{"id":"https://openalex.org/W7155552896","doi":"https://doi.org/10.48550/arxiv.2604.21241","title":"CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors","display_name":"CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155552896","doi":"https://doi.org/10.48550/arxiv.2604.21241"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21241","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.21241","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134493982","display_name":"Dachong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Dachong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049290416","display_name":"Z C Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, ZhuangZhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134484160","display_name":"Jin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134564994","display_name":"Jianqiang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jianqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5134493982"],"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":0.5339000225067139,"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":0.5339000225067139,"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":0.17870000004768372,"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":0.055799998342990875,"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/action","display_name":"Action (physics)","score":0.7034000158309937},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6956999897956848},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4724999964237213},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.451200008392334},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3707999885082245},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3246000111103058}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7034000158309937},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6956999897956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142999887466431},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4724999964237213},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.451200008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44190001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3806000053882599},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3707999885082245},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21241","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.21241","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21241","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":"article"},"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":{"Vision--Language--Action":[0],"(VLA)":[1],"models":[2],"often":[3,18],"use":[4],"intermediate":[5],"representations":[6],"to":[7,41],"connect":[8],"multimodal":[9],"inputs":[10],"with":[11],"continuous":[12],"control,":[13],"yet":[14],"spatial":[15,30,68,138],"guidance":[16,139],"is":[17,147],"injected":[19],"implicitly":[20],"through":[21],"latent":[22,144],"features.":[23],"We":[24],"propose":[25],"$CorridorVLA$,":[26],"which":[27],"predicts":[28],"sparse":[29],"anchors":[31,55],"as":[32],"incremental":[33],"physical":[34,125],"changes":[35],"(e.g.,":[36],"$\u0394$-positions)":[37],"and":[38,81,99,130],"uses":[39],"them":[40],"impose":[42],"an":[43],"explicit":[44],"tolerance":[45],"region":[46],"in":[47,141],"the":[48,87,107],"training":[49],"objective":[50],"for":[51,133],"action":[52,63,135],"generation.":[53],"The":[54],"define":[56],"a":[57,61,115],"corridor":[58],"that":[59,123],"guides":[60],"flow-matching":[62],"head:":[64],"trajectories":[65],"whose":[66],"implied":[67],"evolution":[69],"falls":[70],"outside":[71],"it":[72],"receive":[73],"corrective":[74],"gradients,":[75],"while":[76],"minor":[77],"deviations":[78],"from":[79],"contacts":[80],"execution":[82],"noise":[83],"are":[84],"permitted.":[85],"On":[86],"more":[88],"challenging":[89],"LIBERO-Plus":[90],"benchmark,":[91],"CorridorVLA":[92],"yields":[93],"consistent":[94],"gains":[95],"across":[96],"both":[97],"SmolVLA":[98],"GR00T,":[100],"improving":[101],"success":[102,116],"rate":[103,117],"by":[104],"$3.4\\%$--$12.4\\%$":[105],"over":[106],"corresponding":[108],"baselines;":[109],"notably,":[110],"our":[111],"GR00T-Corr":[112],"variant":[113],"reaches":[114],"of":[118],"$83.21\\%$.":[119],"These":[120],"results":[121],"indicate":[122],"action-aligned":[124],"cues":[126],"can":[127],"provide":[128],"direct":[129],"interpretable":[131],"constraints":[132],"generative":[134],"policies,":[136],"complementing":[137],"encoded":[140],"visual":[142],"or":[143],"forms.":[145],"Code":[146],"available":[148],"at":[149],"https://github.com/corridorVLA.":[150]},"counts_by_year":[],"updated_date":"2026-04-25T06:06:54.107920","created_date":"2026-04-25T00:00:00"}