{"id":"https://openalex.org/W7161702702","doi":"https://doi.org/10.48550/arxiv.2605.16713","title":"GeoWorld-VLM: Geometry from World Models for Vision-Language Models","display_name":"GeoWorld-VLM: Geometry from World Models for Vision-Language Models","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161702702","doi":"https://doi.org/10.48550/arxiv.2605.16713"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16713","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.2605.16713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136471506","display_name":"Renjie Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Renjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136468778","display_name":"Kaichen Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Kaichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136487581","display_name":"Yan Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136494832","display_name":"Mengyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Mengyu","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":0.984499990940094,"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":0.984499990940094,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0038999998942017555,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0019000000320374966,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6919000148773193},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6730999946594238},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5983999967575073},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5971999764442444},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.539900004863739},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.4731999933719635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4494999945163727}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6919000148773193},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6730999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.629800021648407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.616599977016449},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16713","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.2605.16713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16713","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5355085730552673}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"achieve":[4],"strong":[5],"semantic":[6],"recognition,":[7],"yet":[8],"remain":[9],"brittle":[10],"on":[11,196],"elementary":[12],"spatial":[13,60,124,128,157,213],"relations":[14],"such":[15],"as":[16],"left":[17],"of,":[18],"on,":[19],"behind,":[20],"and":[21,87,108,134,168,182,200,212],"between.":[22],"One":[23],"cause":[24],"of":[25,170],"this":[26],"failure":[27],"arises":[28],"before":[29],"language":[30,49,144],"reasoning":[31,214],"begins:":[32],"the":[33,48,84,100,113,139,143,150,160,166,171,198],"visual":[34,118,162,206],"pathway":[35],"may":[36],"compress":[37],"or":[38],"discard":[39],"critical":[40],"3D":[41],"structural":[42],"cues":[43],"during":[44],"feature":[45,132],"extraction,":[46],"so":[47],"model":[50,145,210],"receives":[51],"image":[52,85,92],"representations":[53,97],"that":[54,69,204],"are":[55],"already":[56],"insufficient":[57],"for":[58],"reliable":[59],"judgment.":[61],"We":[62],"introduce":[63],"GeoWorld-VLM,":[64],"a":[65,106,109,121,135],"VLM-side":[66],"distillation":[67],"framework":[68],"transfers":[70],"geometric":[71],"structure":[72],"from":[73],"frozen":[74],"camera-conditioned":[75],"video":[76],"world":[77],"models":[78],"into":[79,120],"VLMs.":[80],"GeoWorld-VLM":[81,148,176,189],"fine-tunes":[82],"only":[83],"encoder":[86],"multimodal":[88],"projector,":[89],"aligning":[90],"post-projector":[91],"features":[93],"with":[94],"intermediate":[95],"world-model":[96,114],"while":[98,155],"leaving":[99],"main":[101],"backbone":[102],"frozen.":[103],"Given":[104],"images,":[105],"prompt,":[107],"sampled":[110],"camera":[111],"trajectory,":[112],"teacher":[115],"converts":[116],"static":[117],"input":[119],"synthetic":[122],"multi-view":[123],"signal.":[125],"Training":[126],"combines":[127],"answer":[129],"supervision,":[130],"teacher-student":[131],"alignment,":[133],"preservation":[136],"anchor":[137],"to":[138,159,177],"original":[140,151],"VLM.":[141],"Since":[142],"remains":[146],"frozen,":[147],"preserves":[149],"model's":[152],"linguistic":[153],"capabilities":[154],"attributing":[156],"improvements":[158,185],"enhanced":[161],"pathway.":[163],"To":[164],"evaluate":[165],"effectiveness":[167],"generality":[169],"proposed":[172],"method,":[173],"we":[174],"apply":[175],"two":[178],"distinct":[179],"VLM":[180],"architectures":[181],"observe":[183],"consistent":[184],"across":[186,209],"both":[187,197],"backbones.":[188],"improves":[190],"performance":[191],"by":[192],"approximately":[193],"4":[194],"percent":[195],"What'sUp":[199],"VSR":[201],"benchmarks,":[202],"suggesting":[203],"world-model-guided":[205],"alignment":[207],"generalizes":[208],"structures":[211],"datasets.":[215]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-20T00:00:00"}