{"id":"https://openalex.org/W7160914369","doi":"https://doi.org/10.48550/arxiv.2605.10819","title":"ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models","display_name":"ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160914369","doi":"https://doi.org/10.48550/arxiv.2605.10819"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10819","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.2605.10819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027891370","display_name":"Zuojin Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Zuojin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125932661","display_name":"Haoyun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haoyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010771116","display_name":"Xinyuan Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Xinyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023569421","display_name":"Changjie Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Changjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125912294","display_name":"Dongjie Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huo, Dongjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135957857","display_name":"Yandan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yandan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135980653","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-2949-832X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024061114","display_name":"\u8521\u54f2\u5609","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Zhejia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135983657","display_name":"Feng Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135973732","display_name":"Mu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Mu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135998022","display_name":"jiachen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, jiachen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135155631","display_name":"De Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, De","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136000891","display_name":"Zhiheng Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Zhiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135938964","display_name":"Gang Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Gang","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":0.538100004196167,"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":0.538100004196167,"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":0.25040000677108765,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.042100001126527786,"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/latent-variable","display_name":"Latent variable","score":0.6014999747276306},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.542900025844574},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.5336999893188477},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5289000272750854},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5051000118255615},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43810001015663147},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4343999922275543},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6014999747276306},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.542900025844574},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.5336999893188477},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5289000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5095999836921692},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5051000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4959000051021576},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4050000011920929},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3917999863624573},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C70727504","wikidata":"https://www.wikidata.org/wiki/Q1806878","display_name":"Latent class model","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C2780617661","wikidata":"https://www.wikidata.org/wiki/Q541563","display_name":"Subcategory","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31869998574256897},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2685000002384186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10819","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.2605.10819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10819","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4103899300098419}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,26],"remain":[3],"constrained":[4],"by":[5,100,105,177],"the":[6,20,55,122,154,196,225,230],"scarcity":[7],"of":[8,18],"action-labeled":[9],"robot":[10,65,137],"data,":[11],"whereas":[12],"action-free":[13,85],"videos":[14],"provide":[15],"abundant":[16],"evidence":[17],"how":[19],"physical":[21],"world":[22],"changes.":[23],"Latent":[24,71,77],"action":[25],"offer":[27],"a":[28,111,140],"promising":[29],"way":[30],"to":[31,58,156,191,202,210],"extract":[32],"such":[33],"priors":[34],"from":[35,200,208,229],"videos,":[36],"but":[37],"reconstruction-trained":[38],"latent":[39,95,128,147,235],"codes":[40],"are":[41,98],"not":[42],"necessarily":[43],"suitable":[44],"for":[45],"policy":[46,151,155],"generation:":[47],"they":[48],"may":[49],"predict":[50],"future":[51],"observations":[52],"while":[53,102],"lacking":[54],"structure":[56],"needed":[57],"be":[59],"reused":[60],"or":[61],"generated":[62],"coherently":[63],"with":[64,136,149,214],"actions.":[66],"We":[67],"introduce":[68],"ALAM":[69,93,171,194],"(Algebraic":[70],"Action":[72,78],"Model),":[73],"an":[74],"Algebraically":[75],"Consistent":[76],"Model":[79],"that":[80,97,170,224],"turns":[81],"temporal":[82],"relations":[83],"in":[84],"video":[86],"into":[87],"structural":[88],"supervision.":[89],"Given":[90],"frame":[91],"triplets,":[92],"learns":[94],"transitions":[96,148,236],"grounded":[99],"reconstruction":[101],"being":[103],"regularized":[104],"composition":[106],"and":[107,125,174,184,207,237],"reversal":[108],"consistency,":[109],"encouraging":[110],"locally":[112,159],"additive":[113],"transition":[114,129,161],"space.":[115],"For":[116],"downstream":[117],"VLA":[118,192],"learning,":[119],"we":[120],"freeze":[121],"pretrained":[123],"encoder":[124],"use":[126],"its":[127],"sequences":[130],"as":[131],"auxiliary":[132],"generative":[133],"targets,":[134],"co-generated":[135],"actions":[138],"under":[139],"joint":[141,238],"flow-matching":[142],"objective.":[143],"This":[144],"couples":[145],"structured":[146,234],"flow-based":[150],"generation,":[152],"allowing":[153],"exploit":[157],"ALAM's":[158],"consistent":[160,215],"geometry":[162],"without":[163],"requiring":[164],"latent-to-action":[165],"decoding.":[166],"Representation":[167],"probes":[168],"show":[169],"reduces":[172],"additivity":[173],"reversibility":[175],"errors":[176],"25-85":[178],"times":[179],"over":[180],"unstructured":[181],"latent-action":[182],"baselines":[183],"improves":[185],"long-horizon":[186],"cumulative":[187],"reconstruction.":[188],"When":[189],"transferred":[190],"policies,":[193],"raises":[195],"average":[197],"success":[198],"rate":[199],"47.9%":[201],"85.0%":[203],"on":[204,212,217],"MetaWorld":[205],"MT50":[206],"94.1%":[209],"98.1%":[211],"LIBERO,":[213],"gains":[216],"real-world":[218],"manipulation":[219],"tasks.":[220],"Ablations":[221],"further":[222],"confirm":[223],"strongest":[226],"improvements":[227],"arise":[228],"synergy":[231],"between":[232],"algebraically":[233],"flow":[239],"matching.":[240]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}