{"id":"https://openalex.org/W7161127285","doi":"https://doi.org/10.48550/arxiv.2605.13328","title":"What Limits Vision-and-Language Navigation ?","display_name":"What Limits Vision-and-Language Navigation ?","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161127285","doi":"https://doi.org/10.48550/arxiv.2605.13328"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13328","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":"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.2605.13328","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128681510","display_name":"Yunheng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yunheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136156292","display_name":"Yuetong Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Yuetong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136152023","display_name":"Taowen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Taowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136113989","display_name":"Lusong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lusong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136183723","display_name":"Kun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136152953","display_name":"Junzhe Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Junzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326599","display_name":"Zizhao Yuan","orcid":"https://orcid.org/0009-0008-8399-7737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Zizhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136137309","display_name":"Yixiao Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yixiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136092603","display_name":"Jiaxi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiaxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136176327","display_name":"Wei Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067106372","display_name":"Zecui Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Zecui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136153280","display_name":"Renjing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Renjing","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":0.6916999816894531,"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":0.6916999816894531,"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":0.0731000006198883,"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":0.03139999881386757,"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/bottleneck","display_name":"Bottleneck","score":0.559499979019165},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5148000121116638},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.40849998593330383},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.39399999380111694},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3871999979019165},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3862999975681305},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.3808000087738037},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3750999867916107},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.36559998989105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6754999756813049},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5974000096321106},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5148000121116638},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.40849998593330383},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.39399999380111694},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3750999867916107},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35339999198913574},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C141141315","wikidata":"https://www.wikidata.org/wiki/Q2379942","display_name":"Guard (computer science)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3018999993801117},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13328","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":"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.2605.13328","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13328","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":"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"is":[3],"a":[4,77,103,143],"cornerstone":[5],"of":[6,64,146,177],"embodied":[7],"intelligence.":[8],"However,":[9],"current":[10],"agents":[11],"often":[12],"suffer":[13],"from":[14,20],"significant":[15],"performance":[16],"degradation":[17],"when":[18,122],"transitioning":[19],"simulation":[21],"to":[22,27,43,82,127,141],"real-world":[23,84,201],"deployment,":[24],"primarily":[25],"due":[26],"perceptual":[28],"instability":[29],"(e.g.,":[30],"lighting":[31],"variations":[32],"and":[33,36,52,68,95,134,148,162,174,179,181,183,191],"motion":[34,132],"blur)":[35],"under-specified":[37],"instructions.":[38],"While":[39],"existing":[40],"methods":[41],"attempt":[42],"bridge":[44],"this":[45,72],"gap":[46,91],"by":[47],"scaling":[48],"up":[49],"model":[50],"size":[51],"training":[53,94,193],"data,":[54],"we":[55,74,98],"argue":[56],"that":[57,112,165,205],"the":[58,62,89,119],"bottleneck":[59],"lies":[60],"in":[61,211],"lack":[63],"robust":[65,78],"spatial":[66],"grounding":[67,118],"cross-domain":[69],"priors.":[70],"In":[71],"paper,":[73],"propose":[75],"StereoNav,":[76],"Vision-Language-Action":[79],"framework":[80],"designed":[81],"enhance":[83],"navigation":[85,209],"consistency.":[86],"To":[87],"address":[88],"inherent":[90],"between":[92],"synthetic":[93],"physical":[96],"execution,":[97],"introduce":[99],"Target-Location":[100],"Priors":[101],"as":[102],"persistent":[104],"bridge.":[105],"These":[106],"priors":[107],"provide":[108],"stable":[109],"visual":[110,129],"guidance":[111],"remains":[113],"invariant":[114],"across":[115],"domains,":[116],"effectively":[117],"agent":[120],"even":[121],"instructions":[123],"are":[124],"vague.":[125],"Furthermore,":[126],"mitigate":[128],"disturbances":[130],"like":[131],"blur":[133],"illumination":[135],"shifts,":[136],"StereoNav":[137,166,206],"leverages":[138],"stereo":[139],"vision":[140],"construct":[142],"unified":[144],"representation":[145],"semantics":[147],"geometry,":[149],"enabling":[150],"precise":[151],"action":[152],"prediction":[153],"through":[154],"enhanced":[155],"depth":[156],"awareness.":[157],"Extensive":[158],"experiments":[159],"on":[160],"R2R-CE":[161],"RxR-CE":[163],"demonstrate":[164],"achieves":[167],"state-of-the-art":[168],"egocentric":[169],"RGB":[170],"performance,":[171],"with":[172],"SR":[173],"SPL":[175],"scores":[176],"81.1%":[178],"68.3%,":[180],"67.5%":[182],"52.0%,":[184],"respectively,":[185],"while":[186],"using":[187],"significantly":[188],"fewer":[189],"parameters":[190],"less":[192],"data":[194],"than":[195],"prior":[196],"scaling-based":[197],"approaches.":[198],"More":[199],"importantly,":[200],"robotic":[202],"deployments":[203],"confirm":[204],"substantially":[207],"improves":[208],"reliability":[210],"complex,":[212],"unstructured":[213],"environments.":[214],"Project":[215],"page:":[216],"https://yunheng-wang.github.io/stereonav-public.github.io.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-15T00:00:00"}
