{"id":"https://openalex.org/W7202277385","doi":"https://doi.org/10.48550/arxiv.2608.10864","title":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models","display_name":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202277385","doi":"https://doi.org/10.48550/arxiv.2608.10864"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.10864","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10864","pdf_url":"https://arxiv.org/pdf/2608.10864","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.10864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146978763","display_name":"Kiet T. Nguyen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nguyen, Kiet T.","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153549389","display_name":"Hanbo Shim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shim, Hanbo","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146942376","display_name":"Jinwoo Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Jinwoo","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125532494","display_name":"Seunghoon Hong","orcid":"https://orcid.org/0009-0004-7685-5352","observed_orcids":["https://orcid.org/0009-0004-7685-5352"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong, Seunghoon","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/knowledge-distillation","display_name":"knowledge distillation","score":0.7730000019073486},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9399999976158142},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.8899999856948853},{"id":"https://openalex.org/keywords/visual-spatial-representation","display_name":"visual-spatial representation","score":0.7639999985694885},{"id":"https://openalex.org/keywords/language-alignment","display_name":"language alignment","score":0.6190000176429749},{"id":"https://openalex.org/keywords/object-grounding","display_name":"object grounding","score":0.7419999837875366},{"id":"https://openalex.org/keywords/dense-captioning","display_name":"dense captioning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/3d-scene-understanding","display_name":"3D scene understanding","score":0.9399999976158142},{"id":"https://openalex.org/keywords/embodied-ai","display_name":"embodied AI","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7268999814987183},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7059999704360962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449999809265137},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6349999904632568},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.59579998254776},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5805000066757202},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4171999990940094},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4059999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.10864","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10864","pdf_url":"https://arxiv.org/pdf/2608.10864","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.10864","doi":"https://doi.org/10.48550/arxiv.2608.10864","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.10864","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.10864","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10864","pdf_url":"https://arxiv.org/pdf/2608.10864","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W7202277385.pdf","grobid_xml":"https://content.openalex.org/works/W7202277385.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161702702","https://openalex.org/W7221143860","https://openalex.org/W7146995672","https://openalex.org/W4416034737","https://openalex.org/W7221175283","https://openalex.org/W7202416645","https://openalex.org/W4417004625","https://openalex.org/W7166799920","https://openalex.org/W7213418816","https://openalex.org/W7172404806"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,69],"(VLMs)":[2],"have":[3],"achieved":[4],"strong":[5],"image":[6],"and":[7,28,86,91,149,162,178,191],"video":[8],"understanding,":[9,121],"yet":[10],"their":[11],"visual-spatial":[12,144],"representations":[13,171],"remain":[14,131],"geometrically":[15],"fragile,":[16],"leading":[17],"to":[18,33,130,133,180],"failures":[19],"in":[20],"spatial":[21,40,120],"reasoning":[22],"needed":[23],"for":[24,119],"embodied":[25],"AI,":[26],"robotics,":[27],"autonomous":[29],"driving.":[30],"Prior":[31],"approaches":[32],"geometry":[34],"grounding":[35],"either":[36],"fine-tune":[37],"VLMs":[38],"on":[39],"question":[41,192],"answering,":[42],"which":[43,57,100],"can":[44,79],"perpetuate":[45],"spurious":[46],"visual":[47,85,170],"representations,":[48,88],"or":[49],"fuse":[50],"features":[51,78,111],"from":[52,66],"large":[53],"geometry-grounded":[54,67],"vision":[55,68],"models,":[56],"substantially":[58],"increases":[59],"model":[60],"size":[61],"at":[62],"inference.":[63],"Knowledge":[64],"distillation":[65,98,151],"offers":[70],"an":[71],"alternative,":[72],"but":[73],"directly":[74],"matching":[75],"multi-view":[76,96],"teacher":[77,110],"disrupt":[80],"the":[81,109,124],"pretrained":[82,135],"alignment":[83],"between":[84],"textual":[87],"degrading":[89],"object-":[90],"language-semantic":[92],"capabilities.":[93],"We":[94,165],"propose":[95],"relational":[97],"(MVRD),":[99],"distills":[101],"patch-wise":[102],"cosine":[103],"similarities":[104],"across":[105],"views":[106],"instead":[107],"of":[108],"themselves.":[112],"These":[113],"relations":[114],"encode":[115],"geometric":[116,173],"correspondences":[117],"adequate":[118],"while":[122,152,174],"leaving":[123],"student":[125],"representation":[126],"underdetermined,":[127],"allowing":[128],"it":[129],"close":[132],"its":[134],"vision-":[136],"language":[137,176],"space.":[138],"Across":[139],"representative":[140],"VLMs,":[141],"MVRD":[142,168],"improves":[143],"reasoning,":[145],"outperforming":[146],"supervised":[147],"fine-tuning":[148],"feature":[150,154],"approaching":[153],"fusion":[155],"methods":[156],"with":[157],"considerably":[158],"fewer":[159],"added":[160],"parameters":[161],"lower":[163],"latency.":[164],"show":[166],"that":[167],"makes":[169],"more":[172],"retaining":[175],"alignment,":[177],"generalizes":[179],"3D":[181],"scene":[182],"understanding":[183],"tasks":[184],"such":[185],"as":[186],"object":[187],"grounding,":[188],"dense":[189],"captioning,":[190],"answering.":[193]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-13T00:00:00"}