{"id":"https://openalex.org/W7127654866","doi":"https://doi.org/10.1109/ccnc65079.2026.11366568","title":"MambaVLA: A Scalable and Efficient Vision-Language-Action Model with State Space Architecture","display_name":"MambaVLA: A Scalable and Efficient Vision-Language-Action Model with State Space Architecture","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7127654866","doi":"https://doi.org/10.1109/ccnc65079.2026.11366568"},"language":null,"primary_location":{"id":"doi:10.1109/ccnc65079.2026.11366568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc65079.2026.11366568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd Consumer Communications & Networking Conference (CCNC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125024802","display_name":"Sai Navaneet Peddapalli","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sai Navaneet Peddapalli","raw_affiliation_strings":["Kyungpook National University,Electronics and Electrical Engineering,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University,Electronics and Electrical Engineering,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125005208","display_name":"Manisha Lingala","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Manisha Lingala","raw_affiliation_strings":["Kyungpook National University,Electronics and Electrical Engineering,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University,Electronics and Electrical Engineering,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124984917","display_name":"Sangmoon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmoon Lee","raw_affiliation_strings":["Kyungpook National University,Electronics and Electrical Engineering,Daegu,South Korea"],"affiliations":[{"raw_affiliation_string":"Kyungpook National University,Electronics and Electrical Engineering,Daegu,South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125001676","display_name":"Ju H. Park","orcid":null},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ju H. Park","raw_affiliation_strings":["Yeungnam University,Dept. Electrical Engineering,Kyongsan,South Korea"],"affiliations":[{"raw_affiliation_string":"Yeungnam University,Dept. Electrical Engineering,Kyongsan,South Korea","institution_ids":["https://openalex.org/I55240360"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5125024802"],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27381404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9435999989509583,"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":0.9435999989509583,"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":0.007600000128149986,"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":0.007499999832361937,"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/scalability","display_name":"Scalability","score":0.7408000230789185},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5587999820709229},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5056999921798706},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.48500001430511475},{"id":"https://openalex.org/keywords/applications-of-artificial-intelligence","display_name":"Applications of artificial intelligence","score":0.30630001425743103},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.30160000920295715}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7408000230789185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876000165939331},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5056999921798706},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.427700012922287},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccnc65079.2026.11366568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccnc65079.2026.11366568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd Consumer Communications & Networking Conference (CCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2060422862","https://openalex.org/W4402353985","https://openalex.org/W4402354045","https://openalex.org/W4407874080","https://openalex.org/W4413146459"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"multimodal":[3,66],"learning":[4],"have":[5],"enabled":[6],"powerful":[7],"Vision\u2013Language\u2013Action":[8],"(VLA)":[9],"systems":[10],"for":[11,30,48,126],"robotic":[12],"reasoning":[13],"and":[14,27,59,86,110,122,129],"control.":[15,88],"However,":[16],"most":[17],"existing":[18],"approaches":[19],"rely":[20],"on":[21,42,91],"Transformer":[22,101],"backbones,":[23],"which":[24],"face":[25],"scalability":[26],"efficiency":[28],"bottlenecks":[29],"long":[31],"sequences.":[32],"This":[33],"work":[34],"introduces":[35],"MambaVLA,":[36],"a":[37],"scalable":[38],"VLA":[39,93],"framework":[40,53],"built":[41],"the":[43,55,116],"Mamba":[44],"state":[45,119],"space":[46,120],"architecture":[47],"efficient":[49],"sequence":[50],"modeling.":[51],"The":[52],"integrates":[54],"Eagle":[56],"visual":[57],"encoder":[58],"Qwen-7B-Chat-Int4":[60],"language":[61],"model":[62],"to":[63],"achieve":[64],"fine-grained":[65],"fusion":[67],"with":[68,80],"linear-time":[69],"complexity.":[70],"A":[71],"diffusion":[72],"flow":[73],"matching":[74],"module":[75],"further":[76],"aligns":[77],"visual\u2013language":[78],"embeddings":[79],"continuous":[81],"action":[82,124],"trajectories,":[83],"enabling":[84],"smooth":[85],"precise":[87],"Extensive":[89],"evaluations":[90],"standard":[92],"benchmarks":[94],"demonstrate":[95],"that":[96],"MambaVLA":[97],"matches":[98],"or":[99],"surpasses":[100],"based":[102],"models":[103],"while":[104],"offering":[105],"substantially":[106],"lower":[107],"computational":[108],"cost":[109],"faster":[111],"inference.":[112],"These":[113],"results":[114],"highlight":[115],"potential":[117],"of":[118],"modeling":[121],"flow-based":[123],"generation":[125],"compact,":[127],"scalable,":[128],"deployable":[130],"embodied":[131],"intelligence":[132],"systems.":[133],"https://sainavaneet.github.io/MambaVLA.gihub.io/":[134]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-06T00:00:00"}