{"id":"https://openalex.org/W7203469167","doi":"https://doi.org/10.48550/arxiv.2608.12515","title":"Can Vision-Language Models Assess Proxemic Risk from Egocentric Robot Images?","display_name":"Can Vision-Language Models Assess Proxemic Risk from Egocentric Robot Images?","publication_year":2026,"publication_date":"2026-08-12","ids":{"openalex":"https://openalex.org/W7203469167","doi":"https://doi.org/10.48550/arxiv.2608.12515"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.12515","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12515","pdf_url":"https://arxiv.org/pdf/2608.12515","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"},"parent_works":[],"lineage":["https://openalex.org/W7203469167"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.12515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147143487","display_name":"Vladyslava Rudas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I112412981","display_name":"National University of Kyiv-Mohyla Academy","ror":"https://ror.org/03wfca816","country_code":"UA","type":"education","lineage":["https://openalex.org/I112412981"]}],"countries":["UA"],"is_corresponding":false,"raw_author_name":"Rudas, Vladyslava","raw_affiliation_strings":["Department of Computer Science , National University of Kyiv-Mohyla Academy , Kyiv , Ukraine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , National University of Kyiv-Mohyla Academy , Kyiv , Ukraine","institution_ids":["https://openalex.org/I112412981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067335362","display_name":"Dmytro Kuzmenko","orcid":"https://orcid.org/0009-0009-9296-1450","observed_orcids":["https://orcid.org/0009-0009-9296-1450"]},"institutions":[{"id":"https://openalex.org/I112412981","display_name":"National University of Kyiv-Mohyla Academy","ror":"https://ror.org/03wfca816","country_code":"UA","type":"education","lineage":["https://openalex.org/I112412981"]},{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT","UA"],"is_corresponding":false,"raw_author_name":"Kuzmenko, Dmytro","raw_affiliation_strings":["Department of Computer Science , University of Turin , Turin , Italy","Department of Multimedia Systems , National University of Kyiv-Mohyla Academy , Kyiv , Ukraine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Turin , Turin , Italy","institution_ids":["https://openalex.org/I55143463"]},{"raw_affiliation_string":"Department of Multimedia Systems , National University of Kyiv-Mohyla Academy , Kyiv , Ukraine","institution_ids":["https://openalex.org/I112412981"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9390000104904175,"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":0.9390000104904175,"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":0.03350000083446503,"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":0.010499999858438969,"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/vision-language-models","display_name":"vision-language models","score":0.9739999771118164},{"id":"https://openalex.org/keywords/robot-safety","display_name":"robot safety","score":0.41100001335144043},{"id":"https://openalex.org/keywords/embodied-navigation","display_name":"embodied navigation","score":0.5360000133514404},{"id":"https://openalex.org/keywords/prompting-strategies","display_name":"prompting strategies","score":0.8029999732971191},{"id":"https://openalex.org/keywords/qlora-fine-tuning","display_name":"QLoRA fine-tuning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/human-localization","display_name":"human localization","score":0.7749999761581421},{"id":"https://openalex.org/keywords/spatial-grounding","display_name":"spatial grounding","score":0.9890000224113464},{"id":"https://openalex.org/keywords/qwen-vl","display_name":"Qwen-VL","score":0.9929999709129333}],"concepts":[{"id":"https://openalex.org/C170334801","wikidata":"https://www.wikidata.org/wiki/Q171755","display_name":"Proxemics","level":2,"score":0.9650999903678894},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6575999855995178},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6455000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.631600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219000220298767},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5109000205993652},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.41019999980926514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.12515","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12515","pdf_url":"https://arxiv.org/pdf/2608.12515","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.2608.12515","doi":"https://doi.org/10.48550/arxiv.2608.12515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.12515","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:2608.12515","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12515","pdf_url":"https://arxiv.org/pdf/2608.12515","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/W7203469167.pdf","grobid_xml":"https://content.openalex.org/works/W7203469167.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2560647685","https://openalex.org/W2626778328","https://openalex.org/W2945169717","https://openalex.org/W2951912364","https://openalex.org/W3133364292","https://openalex.org/W3135367836","https://openalex.org/W3144974485","https://openalex.org/W4225323055","https://openalex.org/W4366330503","https://openalex.org/W4366400053","https://openalex.org/W4386185600","https://openalex.org/W4405595839","https://openalex.org/W4416296080","https://openalex.org/W7083189701","https://openalex.org/W7133231369","https://openalex.org/W7133233472","https://openalex.org/W7151409936"],"related_works":["https://openalex.org/W7167033496","https://openalex.org/W7170082618","https://openalex.org/W4415328840","https://openalex.org/W7154508084","https://openalex.org/W7166132482","https://openalex.org/W7220699115","https://openalex.org/W4409483173","https://openalex.org/W4413945182","https://openalex.org/W7202163802","https://openalex.org/W7125172455"],"abstract_inverted_index":{"Assessing":[0],"proxemic":[1,140],"danger":[2,44,102],"from":[3],"a":[4,57,113,117],"robot's":[5],"egocentric":[6,39],"perspective":[7],"is":[8],"critical":[9],"for":[10,86],"safe":[11],"embodied":[12],"navigation":[13],"in":[14,138,154],"human":[15],"environments":[16],"and":[17,21,33,50,142,148],"requires":[18],"both":[19],"visual":[20],"contextual":[22],"reasoning.":[23],"We":[24],"evaluate":[25],"three":[26,47],"opensource":[27],"vision-language":[28],"models":[29,64],"(VLMs)":[30],"(\\textit{InternVL},":[31],"\\textit{Qwen-VL},":[32],"\\textit{SmolVLM})":[34],"on":[35],"the":[36,67,90,124,128],"classification":[37,103],"of":[38,53,95,127],"robot":[40],"images":[41],"into":[42],"four":[43],"levels,":[45],"comparing":[46],"prompting":[48,147],"strategies":[49],"two":[51],"rounds":[52],"QLoRA":[54],"fine-tuning":[55,70,149],"against":[56],"stratified":[58],"random":[59],"baseline.":[60],"Without":[61],"fine-tuning,":[62],"all":[63],"perform":[65],"near":[66],"baseline,":[68],"while":[69],"yields":[71],"only":[72],"modest":[73],"overall":[74],"improvements.":[75],"However,":[76],"\\textit{Qwen-VL}":[77],"with":[78],"an":[79],"advanced":[80],"prompt":[81],"achieves":[82],"substantially":[83],"higher":[84],"recall":[85],"high-danger":[87,152],"cases":[88],"than":[89],"other":[91],"models.":[92,156],"An":[93],"analysis":[94],"person":[96],"localization":[97],"further":[98],"shows":[99],"that":[100,112,133],"correct":[101],"does":[104],"not":[105],"correspond":[106],"to":[107,123],"better":[108],"spatial":[109,143],"grounding,":[110,144],"indicating":[111],"model":[114],"may":[115],"produce":[116],"useful":[118],"safety":[119],"label":[120],"without":[121],"attending":[122],"relevant":[125],"region":[126],"scene.":[129],"These":[130],"results":[131],"show":[132],"current":[134],"VLMs":[135],"remain":[136],"limited":[137],"fine-grained":[139],"reasoning":[141],"although":[145],"targeted":[146],"can":[150],"improve":[151],"detection":[153],"selected":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-08-15T00:00:00"}