{"id":"https://openalex.org/W4415314685","doi":"https://doi.org/10.48550/arxiv.2506.19579","title":"Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding","display_name":"Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4415314685","doi":"https://doi.org/10.48550/arxiv.2506.19579"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","doi":null,"is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tavella, F, Drinkwater, A & Cangelosi, A 2026, Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding. in Proceedings of the 2026 Conference Towards Autonomous Robotics Systems (TAROS) .","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.manchester.ac.uk/en/publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053569289","display_name":"Federico Tavella","orcid":"https://orcid.org/0000-0001-7640-2944","observed_orcids":["https://orcid.org/0000-0001-7640-2944"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tavella, Federico","raw_affiliation_strings":["Centre for Robotics and AI , University of Manchester , M13 9PL , Manchester , United Kingdom,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Robotics and AI , University of Manchester , M13 9PL , Manchester , United Kingdom,","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120049130","display_name":"Amber Drinkwater","orcid":"https://orcid.org/0009-0008-4896-2424","observed_orcids":["https://orcid.org/0009-0008-4896-2424"]},"institutions":[{"id":"https://openalex.org/I4405263009","display_name":"Amentum (United States)","ror":"https://ror.org/017art439","country_code":"FR","type":"company","lineage":["https://openalex.org/I4405263009"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Drinkwater, Amber","raw_affiliation_strings":["Amentum Clean Energy Ltd , Warrington , WA3 6XF , United Kingdom,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amentum Clean Energy Ltd , Warrington , WA3 6XF , United Kingdom,","institution_ids":["https://openalex.org/I4405263009"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091768977","display_name":"Angelo Cangelosi","orcid":"https://orcid.org/0000-0002-4709-2243","observed_orcids":["https://orcid.org/0000-0002-4709-2243"]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cangelosi, Angelo","raw_affiliation_strings":["Centre for Robotics and AI , University of Manchester , M13 9PL , Manchester , United Kingdom,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Robotics and AI , University of Manchester , M13 9PL , Manchester , United Kingdom,","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9765999913215637,"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":0.9765999913215637,"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":0.02250000089406967,"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":0.00019999999494757503,"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":0.9919999837875366},{"id":"https://openalex.org/keywords/domain-shift","display_name":"domain shift","score":0.8700000047683716},{"id":"https://openalex.org/keywords/3d-printed-objects","display_name":"3D printed objects","score":0.9290000200271606},{"id":"https://openalex.org/keywords/factual-grounding","display_name":"factual grounding","score":0.6389999985694885},{"id":"https://openalex.org/keywords/semantic-alignment","display_name":"semantic alignment","score":0.8119999766349792},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.6899999976158142},{"id":"https://openalex.org/keywords/embodied-agents","display_name":"embodied agents","score":0.7390000224113464},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.4300000071525574},{"id":"https://openalex.org/keywords/robot-manipulators","display_name":"robot manipulators","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9246000051498413},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8411999940872192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541999816894531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6191999912261963},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4936000108718872},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.392300009727478},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3919999897480011},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3650999963283539},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","doi":null,"is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tavella, F, Drinkwater, A & Cangelosi, A 2026, Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding. in Proceedings of the 2026 Conference Towards Autonomous Robotics Systems (TAROS) .","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2506.19579","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.19579","pdf_url":"https://arxiv.org/pdf/2506.19579","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.19579","doi":"https://doi.org/10.48550/arxiv.2506.19579","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.19579","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","doi":null,"is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/6ed9bcb1-4d7d-48af-b4e2-a008aaf4604b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tavella, F, Drinkwater, A & Cangelosi, A 2026, Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding. in Proceedings of the 2026 Conference Towards Autonomous Robotics Systems (TAROS) .","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415314685.pdf","grobid_xml":"https://content.openalex.org/works/W4415314685.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2936695845","https://openalex.org/W4385970122","https://openalex.org/W4388327601","https://openalex.org/W4401307635","https://openalex.org/W4402354046","https://openalex.org/W4402727516","https://openalex.org/W4402733597","https://openalex.org/W4415945598","https://openalex.org/W6947991961"],"related_works":["https://openalex.org/W4409483173","https://openalex.org/W7214198199","https://openalex.org/W4417276558","https://openalex.org/W7166647233","https://openalex.org/W7154508084","https://openalex.org/W4416387536","https://openalex.org/W4415058879","https://openalex.org/W7166796181","https://openalex.org/W4415198390","https://openalex.org/W7155380251"],"abstract_inverted_index":{"Robotic":[0],"scene":[1],"understanding":[2],"increasingly":[3],"relies":[4],"on":[5,89],"Vision-Language":[6],"Models":[7],"(VLMs)":[8],"to":[9,68,110],"generate":[10],"natural":[11],"language":[12],"descriptions":[13],"of":[14,60,127],"the":[15,125,135],"environment.":[16],"In":[17],"this":[18],"work,":[19],"we":[20],"systematically":[21],"evaluate":[22],"single-view":[23],"object":[24],"captioning":[25],"for":[26,131,137],"tabletop":[27],"scenes":[28],"captured":[29],"by":[30],"a":[31,35,58],"robotic":[32,146],"manipulator,":[33],"introducing":[34],"controlled":[36],"physical":[37,145],"domain":[38,112],"shift":[39],"that":[40,49,78,107],"contrasts":[41],"real-world":[42,83],"tools":[43],"with":[44],"geometrically":[45],"similar":[46],"3D-printed":[47,90],"counterparts":[48],"differ":[50],"in":[51,102,144],"texture,":[52],"colour,":[53],"and":[54,72,134,141],"material.":[55],"We":[56,97],"benchmark":[57],"suite":[59],"state-of-the-art,":[61],"locally":[62],"deployable":[63],"VLMs":[64,80],"across":[65],"multiple":[66],"metrics":[67],"assess":[69],"semantic":[70],"alignment":[71],"factual":[73],"grounding.":[74],"Our":[75],"results":[76],"demonstrate":[77],"while":[79],"describe":[81],"common":[82],"objects":[84],"effectively,":[85],"performance":[86],"degrades":[87],"markedly":[88],"items":[91],"despite":[92],"their":[93],"structurally":[94],"familiar":[95],"forms.":[96],"further":[98],"expose":[99],"critical":[100],"vulnerabilities":[101],"standard":[103],"evaluation":[104,142],"metrics,":[105],"showing":[106],"some":[108],"fail":[109],"detect":[111],"shifts":[113],"entirely":[114],"or":[115],"reward":[116],"fluent":[117],"but":[118],"factually":[119],"incorrect":[120],"captions.":[121],"These":[122],"findings":[123],"highlight":[124],"limitations":[126],"deploying":[128],"foundation":[129],"models":[130],"embodied":[132],"agents":[133],"need":[136],"more":[138],"robust":[139],"architectures":[140],"protocols":[143],"applications.":[147]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-18T00:00:00"}