{"id":"https://openalex.org/W7134807796","doi":"https://doi.org/10.48550/arxiv.2603.08361","title":"$\u0394$VLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation","display_name":"$\u0394$VLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134807796","doi":"https://doi.org/10.48550/arxiv.2603.08361"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.08361","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128670881","display_name":"Yijie Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128650668","display_name":"Jie He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128631978","display_name":"Rui Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113137535","display_name":"Kaishen Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Kaishen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128630185","display_name":"Tao Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128678107","display_name":"Xiaochen Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Xiaochen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124366611","display_name":"Zitong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zitong","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30198102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9376999735832214,"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":0.9376999735832214,"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":0.020400000736117363,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/variation","display_name":"Variation (astronomy)","score":0.6003999710083008},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4934999942779541},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.49140000343322754},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47679999470710754},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.44609999656677246},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.39820000529289246},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.33390000462532043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6801000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6277999877929688},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47679999470710754},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C56289545","wikidata":"https://www.wikidata.org/wiki/Q6423376","display_name":"Knowledge integration","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.08361","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.08361","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.08361","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":"pmh:doi:10.48550/arxiv.2603.08361","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Recent":[0],"vision-language-action":[1],"(VLA)":[2],"models":[3,26,39,70],"have":[4],"significantly":[5],"advanced":[6],"robotic":[7,205],"manipulation":[8],"by":[9,120],"unifying":[10],"perception,":[11],"reasoning,":[12],"and":[13,112,123,190,203,216],"control.":[14],"To":[15,60],"achieve":[16],"such":[17],"integration,":[18],"recent":[19],"studies":[20],"adopt":[21],"a":[22,66,152,157],"predictive":[23],"paradigm":[24],"that":[25,69],"future":[27,87],"visual":[28,117],"states":[29],"or":[30],"world":[31,88,96,137,162],"knowledge":[32,78,97,138,163,195],"to":[33,58,74,92,134,160,170,174],"guide":[34],"action":[35,81],"generation.":[36],"However,":[37],"these":[38],"emphasize":[40],"forecasting":[41],"outcomes":[42],"rather":[43,83],"than":[44,84],"reasoning":[45],"about":[46],"the":[47,94,101,116,144,182,192],"underlying":[48],"process":[49],"of":[50,194],"change,":[51],"which":[52],"is":[53],"essential":[54],"for":[55,80],"determining":[56],"how":[57,136],"act.":[59],"address":[61],"this,":[62,133],"we":[63,99,142,180],"propose":[64,100],"$\u0394$VLA,":[65],"prior-guided":[67],"framework":[68],"world-knowledge":[71],"variations":[72],"relative":[73],"an":[75],"explicit":[76],"current-world":[77],"prior":[79,124],"generation,":[82],"regressing":[85],"absolute":[86],"states.":[89],"Specifically,":[90],"1)":[91],"construct":[93],"current":[95],"prior,":[98],"Prior-Guided":[102],"WorldKnowledge":[103],"Extractor":[104],"(PWKE).":[105],"It":[106,150],"extracts":[107],"manipulable":[108],"regions,":[109],"spatial":[110],"relations,":[111],"semantic":[113],"cues":[114],"from":[115,167],"input,":[118],"guided":[119],"auxiliary":[121],"heads":[122],"pseudo":[125],"labels,":[126],"thus":[127],"reducing":[128],"redundancy.":[129],"2)":[130],"Building":[131],"upon":[132],"represent":[135],"evolves":[139],"under":[140],"actions,":[141],"introduce":[143],"Latent":[145],"World":[146],"Variation":[147,184],"Quantization":[148],"(LWVQ).":[149],"learns":[151],"discrete":[153],"latent":[154],"space":[155],"via":[156],"VQ-VAE":[158],"objective":[159],"encode":[161],"variations,":[164],"shifting":[165],"prediction":[166],"full":[168],"modalities":[169],"compact":[171],"latent.":[172],"3)Moreover,":[173],"mitigate":[175],"interference":[176],"during":[177],"variation":[178],"modeling,":[179],"design":[181],"Conditional":[183],"Attention":[185],"(CV-Atten),":[186],"whichpromotes":[187],"disentangled":[188],"learning":[189],"preserves":[191],"independence":[193],"representations.":[196],"Extensive":[197],"experiments":[198],"on":[199],"both":[200],"simulated":[201],"benchmarks":[202],"real-world":[204,217],"tasks":[206],"demonstrate":[207],"$\u0394$VLA":[208],"achieves":[209],"state-of-the-art":[210],"performance":[211],"while":[212],"improving":[213],"efficiency.":[214],"Code":[215],"execution":[218],"videos":[219],"are":[220],"available":[221],"at":[222],"https://github.com/JiuTian-VL/DeltaVLA.":[223]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-11T00:00:00"}