{"id":"https://openalex.org/W7117241752","doi":"https://doi.org/10.48550/arxiv.2512.20166","title":"LoLA: Long Horizon Latent Action Learning for General Robot Manipulation","display_name":"LoLA: Long Horizon Latent Action Learning for General Robot Manipulation","publication_year":2025,"publication_date":"2025-12-23","ids":{"openalex":"https://openalex.org/W7117241752","doi":"https://doi.org/10.48550/arxiv.2512.20166"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.20166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.20166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2512.20166","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121279248","display_name":"Xiaofan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiaofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121245131","display_name":"Xingyu Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Xingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019693483","display_name":"Jianlong Fu","orcid":"https://orcid.org/0000-0002-1749-9296"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jianlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030680663","display_name":"LI Zuolei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zuolei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121267751","display_name":"Dean Fortier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fortier, Dean","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051870798","display_name":"Galen E. Mullins","orcid":"https://orcid.org/0000-0003-1290-2901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mullins, Galen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101862316","display_name":"Andrey Kolobov","orcid":"https://orcid.org/0000-0003-4966-7466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kolobov, Andrey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101666011","display_name":"Baining Guo","orcid":"https://orcid.org/0000-0001-8349-8868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Baining","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":0.6157000064849854,"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":0.6157000064849854,"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":0.21629999577999115,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0502999983727932,"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/robot","display_name":"Robot","score":0.6388000249862671},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4699999988079071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41670000553131104},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.38940000534057617},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.36419999599456787},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.35989999771118164},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3393000066280365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797999739646912},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6388000249862671},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6205999851226807},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4699999988079071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.36419999599456787},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.35989999771118164},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3003999888896942},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2840000092983246},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C2776398200","wikidata":"https://www.wikidata.org/wiki/Q508880","display_name":"Aloha","level":4,"score":0.2770000100135803},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2727000117301941}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.20166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.20166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2512.20166","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.20166","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"capability":[1],"of":[2],"performing":[3],"long-horizon,":[4],"language-guided":[5],"robotic":[6,141],"manipulation":[7,48,180],"tasks":[8,159],"critically":[9],"relies":[10],"on":[11,139,148,160],"leveraging":[12],"historical":[13,75],"information":[14],"and":[15,54,61,77,93,144,152,162],"generating":[16],"coherent":[17],"action":[18,62],"sequences.":[19],"However,":[20],"such":[21,119],"capabilities":[22],"are":[23],"often":[24],"overlooked":[25],"by":[26],"existing":[27,102],"Vision-Language-Action":[28],"(VLA)":[29],"models.":[30],"To":[31],"solve":[32],"this":[33,116],"challenge,":[34],"we":[35],"propose":[36],"LoLA":[37,138,169],"(Long":[38],"Horizon":[39],"Latent":[40,87],"Action":[41],"Learning),":[42],"a":[43,83,131],"framework":[44],"designed":[45],"for":[46],"robot":[47,55,98,108,120],"that":[49,105,168],"integrates":[50],"long-term":[51],"multi-view":[52,78],"observations":[53],"proprioception":[56,109],"to":[57,69,122],"enable":[58],"multi-step":[59],"reasoning":[60],"generation.":[63],"We":[64,80,136],"first":[65],"employ":[66],"Vision-Language":[67],"Models":[68],"encode":[70],"rich":[71],"contextual":[72],"features":[73],"from":[74],"sequences":[76],"observations.":[79],"further":[81],"introduces":[82],"key":[84],"module,":[85],"State-Aware":[86],"Re-representation,":[88],"which":[89],"transforms":[90],"visual":[91],"inputs":[92],"language":[94],"commands":[95],"into":[96],"actionable":[97],"motion":[99],"space.":[100,135],"Unlike":[101],"VLA":[103],"approaches":[104],"merely":[106],"concatenate":[107],"(e.g.,":[110,175],"joint":[111],"angles)":[112],"with":[113],"VL":[114,125],"embeddings,":[115],"module":[117],"leverages":[118],"states":[121],"explicitly":[123],"ground":[124],"representations":[126],"in":[127,178],"physical":[128],"scale":[129],"through":[130],"learnable":[132],"\"embodiment-anchored\"":[133],"latent":[134],"trained":[137],"diverse":[140],"pre-training":[142],"datasets":[143],"conducted":[145],"extensive":[146],"evaluations":[147],"simulation":[149],"benchmarks":[150],"(SIMPLER":[151],"LIBERO),":[153],"as":[154,156],"well":[155],"two":[157],"real-world":[158],"Franka":[161],"Bi-Manual":[163],"Aloha":[164],"robots.":[165],"Results":[166],"show":[167],"significantly":[170],"outperforms":[171],"prior":[172],"state-of-the-art":[173],"methods":[174],"pi0),":[176],"particularly":[177],"long-horizon":[179],"tasks.":[181]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-25T00:00:00"}
