{"id":"https://openalex.org/W7126231383","doi":"https://doi.org/10.48550/arxiv.2601.22150","title":"Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions","display_name":"Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126231383","doi":"https://doi.org/10.48550/arxiv.2601.22150"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.22150","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063311546","display_name":"Xiaoxiao Sun","orcid":"https://orcid.org/0000-0002-0823-8713"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sun, Xiaoxiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416804","display_name":"Yanyan Liu","orcid":"https://orcid.org/0000-0001-8488-5480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mingyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124422083","display_name":"Kun yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Kun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124443555","display_name":"Min Woo Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Min Woo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001083419","display_name":"Mark Endo","orcid":"https://orcid.org/0000-0003-3218-5807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Endo, Mark","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124347906","display_name":"Shengguang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shengguang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124356352","display_name":"Changlin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Changlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124361179","display_name":"Yuhui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124418931","display_name":"Zeyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zeyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124352468","display_name":"Serena Yeung-Levy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeung-Levy, Serena","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5063311546"],"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/T11094","display_name":"Face Recognition and Perception","score":0.27410000562667847,"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"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.27410000562667847,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2603999972343445,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04170000180602074,"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/illusion","display_name":"Illusion","score":0.7110999822616577},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5924000144004822},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5796999931335449},{"id":"https://openalex.org/keywords/optical-illusion","display_name":"Optical illusion","score":0.5522000193595886},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.5098000168800354},{"id":"https://openalex.org/keywords/fixation","display_name":"Fixation (population genetics)","score":0.4657000005245209},{"id":"https://openalex.org/keywords/visual-memory","display_name":"Visual memory","score":0.4465000033378601}],"concepts":[{"id":"https://openalex.org/C184047640","wikidata":"https://www.wikidata.org/wiki/Q182593","display_name":"Illusion","level":2,"score":0.7110999822616577},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.6930000185966492},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.6640999913215637},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C139793654","wikidata":"https://www.wikidata.org/wiki/Q174923","display_name":"Optical illusion","level":3,"score":0.5522000193595886},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.5098000168800354},{"id":"https://openalex.org/C146249460","wikidata":"https://www.wikidata.org/wiki/Q2914991","display_name":"Fixation (population genetics)","level":3,"score":0.4657000005245209},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.4465000033378601},{"id":"https://openalex.org/C15123163","wikidata":"https://www.wikidata.org/wiki/Q500096","display_name":"Psychophysics","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C165520287","wikidata":"https://www.wikidata.org/wiki/Q18652","display_name":"Iconic memory","level":5,"score":0.28200000524520874},{"id":"https://openalex.org/C164280684","wikidata":"https://www.wikidata.org/wiki/Q5529040","display_name":"Gaze-contingency paradigm","level":4,"score":0.2752000093460083},{"id":"https://openalex.org/C101097943","wikidata":"https://www.wikidata.org/wiki/Q5176983","display_name":"Counterintuitive","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C2776058522","wikidata":"https://www.wikidata.org/wiki/Q2364768","display_name":"Visual field","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.22150","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.22150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.22150","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.22150","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5296949744224548}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(VLMs)":[3],"often":[4],"answer":[5],"classic":[6],"visual":[7,27,41,80,170],"illusions":[8],"\"correctly\"":[9],"on":[10,98],"original":[11],"images,":[12],"yet":[13],"persist":[14],"with":[15,75],"the":[16,26,55],"same":[17],"responses":[18],"when":[19],"illusion":[20,83,114],"factors":[21],"are":[22,175],"inverted,":[23],"even":[24],"though":[25],"change":[28],"is":[29],"obvious":[30],"to":[31,64,168],"humans.":[32],"This":[33],"raises":[34],"a":[35,71,134],"fundamental":[36],"question:":[37],"do":[38],"VLMs":[39],"perceive":[40],"changes":[42],"or":[43],"merely":[44],"recall":[45],"memorized":[46],"patterns?":[47],"While":[48],"several":[49],"studies":[50],"have":[51],"noted":[52],"this":[53,67],"phenomenon,":[54],"underlying":[56],"causes":[57,131],"remain":[58],"unclear.":[59],"To":[60],"move":[61],"from":[62,90,129],"observations":[63],"systematic":[65],"understanding,":[66],"paper":[68],"introduces":[69],"VI-Probe,":[70],"controllable":[72],"visual-illusion":[73],"framework":[74],"graded":[76],"perturbations":[77],"and":[78,104,112,158,166,173],"matched":[79,118],"controls":[81],"(without":[82],"inducer)":[84],"that":[85,96,125,162],"disentangles":[86],"visually":[87],"grounded":[88],"perception":[89],"language-driven":[91],"recall.":[92],"Unlike":[93],"prior":[94],"work":[95],"focuses":[97],"averaged":[99],"accuracy,":[100],"we":[101],"measure":[102],"stability":[103],"sensitivity":[105,167],"using":[106],"Polarity-Flip":[107],"Consistency,":[108],"Template":[109],"Fixation":[110],"Index,":[111],"an":[113],"multiplier":[115],"normalized":[116],"against":[117],"controls.":[119],"Experiments":[120],"across":[121],"different":[122],"families":[123],"reveal":[124],"response":[126],"persistence":[127],"arises":[128],"heterogeneous":[130],"rather":[132],"than":[133],"single":[135],"mechanism.":[136],"For":[137],"instance,":[138],"GPT-5":[139],"exhibits":[140],"memory":[141],"override,":[142],"Claude-Opus-4.1":[143],"shows":[144],"perception-memory":[145],"competition,":[146],"while":[147],"Qwen":[148],"variants":[149],"suggest":[150],"visual-processing":[151],"limits.":[152],"Our":[153],"findings":[154],"challenge":[155],"single-cause":[156],"views":[157],"motivate":[159],"probing-based":[160],"evaluation":[161],"measures":[163],"both":[164],"knowledge":[165],"controlled":[169],"change.":[171],"Data":[172],"code":[174],"available":[176],"at":[177],"https://sites.google.com/view/vi-probe/":[178]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-01T00:00:00"}
