{"id":"https://openalex.org/W7140902052","doi":"https://doi.org/10.48550/arxiv.2603.23864","title":"See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning","display_name":"See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140902052","doi":"https://doi.org/10.48550/arxiv.2603.23864"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2603.23864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.23864","pdf_url":"https://arxiv.org/pdf/2603.23864","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/2603.23864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130653907","display_name":"Yuxi Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei, Yuxi","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130683401","display_name":"Wei Hsiang Huang","orcid":"https://orcid.org/0000-0002-7885-4378","observed_orcids":["https://orcid.org/0000-0002-7885-4378"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Huang, Wei","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125177890","display_name":"Qirui Chen","orcid":"https://orcid.org/0009-0002-0330-1688","observed_orcids":["https://orcid.org/0009-0002-0330-1688"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Qirui","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101663633","display_name":"Lu Hou","orcid":"https://orcid.org/0000-0002-4694-1821","observed_orcids":["https://orcid.org/0000-0002-4694-1821","https://orcid.org/0000-0003-3085-9353"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121260409","display_name":"Xiaojuan Qi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi, Xiaojuan","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"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":0.9771000146865845,"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":0.9771000146865845,"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":0.004900000058114529,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.0019000000320374966,"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/embodied-agents","display_name":"embodied agents","score":0.6499999761581421},{"id":"https://openalex.org/keywords/active-exploration","display_name":"active exploration","score":0.6069999933242798},{"id":"https://openalex.org/keywords/temporal-grounding","display_name":"temporal grounding","score":0.6159999966621399},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.38100001215934753},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.699999988079071},{"id":"https://openalex.org/keywords/active-perception","display_name":"active perception","score":0.5180000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075000047683716},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7222999930381775},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6825000047683716},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5849000215530396},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44029998779296875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2603.23864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.23864","pdf_url":"https://arxiv.org/pdf/2603.23864","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.2603.23864","doi":"https://doi.org/10.48550/arxiv.2603.23864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23864","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:2603.23864","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.23864","pdf_url":"https://arxiv.org/pdf/2603.23864","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140902052.pdf","grobid_xml":"https://content.openalex.org/works/W7140902052.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2776202271","https://openalex.org/W3203821123","https://openalex.org/W4327810158","https://openalex.org/W4387929233","https://openalex.org/W4390041933","https://openalex.org/W4400720180","https://openalex.org/W4403580243","https://openalex.org/W4406033487","https://openalex.org/W4407759090","https://openalex.org/W4414051092","https://openalex.org/W4414588530","https://openalex.org/W4415257590","https://openalex.org/W4415270781","https://openalex.org/W4415309321","https://openalex.org/W4416027202","https://openalex.org/W4416027206","https://openalex.org/W4416073598","https://openalex.org/W4416378724","https://openalex.org/W4416613140","https://openalex.org/W4416613191","https://openalex.org/W4416780398","https://openalex.org/W4416790787","https://openalex.org/W4416895257","https://openalex.org/W4417078012","https://openalex.org/W4417095044","https://openalex.org/W4417136661","https://openalex.org/W4417297059","https://openalex.org/W4417443023","https://openalex.org/W4417459816","https://openalex.org/W6929358048","https://openalex.org/W6966787903","https://openalex.org/W7077911270","https://openalex.org/W7080619107","https://openalex.org/W7083189701","https://openalex.org/W7083819494","https://openalex.org/W7106709520","https://openalex.org/W7108223783","https://openalex.org/W7117666444","https://openalex.org/W7117972711","https://openalex.org/W7119597214","https://openalex.org/W7125128317","https://openalex.org/W7125768645","https://openalex.org/W7128848049","https://openalex.org/W7155054664","https://openalex.org/W7166493911","https://openalex.org/W7166853358"],"related_works":["https://openalex.org/W7214801642","https://openalex.org/W7163400197","https://openalex.org/W7220986925","https://openalex.org/W7221762321","https://openalex.org/W7164913088","https://openalex.org/W7165378724","https://openalex.org/W7221171828","https://openalex.org/W7170377220","https://openalex.org/W4417086837","https://openalex.org/W7165743908"],"abstract_inverted_index":{"Spatial":[0],"understanding":[1],"is":[2,36],"fundamental":[3],"for":[4,48,100],"embodied":[5],"agents,":[6],"yet":[7],"most":[8],"spatial":[9,50,127,194],"VLMs":[10],"and":[11,20,29,64,88,91,109,116,144,177,182],"benchmarks":[12],"remain":[13],"offline-evaluating":[14],"post-hoc":[15],"QA":[16],"over":[17],"pre-recorded":[18],"inputs":[19],"overlooking":[21],"two":[22],"crucial":[23],"deployment-critical":[24],"requirements:":[25],"long-horizon":[26,138],"streaming":[27,49,93,126],"inference":[28],"active":[30,54,146],"perception":[31],"when":[32],"the":[33,180],"current":[34],"view":[35],"insufficient.":[37],"To":[38],"address":[39],"this":[40],"gap,":[41],"we":[42],"introduce":[43],"S3-Bench,":[44],"a":[45,78,82],"benchmark":[46],"suite":[47],"question":[51],"answering":[52],"with":[53,85,112],"exploration,":[55,147],"where":[56],"queries":[57],"are":[58],"temporally":[59],"grounded":[60],"to":[61,73,154,165,192],"specific":[62],"timestamps":[63],"must":[65],"be":[66],"answered":[67],"using":[68,167],"only":[69],"observations":[70,139],"available":[71],"up":[72],"that":[74,95],"moment.":[75],"S3-Bench":[76],"adopts":[77],"dual-domain":[79],"design,":[80],"combining":[81],"scalable":[83],"simulator":[84],"controllable":[86],"trajectories":[87],"exploration":[89],"actions,":[90],"real-world":[92],"videos":[94],"capture":[96],"practical":[97],"sensing":[98],"artifacts":[99],"rigorous":[101],"generalization":[102],"evaluation.":[103],"Overall,":[104],"it":[105],"spans":[106],"10K+":[107],"scenes":[108],"26K+":[110],"trajectories,":[111],"dedicated":[113],"training":[114,169],"(S3-Train)":[115],"evaluation":[117],"(S3-Eval)":[118],"splits.":[119],"We":[120],"further":[121],"propose":[122],"AMF-VLM,":[123],"which":[124,136,148],"supports":[125],"reasoning":[128],"under":[129],"bounded":[130],"computing":[131],"via":[132],"(i)":[133],"memory":[134],"folding,":[135],"compresses":[137],"into":[140],"compact":[141],"structured":[142],"memory,":[143],"(ii)":[145],"outputs":[149],"explicit":[150],"actions":[151],"(e.g.":[152],"move/rotate/scan)":[153],"acquire":[155],"missing":[156],"evidence":[157],"before":[158],"answering.":[159],"Extensive":[160],"experiments":[161],"demonstrate":[162],"that,":[163],"compared":[164],"models":[166],"identical":[168],"data,":[170],"our":[171],"approach":[172],"yields":[173],"improvements":[174],"of":[175,185],"8.8%":[176],"13.3%":[178],"on":[179],"simulated":[181],"real":[183],"splits":[184],"S3-Eval,":[186],"respectively,":[187],"while":[188],"maintaining":[189],"competitive":[190],"transferability":[191],"standard":[193],"benchmarks.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-27T00:00:00"}