{"id":"https://openalex.org/W7214400321","doi":"https://doi.org/10.48550/arxiv.2609.29934","title":"Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation","display_name":"Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation","publication_year":2026,"publication_date":"2026-09-24","ids":{"openalex":"https://openalex.org/W7214400321","doi":"https://doi.org/10.48550/arxiv.2609.29934"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.29934","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29934","pdf_url":"https://arxiv.org/pdf/2609.29934","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.29934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152926714","display_name":"Xun Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126163235","display_name":"Shijia Zhao","orcid":"https://orcid.org/0000-0002-1132-134X","observed_orcids":["https://orcid.org/0000-0002-1132-134X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Shijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102736545","display_name":"Rongsheng Qu","orcid":"https://orcid.org/0009-0004-1728-2208","observed_orcids":["https://orcid.org/0009-0004-1728-2208"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Rongsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152814242","display_name":"Jiayuan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiayuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152896801","display_name":"Xin Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152886965","display_name":"Weixin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Weixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152887279","display_name":"Chenglu Wen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Chenglu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5152926537","display_name":"Cheng Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Cheng","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":true,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6039999723434448,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6039999723434448,"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"}},{"id":"https://openalex.org/T11904","display_name":"Spatial Cognition and Navigation","score":0.2549000084400177,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04919999837875366,"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/spatial-reasoning","display_name":"spatial reasoning","score":0.6430000066757202},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/spatial-priors","display_name":"spatial priors","score":0.4740000069141388},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/hm3d","display_name":"HM3D","score":0.6470000147819519},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.4410000145435333},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.5009999871253967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6951000094413757},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978000164031982},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4641999900341034},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.29934","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29934","pdf_url":"https://arxiv.org/pdf/2609.29934","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.29934","doi":"https://doi.org/10.48550/arxiv.2609.29934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.29934","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.29934","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.29934","pdf_url":"https://arxiv.org/pdf/2609.29934","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214400321.pdf","grobid_xml":"https://content.openalex.org/works/W7214400321.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2964339842","https://openalex.org/W3200063923","https://openalex.org/W4404390073","https://openalex.org/W4407590542","https://openalex.org/W4414050622","https://openalex.org/W4416692073","https://openalex.org/W7125861034","https://openalex.org/W7133306743","https://openalex.org/W7133489736","https://openalex.org/W7134925023","https://openalex.org/W7140902052","https://openalex.org/W7161735637","https://openalex.org/W7163188218","https://openalex.org/W7164010433","https://openalex.org/W7165037828","https://openalex.org/W7166551559"],"related_works":["https://openalex.org/W7214791340","https://openalex.org/W4416383403","https://openalex.org/W7134925023","https://openalex.org/W3182243998","https://openalex.org/W7148471530","https://openalex.org/W7164854364","https://openalex.org/W7214938949","https://openalex.org/W7153273023","https://openalex.org/W7154077499","https://openalex.org/W3183185933"],"abstract_inverted_index":{"Does":[0],"progress":[1],"on":[2,90,127,130,134,143],"spatial":[3,32,41,91,107],"reasoning":[4,108],"benchmarks":[5,11],"translate":[6],"into":[7,100],"better":[8],"navigation?":[9],"Existing":[10],"test":[12],"isolated":[13],"inferences":[14],"from":[15],"images":[16],"or":[17,146],"videos,":[18],"with":[19,43,76],"little":[20],"connection":[21],"to":[22],"downstream":[23],"navigation.":[24,51],"Our":[25],"analysis":[26],"reveals":[27],"a":[28,67,87,101],"gap":[29],"between":[30],"benchmark-oriented":[31],"specialization":[33],"and":[34,37,47,59,71,97,132,160],"navigation":[35,44],"performance,":[36],"shows":[38],"how":[39],"aligning":[40],"supervision":[42],"goals,":[45],"phases,":[46],"decision":[48],"learning":[49,66],"improves":[50],"Guided":[52],"by":[53],"these":[54],"findings,":[55],"we":[56],"build":[57],"\\textsc{Spatial-Nav-100K}":[58],"fine-tune":[60],"in":[61],"two":[62],"stages,":[63],"\\textit{i.e.}":[64],"first":[65],"shared":[68],"spatial-navigation":[69],"foundation,":[70],"then":[72],"specializing":[73],"each":[74],"phase":[75],"the":[77],"abilities":[78],"it":[79],"relies":[80],"on.":[81],"We":[82],"further":[83],"introduce":[84],"Spatial-NPD,":[85],"where":[86],"teacher":[88],"conditioned":[89],"priors":[92],"produces":[93],"grounded":[94],"action":[95,156],"preferences":[96],"distills":[98],"them":[99],"student":[102],"policy,":[103],"so":[104],"no":[105],"explicit":[106],"is":[109],"needed":[110],"at":[111,152,166],"inference.":[112],"With":[113],"45":[114],"A100":[115],"GPU-hours":[116,149],"of":[117,125,148,150],"policy":[118],"training,":[119,151],"our":[120],"8B":[121],"model":[122],"reaches":[123],"SR/SPL":[124],"77.4/35.4":[126],"HM3D-v0.2,":[128],"60.2/30.5":[129],"HM3D-v0.1,":[131],"47.9/20.6":[133],"train-unseen":[135],"MP3D.":[136],"It":[137],"outperforms":[138],"several":[139],"systems":[140],"that":[141],"rely":[142],"closed-source":[144],"models":[145],"thousands":[147],"148":[153],"ms":[154],"per":[155],"step.":[157],"All":[158],"code":[159],"datasets":[161],"will":[162],"be":[163],"publicly":[164],"available":[165],"https://github.com/ylwhxht/Spatial-Nav.":[167]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-26T00:00:00"}