{"id":"https://openalex.org/W7128537811","doi":"https://doi.org/10.48550/arxiv.2602.08236","title":"When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning","display_name":"When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128537811","doi":"https://doi.org/10.48550/arxiv.2602.08236"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.08236","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059195621","display_name":"Shoubin Yu","orcid":"https://orcid.org/0009-0006-1670-0054"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu, Shoubin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125514303","display_name":"Yue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122925318","display_name":"Zun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125506826","display_name":"Jaehong Yoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Jaehong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123700416","display_name":"Huaxiu Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Huaxiu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074680606","display_name":"Ping Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Mingyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125578398","display_name":"Mohit Bansal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bansal, Mohit","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5059195621"],"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":0.9779999852180481,"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":0.9779999852180481,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.0015999999595806003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6675000190734863},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6370000243186951},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5092999935150146},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5008999705314636},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46239998936653137},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4429999887943268},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.400299996137619},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6675000190734863},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169000267982483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5885999798774719},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.47859999537467957},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4120999872684479},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C2868805","wikidata":"https://www.wikidata.org/wiki/Q34516","display_name":"Imagination","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29429998993873596},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.08236","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.08236","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08236","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.08236","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5471600890159607}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"rapid":[1],"progress":[2],"in":[3],"Multimodal":[4],"Large":[5],"Language":[6],"Models":[7],"(MLLMs),":[8],"visual":[9,40,90,103,143,150],"spatial":[10,97,153,212],"reasoning":[11,35,154],"remains":[12],"unreliable":[13],"when":[14,46,58,101,107],"correct":[15],"answers":[16],"depend":[17],"on":[18],"how":[19,51,112],"a":[20,93],"scene":[21],"would":[22],"appear":[23],"under":[24],"unseen":[25],"or":[26,114,174,183],"alternative":[27],"viewpoints.":[28],"Recent":[29],"work":[30],"addresses":[31],"this":[32,81,123],"by":[33,76],"augmenting":[34],"with":[36,132,188],"world":[37,133],"models":[38,134],"for":[39,96,208],"imagination,":[41],"but":[42],"questions":[43],"such":[44],"as":[45,92],"imagination":[47,68,91,108,116,170,186,207],"is":[48,55,105,171],"actually":[49],"necessary,":[50],"much":[52],"of":[53,88,141,202],"it":[54,59],"beneficial,":[56],"and":[57,72,111,119,148,158,176,193,204,210],"becomes":[60],"harmful,":[61],"remain":[62],"poorly":[63],"understood.":[64],"In":[65,80],"practice,":[66],"indiscriminate":[67],"can":[69,181],"increase":[70],"computation":[71],"even":[73],"degrade":[74],"performance":[75],"introducing":[77],"misleading":[78],"evidence.":[79],"work,":[82],"we":[83,125],"present":[84],"an":[85,128,159],"in-depth":[86],"analysis":[87],"test-time":[89,130,206],"controllable":[94],"resource":[95],"reasoning.":[98,213],"We":[99],"study":[100],"static":[102],"evidence":[104,144],"sufficient,":[106],"improves":[109],"reasoning,":[110],"excessive":[113],"unnecessary":[115],"affects":[117],"accuracy":[118],"efficiency.":[120],"To":[121],"support":[122],"analysis,":[124],"introduce":[126],"AVIC,":[127],"adaptive":[129],"framework":[131],"that":[135,178],"explicitly":[136],"reasons":[137],"about":[138],"the":[139,200],"sufficiency":[140],"current":[142],"before":[145],"selectively":[146],"invoking":[147],"scaling":[149],"imagination.":[151],"Across":[152],"benchmarks":[155],"(SAT,":[156],"MMSI)":[157],"embodied":[160],"navigation":[161],"benchmark":[162],"(R2R),":[163],"our":[164,197],"results":[165],"reveal":[166],"clear":[167],"scenarios":[168],"where":[169],"critical,":[172],"marginal,":[173],"detrimental,":[175],"show":[177],"selective":[179],"control":[180],"match":[182],"outperform":[184],"fixed":[185],"strategies":[187],"substantially":[189],"fewer":[190],"world-model":[191],"calls":[192],"language":[194],"tokens.":[195],"Overall,":[196],"findings":[198],"highlight":[199],"importance":[201],"analyzing":[203],"controlling":[205],"efficient":[209],"reliable":[211]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-11T00:00:00"}