{"id":"https://openalex.org/W7162561547","doi":"https://doi.org/10.48550/arxiv.2605.27310","title":"How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning","display_name":"How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162561547","doi":"https://doi.org/10.48550/arxiv.2605.27310"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.27310","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27310","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.27310","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137142163","display_name":"Qian Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022074748","display_name":"Ankur Sikarwar","orcid":"https://orcid.org/0009-0007-4946-5289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sikarwar, Ankur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137181899","display_name":"Huy Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Huy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137169024","display_name":"Le Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137091621","display_name":"Zhuan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Zhuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028946392","display_name":"Perouz Taslakian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taslakian, Perouz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063960231","display_name":"Aishwarya Agrawal","orcid":"https://orcid.org/0000-0002-8620-8077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agrawal, Aishwarya","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":0.9921000003814697,"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":0.9921000003814697,"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/T10028","display_name":"Topic Modeling","score":0.0008999999845400453,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-thinking","display_name":"Visual thinking","score":0.7239000201225281},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6100999712944031},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.5963000059127808},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.33180001378059387},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.31850001215934753},{"id":"https://openalex.org/keywords/thinking-processes","display_name":"Thinking processes","score":0.313400000333786}],"concepts":[{"id":"https://openalex.org/C552651612","wikidata":"https://www.wikidata.org/wiki/Q7328862","display_name":"Visual thinking","level":2,"score":0.7239000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464999914169312},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641000270843506},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3165000081062317},{"id":"https://openalex.org/C187179951","wikidata":"https://www.wikidata.org/wiki/Q7784616","display_name":"Thinking processes","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2614000141620636},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.27310","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27310","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.27310","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.27310","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Cross-view":[0],"spatial":[1],"reasoning":[2],"remains":[3],"a":[4,93,157],"weak":[5],"spot":[6],"for":[7,22,140],"vision-language":[8],"models":[9,43,76],"(VLMs):":[10],"they":[11],"often":[12,44],"reason":[13],"in":[14,49,73],"language":[15],"and":[16,61,160,167,174,194,196],"lose":[17],"the":[18,23,46,85,104,112,117,121,131,135,187,199],"fine-grained":[19],"geometry":[20],"needed":[21],"task.":[24],"Thinking":[25],"with":[26,184],"images":[27],"aims":[28],"to":[29,56,111,119],"address":[30],"this":[31,155],"by":[32],"generating":[33],"an":[34],"intermediate":[35],"thinking":[36,59,66,122,136,149,183],"image,":[37],"but":[38],"recent":[39],"work":[40],"shows":[41],"that":[42,96,190],"ignore":[45],"visual":[47,58,65,148,182],"evidence":[48],"these":[50,71],"traces.":[51],"We":[52,69,153],"therefore":[53],"ask":[54],"how":[55],"make":[57],"matter,":[60],"what":[62],"kind":[63],"of":[64,99,127,147],"works":[67],"best.":[68],"study":[70,144],"questions":[72],"unified":[74],"multimodal":[75],"(UMMs),":[77],"which":[78,145],"natively":[79],"support":[80],"interleaved":[81],"image-text":[82],"generation.":[83],"For":[84],"first":[86],"question,":[87],"we":[88,143],"propose":[89],"View":[90],"Dropout":[91],"(VDrop),":[92],"training-time":[94],"intervention":[95],"hides":[97],"parts":[98],"one":[100],"input":[101,132],"view":[102],"from":[103],"answer":[105,141],"span":[106],"while":[107],"keeping":[108],"them":[109],"visible":[110],"thinking-image":[113,163],"tokens.":[114],"This":[115],"encourages":[116],"model":[118],"use":[120],"image":[123,137],"when":[124],"answering,":[125],"instead":[126],"relying":[128],"only":[129,188],"on":[130,171,176],"views.":[133],"Once":[134],"is":[138,150,186,191],"used":[139],"prediction,":[142],"type":[146],"most":[151],"effective.":[152],"frame":[154],"as":[156],"learnability-informativeness":[158],"tradeoff":[159],"compare":[161],"three":[162],"variants:":[164],"top-down,":[165],"panoramic,":[166],"point-matching":[168],"renderings.":[169],"Trained":[170],"synthetic":[172],"scenes":[173],"evaluated":[175],"five":[177],"real-world":[178],"out-of-domain":[179,201],"benchmarks,":[180],"panoramic":[181],"VDrop":[185],"configuration":[189],"both":[192],"informative":[193],"learnable,":[195],"it":[197],"achieves":[198],"best":[200],"generalization.":[202]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-28T00:00:00"}