{"id":"https://openalex.org/W7202416645","doi":null,"title":"Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models","display_name":"Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models","publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202416645"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.10278","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10278","pdf_url":"https://arxiv.org/pdf/2608.10278","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"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.10278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063275464","display_name":"Hunter Schofield","orcid":"https://orcid.org/0000-0002-0647-1300","observed_orcids":["https://orcid.org/0000-0002-0647-1300"]},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]},{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Schofield, Hunter","raw_affiliation_strings":["Huawei Technologies Canada","York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000554621","display_name":"Mohammed Elmahgiubi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Elmahgiubi, Mohammed","raw_affiliation_strings":["Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035729928","display_name":"Mohammad Mahdavian","orcid":"https://orcid.org/0000-0002-2904-6462","observed_orcids":["https://orcid.org/0000-0002-2904-6462"]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mahdavian, Mohammad","raw_affiliation_strings":["Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147119995","display_name":"Richard Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shi, Richard","raw_affiliation_strings":["Huawei Technologies Canada","University of Toronto {hunterls ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"University of Toronto {hunterls ,","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125657930","display_name":"Jinjun Shan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shan, Jinjun","raw_affiliation_strings":["York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"York University","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012752787","display_name":"Amir Rasouli","orcid":"https://orcid.org/0000-0002-0106-2225","observed_orcids":["https://orcid.org/0000-0002-0106-2225","https://orcid.org/0009-0002-1020-5483"]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rasouli, Amir","raw_affiliation_strings":["Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113280423","display_name":"Dongfeng Bai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bai, Dongfeng","raw_affiliation_strings":["Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spatial-grounding","display_name":"spatial grounding","score":0.9399999976158142},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9279999732971191},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.7459999918937683},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.7590000033378601},{"id":"https://openalex.org/keywords/object-size-estimation","display_name":"object size estimation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.7782999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512000203132629},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5393999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531499981880188},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49160000681877136},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3806999921798706},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3677999973297119},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C22304111","wikidata":"https://www.wikidata.org/wiki/Q1417978","display_name":"Object permanence","level":4,"score":0.33559998869895935},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2780871342","wikidata":"https://www.wikidata.org/wiki/Q7883752","display_name":"Underpinning","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26440000534057617}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2608.10278","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10278","pdf_url":"https://arxiv.org/pdf/2608.10278","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.10278","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10278","pdf_url":"https://arxiv.org/pdf/2608.10278","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/W7202416645.pdf","grobid_xml":"https://content.openalex.org/works/W7202416645.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W3168867926","https://openalex.org/W4390041933","https://openalex.org/W4391631327","https://openalex.org/W4403370767","https://openalex.org/W4414528763","https://openalex.org/W4414588530","https://openalex.org/W4414858116","https://openalex.org/W4415320074","https://openalex.org/W4416053382","https://openalex.org/W4416056960","https://openalex.org/W4416341260","https://openalex.org/W4416378724","https://openalex.org/W4416780398","https://openalex.org/W4417300531","https://openalex.org/W4417308961","https://openalex.org/W4417530744","https://openalex.org/W6947991961","https://openalex.org/W6948058629","https://openalex.org/W7106716530","https://openalex.org/W7106808433","https://openalex.org/W7108223783","https://openalex.org/W7127922984","https://openalex.org/W7133305662","https://openalex.org/W7134070812","https://openalex.org/W7162088579"],"related_works":["https://openalex.org/W7213418816","https://openalex.org/W7172404806","https://openalex.org/W7108223783","https://openalex.org/W4417495068","https://openalex.org/W7106716530","https://openalex.org/W4415800665","https://openalex.org/W7139944781","https://openalex.org/W7162795478","https://openalex.org/W7163422337","https://openalex.org/W4416339605"],"abstract_inverted_index":{"Spatial":[0],"understanding":[1],"is":[2],"fundamental":[3],"to":[4,86,113,128],"embodied":[5,13],"intelligence,":[6],"underpinning":[7],"applications":[8],"such":[9],"as":[10],"robotic":[11],"manipulation,":[12],"navigation,":[14],"and":[15,73,138,150,166],"autonomous":[16],"driving.":[17],"Although":[18],"recent":[19],"vision-language":[20,176],"models":[21],"(VLMs)":[22],"have":[23],"achieved":[24],"impressive":[25],"performance":[26,145],"on":[27,35,132,146],"spatial":[28,37,61,75,99,160],"reasoning":[29,93,100,173],"benchmarks,":[30],"state-of-the-art":[31,144],"approaches":[32],"typically":[33],"rely":[34],"additional":[36,65,129],"encoders":[38],"or":[39],"architectural":[40],"modifications":[41],"during":[42],"inference,":[43],"increasing":[44],"computational":[45],"cost.":[46],"We":[47],"introduce":[48],"Space":[49],"Tokens,":[50],"a":[51,91],"lightweight,":[52],"architecture-agnostic":[53],"framework":[54],"that":[55,115,158],"equips":[56],"VLMs":[57],"with":[58],"explicit":[59],"continuous":[60,78,159],"representations":[62,108],"without":[63],"requiring":[64],"inference-time":[66],"modules.":[67],"By":[68],"distilling":[69],"scene-level":[70],"3D":[71],"geometry":[72],"object-centric":[74],"attributes":[76],"into":[77,90,174],"latent":[79],"tokens,":[80],"our":[81],"method":[82],"enables":[83],"these":[84],"modalities":[85],"be":[87,110],"directly":[88],"incorporated":[89],"chain-of-thought":[92],"process,":[94],"thereby":[95],"improving":[96],"the":[97,103,106,122],"VLM's":[98],"capabilities.":[101],"At":[102],"same":[104],"time,":[105],"learned":[107],"can":[109],"explicitly":[111],"decoded":[112],"verify":[114],"they":[116],"encode":[117],"meaningful":[118],"geometric":[119,172],"information,":[120],"while":[121,142],"unified":[123],"token":[124],"interface":[125],"remains":[126],"extensible":[127],"modalities.":[130],"Experiments":[131],"VSI-Bench":[133],"improve":[134],"Qwen3-VL-8B":[135],"by":[136,140],"4.3%":[137],"SenseNova-SI-1.3":[139],"1.3%,":[141],"achieving":[143],"object":[147],"size":[148,152],"(79.2%)":[149],"room":[151],"estimation":[153],"(75.7%).":[154],"These":[155],"results":[156],"demonstrate":[157],"tokens":[161],"provide":[162],"an":[163],"effective,":[164],"interpretable,":[165],"computationally":[167],"efficient":[168],"mechanism":[169],"for":[170],"integrating":[171],"large":[175],"models.":[177]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-14T00:00:00"}