{"id":"https://openalex.org/W7169226898","doi":"https://doi.org/10.48550/arxiv.2607.13926","title":"S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving","display_name":"S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7169226898","doi":"https://doi.org/10.48550/arxiv.2607.13926"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.13926","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.13926","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":null,"license_id":null,"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.2607.13926","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141025778","display_name":"Jianguo Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jianguo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087671743","display_name":"Rukang Wang","orcid":"https://orcid.org/0000-0002-3647-8247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Rukang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141001266","display_name":"Duanfeng Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Duanfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141002806","display_name":"Chen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120605297","display_name":"Renju Feng","orcid":"https://orcid.org/0009-0007-5753-3448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Renju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140987347","display_name":"Liping Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Liping","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":0.6902999877929688,"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":0.6902999877929688,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.1446000039577484,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10036","display_name":"Advanced Neural Network Applications","score":0.0333000011742115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6383000016212463},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4016000032424927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3903999924659729},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3675999939441681},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3515999913215637},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.34860000014305115},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.3393000066280365},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3327000141143799},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.3246999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426999807357788},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4207000136375427},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C86369673","wikidata":"https://www.wikidata.org/wiki/Q1203659","display_name":"Simultaneous localization and mapping","level":4,"score":0.27489998936653137},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.27149999141693115},{"id":"https://openalex.org/C158709400","wikidata":"https://www.wikidata.org/wiki/Q3578586","display_name":"Spatial ecology","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.267300009727478},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.2590000033378601},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.13926","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.13926","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.13926","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.13926","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":null,"license_id":null,"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":[0],"Models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"potential":[6],"for":[7,86,120,200],"high-level":[8,167],"reasoning":[9],"in":[10,27,106],"autonomous":[11],"driving,":[12],"yet":[13],"they":[14],"fundamentally":[15],"struggle":[16],"to":[17,49,115],"generate":[18],"precise,":[19],"low-level":[20],"control":[21,57],"actions.":[22],"This":[23],"limitation":[24],"is":[25],"rooted":[26],"a":[28,59,65,71,162,188,197,204],"semantic-physical":[29],"gap":[30,52],"caused":[31],"by":[32,53],"the":[33,79,96,101,131,141,153,180,212,225],"inherent":[34],"mismatch":[35],"between":[36],"discrete":[37],"language":[38,133],"tokens":[39],"and":[40,56,82,103,158],"continuous":[41],"trajectory":[42],"planning.":[43],"While":[44],"Vision-Language-Action":[45,107],"(VLA)":[46],"architectures":[47],"attempt":[48],"bridge":[50],"this":[51,62,92,149],"unifying":[54],"perception":[55,147],"into":[58],"single":[60],"policy,":[61],"entanglement":[63],"creates":[64],"new":[66,198],"bottleneck.":[67],"Standard":[68],"VLAs":[69],"experience":[70],"severe":[72],"spatial":[73,81,104,128,138,157,172,213],"representation":[74,214],"collapse,":[75],"which":[76,98],"irreversibly":[77],"degrades":[78],"fine-grained":[80],"geometric":[83,159],"priors":[84],"essential":[85],"safe,":[87],"boundary-aware":[88],"navigation.":[89],"To":[90],"address":[91],"limitation,":[93],"we":[94],"propose":[95],"S-squared-VLA,":[97],"explicitly":[99,151],"decouples":[100],"semantic":[102,110,168],"streams":[105],"models.":[108],"The":[109],"stream":[111,129,150],"leverages":[112],"hierarchical":[113],"bridging":[114],"extract":[116],"multi-scale":[117],"VLM":[118],"features":[119,139],"robust":[121],"intent":[122,169],"reasoning.":[123],"In":[124],"parallel,":[125],"an":[126],"independent":[127],"bypasses":[130],"autoregressive":[132],"bottleneck,":[134],"directly":[135],"preserving":[136],"uncompressed":[137],"from":[140],"visual":[142],"encoder.":[143],"By":[144,210],"integrating":[145],"auxiliary":[146],"supervision,":[148],"equips":[152],"model":[154],"with":[155,170],"rich":[156],"priors.":[160],"Finally,":[161],"dual-stream":[163],"planning":[164],"adapter":[165],"fuses":[166],"precise":[171],"constraints":[173],"via":[174],"cascaded":[175],"attention":[176],"mechanisms.":[177],"Evaluations":[178],"on":[179],"NAVSIM":[181],"closed-loop":[182],"benchmark":[183],"show":[184],"that":[185],"S-squared-VLA":[186],"achieves":[187],"Predictive":[189],"Driver":[190],"Model":[191],"Score":[192],"(PDMS)":[193],"of":[194,216,231],"87.1,":[195],"establishing":[196],"state-of-the-art":[199],"VLA":[201],"models":[202],"under":[203],"purely":[205],"supervised":[206],"fine-tuning":[207],"(SFT)":[208],"setting.":[209],"mitigating":[211],"collapse":[215],"traditional":[217],"VLMs,":[218],"our":[219],"framework":[220],"significantly":[221],"outperforms":[222],"baselines,":[223],"achieving":[224],"highest":[226],"No":[227],"Collision":[228],"(NC)":[229],"rate":[230],"98.4":[232],"among":[233],"all":[234],"evaluated":[235],"methods.":[236]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-17T00:00:00"}