765396118},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5041000247001648},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4893999993801117},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48069998621940613},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.46950000524520874},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.42250001430511475},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41600000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6531000137329102},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6148999929428101},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48069998621940613},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3937000036239624},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3151000142097473},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28040000796318054},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17408","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17408","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.2606.17408","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17408","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"robot":[1,185],"policies":[2],"typically":[3],"begin":[4],"action":[5,28,49,93],"generation":[6,29],"from":[7,99],"an":[8,81,100,111,177],"observation-independent":[9],"standard":[10,41],"Gaussian":[11,42,47],"distribution,":[12,67],"leaving":[13],"the":[14,40,59,65,70,87,166,173,189],"choice":[15,190],"of":[16,64,115,191],"source":[17,36,66,174],"distribution":[18,175],"underexplored.":[19],"This":[20,78],"work":[21],"asks":[22],"a":[23,34,44,53,125,129],"simple":[24],"question:":[25],"where":[26,163],"should":[27],"begin?":[30],"We":[31],"propose":[32],"LeaP,":[33],"Learnable":[35],"Prior":[37],"that":[38,172],"replaces":[39],"with":[43],"proprioception-conditioned":[45],"diagonal":[46],"over":[48,159],"chunks.":[50],"Parameterized":[51],"by":[52,133],"lightweight":[54],"MLP,":[55],"LeaP":[56,109,164],"jointly":[57],"predicts":[58],"mean":[60],"and":[61,74,128,146,153,179],"state-adaptive":[62],"variance":[63],"while":[68,149],"keeping":[69],"downstream":[71],"generator":[72,88],"architecture":[73],"inference":[75],"solver":[76],"unchanged.":[77],"design":[79,181],"provides":[80],"observation-informed":[82],"yet":[83],"stochastic":[84],"initialization,":[85],"allowing":[86],"to":[89,135,160,188],"focus":[90],"on":[91],"precise":[92],"refinement":[94],"rather":[95],"than":[96],"transporting":[97],"samples":[98],"uninformed":[101],"noise":[102],"source.":[103],"On":[104],"15":[105],"RoboTwin":[106],"manipulation":[107],"tasks,":[108],"achieves":[110],"average":[112],"success":[113],"rate":[114],"81.6%,":[116],"outperforming":[117],"four":[118],"representative":[119],"baselines":[120],"--":[121,132],"including":[122],"deterministic-source":[123],"methods,":[124],"no-prior":[126],"counterpart,":[127],"diffusion-bridge":[130,147],"policy":[131],"6.5":[134],"25.5":[136],"percentage":[137],"points.":[138],"The":[139,156],"same":[140],"prior":[141],"consistently":[142],"improves":[143],"both":[144],"flow-matching":[145],"generators,":[148],"using":[150],"fewer":[151],"parameters":[152],"converging":[154],"faster.":[155],"advantage":[157],"carries":[158],"real-world":[161],"deployment,":[162],"attains":[165],"best":[167],"performance.":[168],"These":[169],"results":[170],"suggest":[171],"is":[176],"independent":[178],"reusable":[180],"axis":[182],"for":[183],"generative":[184,192],"policies,":[186],"complementary":[187],"dynamics.":[193]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-18T00:00:00"}