{"id":"https://openalex.org/W7164416893","doi":"https://doi.org/10.48550/arxiv.2606.11221","title":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment","display_name":"LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment","publication_year":2026,"publication_date":"2026-05-27","ids":{"openalex":"https://openalex.org/W7164416893","doi":"https://doi.org/10.48550/arxiv.2606.11221"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11221","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.2606.11221","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138449388","display_name":"Huaihai Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Huaihai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138427677","display_name":"Chaofan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chaofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138463722","display_name":"Yuheng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Yuheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138481971","display_name":"Xiansheng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xiansheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138443998","display_name":"Pengwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Pengwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138447146","display_name":"Shanghang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shanghang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138425589","display_name":"Changsheng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Changsheng","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/T10653","display_name":"Robot Manipulation and Learning","score":0.29030001163482666,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.29030001163482666,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.20890000462532043,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1289999932050705,"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/manifold","display_name":"Manifold (fluid mechanics)","score":0.5943999886512756},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5325000286102295},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.475600004196167},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.43290001153945923},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4120999872684479},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.39559999108314514},{"id":"https://openalex.org/keywords/metric-space","display_name":"Metric space","score":0.38280001282691956}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6622999906539917},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.5943999886512756},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.3756999969482422},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C81332173","wikidata":"https://www.wikidata.org/wiki/Q179899","display_name":"Topological space","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C74349738","wikidata":"https://www.wikidata.org/wiki/Q1517914","display_name":"Closed manifold","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2596000134944916},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11221","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.2606.11221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11221","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":{"We":[0],"take":[1],"a":[2,97,114],"Gromov-Wasserstein":[3],"perspective":[4],"on":[5],"Vision-Language-Action":[6],"(VLA)":[7],"learning,":[8],"where":[9],"the":[10,15,23,36,40,42,53,84,93,105,125,142,147],"goal":[11],"is":[12,32,47,59],"to":[13,35,87],"make":[14],"relational":[16],"geometry":[17,25],"of":[18,26,45,56],"action":[19,58,85,106],"representations":[20],"compatible":[21],"with":[22,92,141,160],"semantic":[24,43,143],"VL":[27,94],"embeddings.":[28],"However,":[29],"this":[30,73],"alignment":[31],"non-trivial":[33],"due":[34],"mathematical":[37],"heterogeneity":[38],"between":[39],"domains:":[41],"space":[44,86],"vision-language":[46],"topologically":[48],"linear":[49],"and":[50,61,129,153,163],"isotropic,":[51],"whereas":[52],"physical":[54],"manifold":[55,107],"robotic":[57],"non-Euclidean":[60],"anisotropic.":[62],"Their":[63],"disjoint":[64],"metric":[65,90],"structures":[66],"render":[67],"direct":[68],"regression":[69],"ill-posed.":[70],"To":[71],"resolve":[72],"incompatibility,":[74],"we":[75],"introduce":[76],"LAST":[77,156],"(Lie-algebraic":[78],"Action":[79],"Space":[80],"Tokenizer),":[81],"which":[82],"reconstructs":[83],"establish":[88],"local":[89,135,154],"compatibility":[91],"modality":[95],"via":[96,108],"two-stage":[98],"transformation:":[99],"(1)":[100],"Global":[101],"Topological":[102],"Linearization:":[103],"linearizing":[104],"Lie-algebraic":[109],"mapping,":[110],"converting":[111],"trajectories":[112],"into":[113,127],"fixed-length,":[115],"physically":[116],"additive":[117],"representation.":[118],"(2)":[119],"Local":[120],"Metric":[121],"Discretization:":[122],"hierarchically":[123],"discretizing":[124],"representation":[126],"schemas":[128],"whitened":[130],"residuals,":[131],"yielding":[132],"approximately":[133],"isotropic":[134],"charts":[136],"that":[137],"are":[138],"statistically":[139],"aligned":[140],"metric.":[144],"By":[145],"resolving":[146],"structural":[148],"mismatch":[149],"at":[150],"both":[151],"global":[152],"levels,":[155],"enables":[157],"VLA":[158],"models":[159],"superior":[161],"convergence":[162],"generalizability.":[164]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}