{"id":"https://openalex.org/W7140999116","doi":"https://doi.org/10.48550/arxiv.2603.25399","title":"LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior","display_name":"LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7140999116","doi":"https://doi.org/10.48550/arxiv.2603.25399"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25399","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.2603.25399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101880233","display_name":"Xinkai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130808446","display_name":"Chenyi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130787349","display_name":"Yifu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yifu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075591612","display_name":"Mingzhe Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Mingzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130724430","display_name":"Fu-Cheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055763568","display_name":"Jialin Tian","orcid":"https://orcid.org/0009-0002-2434-2737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Jialin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130740851","display_name":"Xinyu Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130762060","display_name":"Lifeng Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Lifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130786207","display_name":"Cewu Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Cewu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130814086","display_name":"Lixin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Lixin","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":0.617900013923645,"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":0.617900013923645,"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":0.16089999675750732,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0714000016450882,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7240999937057495},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.49549999833106995},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4860000014305115},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4593000113964081},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.39809998869895935},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3944999873638153},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.3711000084877014}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7249000072479248},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7240999937057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7010999917984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6078000068664551},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.49549999833106995},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4593000113964081},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.39809998869895935},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25399","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.2603.25399","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25399","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":{"We":[0],"introduce":[1],"\\textbf{LaMP},":[2],"a":[3,14,53,58,69],"dual-expert":[4],"Vision-Language-Action":[5],"framework":[6],"that":[7],"embeds":[8],"dense":[9],"3D":[10,36,73],"scene":[11,74],"flow":[12],"as":[13,98,100],"latent":[15],"motion":[16],"prior":[17,142],"for":[18],"robotic":[19],"manipulation.Existing":[20],"VLA":[21,106],"models":[22],"regress":[23],"actions":[24],"directly":[25],"from":[26],"2D":[27],"semantic":[28],"visual":[29],"features,":[30],"forcing":[31],"them":[32],"to":[33],"learn":[34],"complex":[35],"physical":[37],"interactions":[38],"implicitly.This":[39],"implicit":[40],"learning":[41],"strategy":[42],"degrades":[43],"under":[44,121],"unfamiliar":[45],"spatial":[46],"dynamics.LaMP":[47],"addresses":[48],"this":[49],"limitation":[50],"by":[51],"aligning":[52],"flow-matching":[54],"\\emph{Motion":[55],"Expert}":[56,61],"with":[57,134],"policy-predicting":[59],"\\emph{Action":[60],"through":[62],"gated":[63],"cross-attention.Specifically,":[64],"the":[65,81,91,115,122,140],"Motion":[66],"Expert":[67,83],"generates":[68],"one-step":[70],"partially":[71],"denoised":[72],"flow,":[75],"and":[76,94,111],"its":[77],"hidden":[78],"states":[79],"condition":[80],"Action":[82],"without":[84],"full":[85],"multi-step":[86],"reconstruction.We":[87],"evaluate":[88],"LaMP":[89,130],"on":[90],"LIBERO,":[92,109],"LIBERO-Plus,":[93,110],"SimplerEnv-WidowX":[95,112],"simulation":[96],"benchmarks":[97],"well":[99],"real-world":[101],"experiments.LaMP":[102],"consistently":[103],"outperforms":[104],"evaluated":[105],"baselines":[107],"across":[108],"benchmarks,":[113],"achieving":[114],"highest":[116],"reported":[117],"average":[118,136],"success":[119],"rates":[120],"same":[123],"training":[124],"budgets.":[125],"On":[126],"LIBERO-Plus":[127],"OOD":[128],"perturbations,":[129],"shows":[131],"improved":[132],"robustness":[133],"an":[135],"9.7\\%":[137],"gain":[138],"over":[139],"strongest":[141],"baseline.Our":[143],"project":[144],"page":[145],"is":[146],"available":[147],"at":[148],"https://summerwxk.github.io/lamp-project-page/.":[149]},"counts_by_year":[],"updated_date":"2026-07-02T06:12:58.138171","created_date":"2026-03-28T00:00:00"}