{"id":"https://openalex.org/W7204585340","doi":"https://doi.org/10.48550/arxiv.2608.26866","title":"Order Matters: A Chinese Multi-Panel Meme Benchmark for Vision-Language Reasoning","display_name":"Order Matters: A Chinese Multi-Panel Meme Benchmark for Vision-Language Reasoning","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204585340","doi":"https://doi.org/10.48550/arxiv.2608.26866"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.26866","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26866","pdf_url":"https://arxiv.org/pdf/2608.26866","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.26866","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148539105","display_name":"Haihan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]},{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Haihan","raw_affiliation_strings":["Dalian Maritime University , Dalian , China","Shanghai Maritime University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Maritime University , Dalian , China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Shanghai Maritime University , Shanghai , China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148549087","display_name":"Haihao Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]},{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Haihao","raw_affiliation_strings":["Dalian Maritime University , Dalian , China","Shanghai Maritime University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Maritime University , Dalian , China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Shanghai Maritime University , Shanghai , China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148488317","display_name":"Zhenfei Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Zhenfei","raw_affiliation_strings":["Shanghai Maritime University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Maritime University , Shanghai , China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015357873","display_name":"Jize Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Jize","raw_affiliation_strings":["Shanghai Maritime University , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Maritime University , Shanghai , China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042755676","display_name":"Yubo Xie","orcid":"https://orcid.org/0000-0002-7198-7506","observed_orcids":["https://orcid.org/0000-0002-7198-7506"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yubo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/internet-memes","display_name":"internet memes","score":0.9049999713897705},{"id":"https://openalex.org/keywords/chinese-social-media","display_name":"Chinese social media","score":0.6110000014305115},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7120000123977661},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.3059999942779541}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.728600025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940000057220459},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6480000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896000266075134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4729999899864197},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C2993167945","wikidata":"https://www.wikidata.org/wiki/Q196626","display_name":"Linguistic context","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2700999975204468}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.26866","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26866","pdf_url":"https://arxiv.org/pdf/2608.26866","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.2608.26866","doi":"https://doi.org/10.48550/arxiv.2608.26866","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26866","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:arXiv.org:2608.26866","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26866","pdf_url":"https://arxiv.org/pdf/2608.26866","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/W7204585340.pdf","grobid_xml":"https://content.openalex.org/works/W7204585340.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W4386185600","https://openalex.org/W4402713111","https://openalex.org/W4403081466","https://openalex.org/W4403853618","https://openalex.org/W4415798312","https://openalex.org/W4416036194","https://openalex.org/W4416037090","https://openalex.org/W6891822422","https://openalex.org/W7129045588"],"related_works":["https://openalex.org/W7171957623","https://openalex.org/W6929251851","https://openalex.org/W7125274205","https://openalex.org/W4416036718","https://openalex.org/W4402667011","https://openalex.org/W7208794472","https://openalex.org/W7212086610","https://openalex.org/W7166804489","https://openalex.org/W4414992335","https://openalex.org/W7160158573"],"abstract_inverted_index":{"Many":[0],"multimodal":[1,170],"tasks":[2],"depend":[3],"on":[4,14,32,49,122],"how":[5],"visual":[6],"elements":[7],"are":[8,21],"ordered":[9],"and":[10,37,90,103,112,131,178,191,196],"composed,":[11],"not":[12,148],"only":[13,188],"recognizing":[15],"them":[16],"in":[17,66,168],"isolation.":[18],"Internet":[19],"memes":[20],"a":[22,33,73,96,108,139,160,165,189],"compact":[23],"case":[24],"of":[25,152],"this":[26],"problem:":[27],"their":[28],"punchline":[29],"often":[30],"depends":[31],"constrained":[34],"reading":[35],"order":[36,153],"cross-panel":[38],"visual--textual":[39],"cues.":[40],"While":[41],"large":[42],"vision-language":[43],"models":[44],"(LVLMs)":[45],"show":[46],"strong":[47],"performance":[48],"single-image":[50],"understanding,":[51],"it":[52],"remains":[53],"unclear":[54],"whether":[55],"they":[56],"can":[57],"perform":[58],"sequence-aware":[59],"reasoning":[60],"over":[61],"structured":[62],"meme":[63,116],"layouts,":[64],"especially":[65],"Chinese":[67,74,115],"social":[68],"media.":[69],"We":[70,94,133],"introduce":[71],"CMPM,":[72],"Multi-Panel":[75],"Meme":[76],"benchmark":[77,134],"with":[78,119],"1,214":[79],"annotated":[80],"samples":[81],"covering":[82],"five":[83,123,135],"structural":[84],"types,":[85],"ordering":[86],"dependency,":[87],"panel-order":[88],"constraints,":[89],"optional":[91],"comment":[92,185],"context.":[93],"formulate":[95],"two-layer":[97],"evaluation:":[98],"Task1":[99],"probes":[100],"structure":[101],"typing":[102],"order-sensitive":[104,169],"panel":[105],"sequencing":[106],"(with":[107],"context":[109,186],"ablation":[110],"setting),":[111],"Task2":[113,172],"evaluates":[114],"explanation":[117],"generation":[118],"human":[120],"ratings":[121],"1-3":[124],"Likert":[125],"dimensions":[126],"(visual,":[127],"panel,":[128],"humor,":[129],"context,":[130],"faithfulness).":[132],"representative":[136],"LVLMs":[137],"under":[138],"unified":[140],"protocol.":[141],"Results":[142],"indicate":[143],"that":[144],"canonical-display":[145],"accuracy":[146,162],"is":[147],"by":[149],"itself":[150],"evidence":[151],"understanding:":[154],"the":[155,181],"primary":[156],"shuffled":[157],"condition":[158],"produces":[159],"sharp":[161],"drop,":[163],"revealing":[164],"persistent":[166],"gap":[167],"reasoning.":[171],"preferences":[173],"place":[174],"Gemini":[175],"3.1":[176],"Pro":[177],"GPT-5.5":[179],"above":[180],"open":[182],"models,":[183],"while":[184],"yields":[187],"small":[190],"mixed":[192],"Core4":[193],"gain.":[194],"Code":[195],"data":[197],"will":[198],"be":[199],"released":[200],"upon":[201],"acceptance.":[202]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-29T00:00:00"}