{"id":"https://openalex.org/W7160303326","doi":"https://doi.org/10.48550/arxiv.2605.00884","title":"LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception","display_name":"LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7160303326","doi":"https://doi.org/10.48550/arxiv.2605.00884"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00884","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.2605.00884","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135353926","display_name":"Justn williams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"williams, Justin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135308156","display_name":"Kishor Datta Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Kishor Datta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135393697","display_name":"Roy George","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George, Roy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135289947","display_name":"Mrinmoy Sarkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarkar, Mrinmoy","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":0.843500018119812,"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":0.843500018119812,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03139999881386757,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01269999984651804,"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/software-deployment","display_name":"Software deployment","score":0.6256999969482422},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6097999811172485},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.4023999869823456},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3926999866962433},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.3776000142097473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286999821662903},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6256999969482422},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6097999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2854999899864197},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.266400009393692}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00884","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.2605.00884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00884","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],"have":[3],"shown":[4],"strong":[5],"semantic":[6,61,117,148,191],"grounding":[7],"and":[8,28,58,68,150,170],"task":[9],"generalization":[10],"in":[11,77],"manipulation,":[12],"but":[13],"aerial":[14,147],"deployment":[15,186],"remains":[16],"difficult":[17],"because":[18],"drones":[19],"require":[20],"low-latency":[21],"closed-loop":[22],"guidance":[23,52],"under":[24,184],"strict":[25],"onboard":[26],"compute":[27],"communication":[29],"constraints.":[30],"We":[31],"present":[32],"LiteVLA-H,":[33],"a":[34,49,59,97,103,138,179],"compact":[35,79],"256M-parameter":[36],"VLA":[37],"system":[38,162],"designed":[39],"for":[40,54,63],"dual-rate":[41],"operation":[42],"on":[43,122],"an":[44],"NVIDIA":[45],"Jetson":[46],"AGX":[47],"Orin:":[48],"fast":[50],"outer-loop":[51],"mode":[53,62],"short":[55],"action-token":[56],"outputs":[57,118],"slower":[60],"scene":[64],"understanding,":[65],"hazard":[66],"description,":[67],"operator-facing":[69],"narration.":[70],"The":[71],"central":[72],"empirical":[73],"observation":[74],"is":[75,84],"that,":[76],"this":[78],"edge":[80,181],"regime,":[81],"end-to-end":[82],"latency":[83,157],"dominated":[85],"by":[86,91],"multimodal":[87],"pre-fill":[88],"rather":[89],"than":[90],"the":[92,123,129,161,174],"marginal":[93],"cost":[94],"of":[95],"decoding":[96],"few":[98],"extra":[99],"tokens.":[100],"This":[101],"motivates":[102],"scheduler":[104],"that":[105,142,173],"issues":[106],"reactive":[107,144],"action":[108,176],"tokens":[109],"at":[110,119],"50.65,ms":[111],"(19.74,Hz)":[112],"while":[113,188],"still":[114],"supporting":[115],"sentence-level":[116],"149.90--164.57\\ms":[120],"(6.08--6.67,Hz)":[121],"same":[124],"embedded":[125],"platform.":[126],"To":[127],"specialize":[128],"model":[130],"without":[131],"collapsing":[132],"its":[133],"descriptive":[134],"competence,":[135],"we":[136,159],"use":[137],"knowledge-preserving":[139],"fine-tuning":[140],"recipe":[141],"mixes":[143],"flight":[145],"data,":[146,149],"generic":[151],"caption/VQA":[152],"supervision.":[153],"Beyond":[154],"reporting":[155],"current":[156],"measurements,":[158],"position":[160],"against":[163],"recent":[164],"state-of-the-art":[165],"architectures,":[166],"including":[167],"AnywhereVLA,":[168],"FutureVLA,":[169],"ReMem-VLA,":[171],"showing":[172],"measured":[175],"branch":[177],"reaches":[178],"higher":[180],"inference":[182],"rate":[183],"our":[185],"conditions":[187],"retaining":[189],"periodic":[190],"awareness.":[192]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-06T00:00:00"}