{"id":"https://openalex.org/W4417534267","doi":"https://doi.org/10.1109/wacv61042.2026.00166","title":"The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs","display_name":"The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4417534267","doi":"https://doi.org/10.1109/wacv61042.2026.00166"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.15949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tejas Anvekar","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tejas Anvekar","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fenil Bardoliya","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fenil Bardoliya","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pavan K. Turaga","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan K. Turaga","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chitta Baral","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitta Baral","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":null,"display_name":"Vivek Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Gupta","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03521811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1653","last_page":"1663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.37369999289512634,"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":0.37369999289512634,"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/T11448","display_name":"Face recognition and analysis","score":0.20059999823570251,"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/T11094","display_name":"Face Recognition and Perception","score":0.18700000643730164,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.629800021648407},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6251999735832214},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.4876999855041504},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.438400000333786},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4244999885559082},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.41839998960494995},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.38940000534057617},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.37380000948905945},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.34450000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6470000147819519},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.629800021648407},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805000066757202},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.38940000534057617},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2776207355","wikidata":"https://www.wikidata.org/wiki/Q191035","display_name":"Sarcasm","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.15949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.15949","pdf_url":"https://arxiv.org/pdf/2512.15949","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.15949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.15949","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":"pmh:oai:arXiv.org:2512.15949","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.15949","pdf_url":"https://arxiv.org/pdf/2512.15949","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309835","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"multimodal":[3],"large":[4],"language":[5,26],"models":[6],"(MLLMs)":[7],"have":[8],"yielded":[9],"increasingly":[10],"powerful":[11],"models,":[12],"yet":[13],"their":[14],"perceptual":[15,146],"capacities":[16],"remain":[17],"poorly":[18],"characterized.":[19],"In":[20],"practice,":[21],"most":[22],"model":[23],"families":[24],"scale":[25],"component":[27],"while":[28],"reusing":[29],"nearly":[30],"identical":[31],"vision":[32,85],"encoders":[33],"(e.g.,":[34],"Qwen2.5-VL":[35],"3B/7B/72B),":[36],"which":[37,107],"raises":[38],"pivotal":[39],"concerns":[40],"about":[41],"whether":[42],"progress":[43],"reflects":[44],"genuine":[45],"visual":[46,110],"grounding":[47,147],"or":[48],"reliance":[49],"on":[50],"internet-scale":[51],"textual":[52],"world":[53],"knowledge.":[54],"Existing":[55],"evaluation":[56],"methods":[57],"emphasize":[58],"end-task":[59],"accuracy,":[60],"overlooking":[61],"robustness,":[62],"attribution":[63],"fidelity,":[64],"and":[65,91,104,121,128,148,160,164],"reasoning":[66],"under":[67,151],"controlled":[68],"perturbations.":[69],"We":[70],"present":[71],"The":[72,132],"Perceptual":[73,133],"Observatory,":[74],"a":[75,154],"framework":[76],"that":[77],"characterizes":[78],"MLLMs":[79,144],"across":[80],"verticals":[81],"like:":[82],"(i)":[83],"simple":[84],"tasks,":[86],"such":[87],"as":[88],"face":[89],"matching":[90],"text-in-vision":[92],"comprehension":[93],"capabilities;":[94],"(ii)":[95],"local-to-global":[96],"understanding,":[97],"encompassing":[98],"image":[99],"matching,":[100],"grid":[101],"pointing":[102],"game,":[103],"attribute":[105],"localization,":[106],"tests":[108],"general":[109],"grounding.":[111],"Each":[112],"vertical":[113],"is":[114],"instantiated":[115],"with":[116],"ground-truth":[117],"datasets":[118],"of":[119,162],"faces":[120],"words,":[122],"systematically":[123],"perturbed":[124],"through":[125],"pixel-based":[126],"augmentations":[127],"diffusion-based":[129],"stylized":[130],"illusions.":[131],"Observatory":[134],"moves":[135],"beyond":[136],"leaderboard":[137],"accuracy":[138],"to":[139],"yield":[140],"insights":[141],"into":[142],"how":[143],"preserve":[145],"relational":[149],"structure":[150],"perturbations,":[152],"providing":[153],"principled":[155],"foundation":[156],"for":[157],"analyzing":[158],"strengths":[159],"weaknesses":[161],"current":[163],"future":[165],"models.":[166]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-21T00:00:00"}