{"id":"https://openalex.org/W7171727028","doi":"https://doi.org/10.48550/arxiv.2607.25516","title":"A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models","display_name":"A Causality-aware Infer-diagnose-refine Framework for Test-time Modality Adaptation in VLA Models","publication_year":2026,"publication_date":"2026-07-28","ids":{"openalex":"https://openalex.org/W7171727028","doi":"https://doi.org/10.48550/arxiv.2607.25516"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.25516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.25516","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":"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.2607.25516","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143950156","display_name":"Haoyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143873722","display_name":"Yuwei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143916453","display_name":"Jin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053519162","display_name":"Gao Zhi","orcid":"https://orcid.org/0000-0003-4101-9923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi, Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124979033","display_name":"Zhenxin Diao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diao, Zhenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143926689","display_name":"Mingyang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Mingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143966743","display_name":"Kun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101668970","display_name":"Yongchun Liu","orcid":"https://orcid.org/0000-0002-3318-5019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yongchun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143904161","display_name":"Fan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Fan","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":0.8522999882698059,"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":0.8522999882698059,"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":0.02449999935925007,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.01720000058412552,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.671500027179718},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5906999707221985},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4480000138282776},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.44269999861717224},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4397999942302704},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3476000130176544},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.3285999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462000250816345},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.671500027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6542999744415283},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4918999969959259},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.25516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.25516","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":"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.2607.25516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.25516","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":"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":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,27],"predict":[3],"sequential":[4],"actions":[5,86],"to":[6,22,113,129],"execute":[7],"tasks":[8,162],"specified":[9],"by":[10],"language":[11],"instructions,":[12],"conditioned":[13],"on":[14,156],"visual":[15,50,93,102,178],"observations":[16,51,103],"and":[17,42,89,95,147,160],"proprioceptive":[18],"states.":[19],"However,":[20],"how":[21],"fuse":[23],"modalities":[24],"in":[25,45,118,165],"VLA":[26,74,170],"remains":[28],"an":[29,61],"open":[30],"problem,":[31],"since":[32],"robot":[33],"manipulation":[34],"involves":[35],"dynamic":[36,107],"phases,":[37],"such":[38],"as":[39,104],"long-distance":[40],"movements":[41],"close-range":[43],"interactions,":[44],"which":[46,109],"the":[47,98,105,115,131,173],"importance":[48,179],"of":[49,92,101,175],"may":[52],"vary":[53],"over":[54],"time.":[55,82,182],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"infer-diagnose-refine":[62],"(IDR)":[63],"framework,":[64,133],"a":[65,119,125],"model-agnostic":[66],"framework":[67],"that":[68],"can":[69],"be":[70],"integrated":[71],"with":[72],"diverse":[73],"architectures":[75],"for":[76,137,143,151],"refining":[77,152],"action":[78,116,127],"predictions":[79,117],"at":[80,180],"test":[81,181],"IDR":[83,132],"first":[84],"infers":[85],"under":[87],"factual":[88],"counterfactual":[90,139],"scenarios":[91],"observations,":[94],"then":[96],"diagnoses":[97],"causal":[99,145],"effects":[100],"estimated":[106],"importance,":[108],"is":[110],"finally":[111],"used":[112],"refine":[114],"training-free":[120],"manner.":[121],"We":[122],"further":[123],"design":[124],"causality-aware":[126],"refiner":[128],"realize":[130],"including":[134],"zero-padding":[135],"interventions":[136],"inferring":[138],"actions,":[140],"norm-based":[141],"quantification":[142],"diagnosing":[144],"effects,":[146],"gated":[148],"residual":[149],"fusion":[150],"actions.":[153],"Extensive":[154],"experiments":[155],"both":[157],"simulation":[158],"benchmarks":[159],"real-world":[161],"show":[163],"improvements":[164],"overall":[166],"performance":[167],"across":[168],"multiple":[169],"backbones,":[171],"demonstrating":[172],"efficacy":[174],"dynamically":[176],"adjusting":[177]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-30T00:00:00"}