{"id":"https://openalex.org/W4416764938","doi":"https://doi.org/10.48550/arxiv.2511.19526","title":"Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models","display_name":"Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416764938","doi":"https://doi.org/10.48550/arxiv.2511.19526"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2511.19526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.19526","pdf_url":"https://arxiv.org/pdf/2511.19526","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.19526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lee, Jonathan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee, Jonathan","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103126299","display_name":"Xingrui Wang","orcid":"https://orcid.org/0000-0003-0480-2302","observed_orcids":["https://orcid.org/0000-0003-0480-2302"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xingrui","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101803193","display_name":"Jiawei Peng","orcid":"https://orcid.org/0000-0002-1608-3280","observed_orcids":["https://orcid.org/0000-0002-1608-3280"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng, Jiawei","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113273834","display_name":"Luoxin Ye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye, Luoxin","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063311054","display_name":"Zehan Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Zehan","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062036320","display_name":"Tiezheng Zhang","orcid":"https://orcid.org/0009-0001-9988-148X","observed_orcids":["https://orcid.org/0009-0001-9988-148X"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Tiezheng","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453525","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-4355-149X","observed_orcids":["https://orcid.org/0000-0002-4355-149X"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Tao","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070188278","display_name":"Wufei Ma","orcid":"https://orcid.org/0000-0002-4696-2833","observed_orcids":["https://orcid.org/0000-0002-4696-2833"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ma, Wufei","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033533946","display_name":"Si\u2010Yi Chen","orcid":"https://orcid.org/0000-0001-8076-0576","observed_orcids":["https://orcid.org/0000-0001-8076-0576"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Siyi","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063072430","display_name":"Yu-Cheng Chou","orcid":"https://orcid.org/0000-0002-9334-2899","observed_orcids":["https://orcid.org/0000-0002-9334-2899"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chou, Yu-Cheng","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025289100","display_name":"Prakhar Kaushik","orcid":"https://orcid.org/0000-0001-6449-8088","observed_orcids":["https://orcid.org/0000-0001-6449-8088"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik, Prakhar","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086706224","display_name":"Alan Yuille","orcid":"https://orcid.org/0000-0001-5207-9249","observed_orcids":["https://orcid.org/0000-0001-5207-9249"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuille, Alan","raw_affiliation_strings":["Johns Hopkins University https"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University https","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/scene-understanding","display_name":"scene understanding","score":0.6449999809265137},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9190000295639038},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.4869999885559082},{"id":"https://openalex.org/keywords/affordances","display_name":"affordances","score":0.7979999780654907},{"id":"https://openalex.org/keywords/material-properties","display_name":"material properties","score":0.6639999747276306},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.7459999918937683},{"id":"https://openalex.org/keywords/prompting","display_name":"prompting","score":0.6230000257492065},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.5860000252723694},{"id":"https://openalex.org/keywords/synthetic-scenes","display_name":"synthetic scenes","score":0.5180000066757202},{"id":"https://openalex.org/keywords/fine-grained-visual-understanding","display_name":"fine-grained visual understanding","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418000102043152},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7098000049591064},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6402000188827515},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4244999885559082},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3686000108718872},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.19526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.19526","pdf_url":"https://arxiv.org/pdf/2511.19526","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.2511.19526","doi":"https://doi.org/10.48550/arxiv.2511.19526","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.19526","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:2511.19526","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.19526","pdf_url":"https://arxiv.org/pdf/2511.19526","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416764938.pdf","grobid_xml":"https://content.openalex.org/works/W4416764938.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7211990150","https://openalex.org/W7124438147","https://openalex.org/W7162606446","https://openalex.org/W7117312522","https://openalex.org/W4415278944","https://openalex.org/W7213402754","https://openalex.org/W7124519356","https://openalex.org/W6948369034","https://openalex.org/W4416288921","https://openalex.org/W4416778099"],"abstract_inverted_index":{"We":[0,77,194],"propose":[1],"Perceptual":[2,68],"Taxonomy,":[3,69],"a":[4,70,94,175],"structured":[5,170,179],"process":[6],"of":[7,37,50,138,185,215],"scene":[8],"understanding":[9,181],"that":[10,145,188,197],"first":[11],"recognizes":[12],"objects":[13,80],"and":[14,27,53,104,122,182,209],"their":[15],"spatial":[16,118],"configurations,":[17],"then":[18],"infers":[19],"task-relevant":[20],"properties":[21],"such":[22],"as":[23],"material,":[24],"affordance,":[25],"function,":[26],"physical":[28],"attributes":[29],"to":[30,41,131,158],"support":[31],"goal-directed":[32],"reasoning.":[33,76,141],"While":[34],"this":[35,51,64],"form":[36],"reasoning":[38,168,200],"is":[39],"fundamental":[40],"human":[42],"cognition,":[43],"current":[44,186],"vision-language":[45,147],"benchmarks":[46],"lack":[47],"comprehensive":[48],"evaluation":[49],"ability":[52],"instead":[54],"focus":[55],"on":[56,151,161,191,207],"surface-level":[57],"recognition":[58,152],"or":[59],"image-text":[60],"alignment.":[61],"To":[62],"address":[63],"gap,":[65],"we":[66,92],"introduce":[67],"benchmark":[71,97,108],"for":[72],"physically":[73],"grounded":[74],"visual":[75,180],"annotate":[78],"3173":[79],"with":[81,98,126],"four":[82,114],"property":[83,120],"families":[84],"covering":[85],"84":[86],"fine-grained":[87],"attributes.":[88,171],"Using":[89],"these":[90],"annotations,":[91],"construct":[93],"multiple-choice":[95],"question":[96],"5802":[99],"images":[100],"across":[101,134],"both":[102],"synthetic":[103],"real":[105],"domains.":[106],"The":[107],"contains":[109],"28033":[110],"template-based":[111],"questions":[112,129],"spanning":[113],"types":[115],"(object":[116],"description,":[117],"reasoning,":[119],"matching,":[121],"taxonomy":[123,140],"reasoning),":[124],"along":[125],"50":[127],"expert-crafted":[128],"designed":[130],"evaluate":[132],"models":[133,148,187],"the":[135,183,213],"full":[136],"spectrum":[137],"perceptual":[139],"Experimental":[142],"results":[143],"show":[144,196],"leading":[146],"perform":[149],"well":[150],"tasks":[153],"but":[154],"degrade":[155],"by":[156],"10":[157],"20":[159],"percent":[160],"property-driven":[162],"questions,":[163,211],"especially":[164],"those":[165],"requiring":[166],"multi-step":[167],"over":[169],"These":[172],"findings":[173],"highlight":[174],"persistent":[176],"gap":[177],"in":[178],"limitations":[184],"rely":[189],"heavily":[190],"pattern":[192],"matching.":[193],"also":[195],"providing":[198],"in-context":[199],"examples":[201],"from":[202],"simulated":[203],"scenes":[204],"improves":[205],"performance":[206],"real-world":[208],"expert-curated":[210],"demonstrating":[212],"effectiveness":[214],"perceptual-taxonomy-guided":[216],"prompting.":[217]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-11-28T00:00:00"}
