{"id":"https://openalex.org/W7124428636","doi":"https://doi.org/10.48550/arxiv.2601.09954","title":"The Spatial Blindspot of Vision-Language Models","display_name":"The Spatial Blindspot of Vision-Language Models","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124428636","doi":"https://doi.org/10.48550/arxiv.2601.09954"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.09954","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.09954","pdf_url":"https://arxiv.org/pdf/2601.09954","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.09954","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123190431","display_name":"Nahid Alam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726847","display_name":"Cohere (Canada)","ror":"https://ror.org/050yr0479","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alam, Nahid","raw_affiliation_strings":["Cohere Labs Community ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cohere Labs Community ,","institution_ids":["https://openalex.org/I4401726847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110671845","display_name":"Leema Krishna Murali","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210151718","display_name":"Eisai (United States)","ror":"https://ror.org/0469x1750","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151718","https://openalex.org/I55881946"]},{"id":"https://openalex.org/I4401726847","display_name":"Cohere (Canada)","ror":"https://ror.org/050yr0479","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726847"]},{"id":"https://openalex.org/I55881946","display_name":"Eisai (Japan)","ror":"https://ror.org/04vvh7p27","country_code":"JP","type":"company","lineage":["https://openalex.org/I55881946"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Murali, Leema Krishna","raw_affiliation_strings":["Cohere Labs Community ,","Eisai Inc. ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cohere Labs Community ,","institution_ids":["https://openalex.org/I4401726847"]},{"raw_affiliation_string":"Eisai Inc. ,","institution_ids":["https://openalex.org/I4210151718","https://openalex.org/I55881946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113413172","display_name":"Siddhant Bharadwaj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bharadwaj, Siddhant","raw_affiliation_strings":["Indian Institute of Science , Bangalore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science , Bangalore ,","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123210126","display_name":"Patrick Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Patrick","raw_affiliation_strings":["UIUC ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC ,","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067312730","display_name":"Timothy S. Chung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726847","display_name":"Cohere (Canada)","ror":"https://ror.org/050yr0479","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726847"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Chung, Timothy","raw_affiliation_strings":["Cohere Labs Community ,","Imperial College London ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cohere Labs Community ,","institution_ids":["https://openalex.org/I4401726847"]},{"raw_affiliation_string":"Imperial College London ,","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123206655","display_name":"Drishti Sharma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726847","display_name":"Cohere (Canada)","ror":"https://ror.org/050yr0479","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharma, Drishti","raw_affiliation_strings":["Cohere Labs Community ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cohere Labs Community ,","institution_ids":["https://openalex.org/I4401726847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121301028","display_name":"Akshata M. A","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A, Akshata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123199068","display_name":"Kranthi Kiran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726847","display_name":"Cohere (Canada)","ror":"https://ror.org/050yr0479","country_code":"US","type":"company","lineage":["https://openalex.org/I4401726847"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kiran, Kranthi","raw_affiliation_strings":["Cohere Labs Community ,","EleutherAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cohere Labs Community ,","institution_ids":["https://openalex.org/I4401726847"]},{"raw_affiliation_string":"EleutherAI ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123203120","display_name":"Wesley Tam","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tam, Wesley","raw_affiliation_strings":["EleutherAI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EleutherAI ,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115087595","display_name":"Bala Krishna S Vegesna","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vegesna, Bala Krishna S","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"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":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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/spatial-grounding","display_name":"spatial grounding","score":0.5920000076293945},{"id":"https://openalex.org/keywords/image-encoder","display_name":"image encoder","score":0.8309999704360962},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.5040000081062317},{"id":"https://openalex.org/keywords/embodied-ai","display_name":"embodied AI","score":0.6830000281333923},{"id":"https://openalex.org/keywords/robotics","display_name":"robotics","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.7842000126838684},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.7842000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.696399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.696399986743927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6395000219345093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6395000219345093},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4629000127315521},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4629000127315521},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4471000134944916},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C2781179811","wikidata":"https://www.wikidata.org/wiki/Q28134081","display_name":"Spatial configuration","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C2781179811","wikidata":"https://www.wikidata.org/wiki/Q28134081","display_name":"Spatial configuration","level":3,"score":0.3262999951839447},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.2612999975681305}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.09954","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.09954","pdf_url":"https://arxiv.org/pdf/2601.09954","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.2601.09954","doi":"https://doi.org/10.48550/arxiv.2601.09954","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.09954","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:2601.09954","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.09954","pdf_url":"https://arxiv.org/pdf/2601.09954","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124428636.pdf","grobid_xml":"https://content.openalex.org/works/W7124428636.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W4296406182","https://openalex.org/W4382490555","https://openalex.org/W4400601172","https://openalex.org/W4402727516","https://openalex.org/W4403853618","https://openalex.org/W4404002404","https://openalex.org/W4413147844","https://openalex.org/W4416119086"],"related_works":["https://openalex.org/W7136433952","https://openalex.org/W6966787903","https://openalex.org/W4415085973","https://openalex.org/W7162810245","https://openalex.org/W4416082444","https://openalex.org/W7119022055","https://openalex.org/W7172404806","https://openalex.org/W7106117993","https://openalex.org/W4415796893","https://openalex.org/W4414588912"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3],"advanced":[4],"rapidly,":[5],"but":[6],"their":[7],"ability":[8],"to":[9,102],"capture":[10],"spatial":[11,45,53,68,104],"relationships":[12],"remains":[13],"a":[14,56,63],"blindspot.":[15],"Current":[16],"VLMs":[17],"are":[18],"typically":[19],"built":[20],"with":[21,85],"contrastive":[22],"language-image":[23],"pretraining":[24],"(CLIP)":[25],"style":[26],"image":[27,82],"encoders.":[28],"The":[29],"training":[30],"recipe":[31],"often":[32],"flattens":[33],"images":[34],"into":[35],"1D":[36],"patch":[37],"sequences,":[38],"discarding":[39],"the":[40],"2D":[41,90],"structure":[42],"necessary":[43],"for":[44,65],"reasoning.":[46],"We":[47],"argue":[48],"that":[49,96],"this":[50],"lack":[51],"of":[52],"awareness":[54],"is":[55],"missing":[57],"dimension":[58],"in":[59],"VLM":[60],"design":[61],"and":[62,73,88],"bottleneck":[64],"applications":[66],"requiring":[67],"grounding,":[69],"such":[70],"as":[71],"robotics":[72],"embodied":[74],"AI.":[75],"To":[76],"address":[77],"this,":[78],"we":[79],"investigate":[80],"(i)":[81],"encoders":[83],"trained":[84],"alternative":[86],"objectives":[87],"(ii)":[89],"positional":[91],"encodings.":[92],"Our":[93],"experiments":[94],"show":[95],"these":[97],"architectural":[98],"choices":[99],"can":[100],"lead":[101],"improved":[103],"reasoning":[105],"on":[106],"several":[107],"benchmarks.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-17T00:00:00"}
