{"id":"https://openalex.org/W4415538208","doi":"https://doi.org/10.1145/3746027.3762000","title":"MIRAGE25: ACM MM25 Multimodal Interleaved Reasoning and Generation Challenge","display_name":"MIRAGE25: ACM MM25 Multimodal Interleaved Reasoning and Generation Challenge","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538208","doi":"https://doi.org/10.1145/3746027.3762000"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091714064","display_name":"Dong Chen","orcid":"https://orcid.org/0000-0002-4859-1757"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Chen","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4859-1757","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Gao","orcid":"https://orcid.org/0000-0003-0144-2815"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0144-2815","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101249701","display_name":"Zhengqing Hu","orcid":"https://orcid.org/0009-0008-7293-2735"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqing Hu","raw_affiliation_strings":["Zhengzhou University, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-7293-2735","affiliations":[{"raw_affiliation_string":"Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091714064"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28736283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13797","last_page":"13798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/multimodal-interaction","display_name":"Multimodal interaction","score":0.5101000070571899},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.42649999260902405},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4235000014305115},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730000019073486},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C4441509","wikidata":"https://www.wikidata.org/wiki/Q6418787","display_name":"Multimodal therapy","level":2,"score":0.24369999766349792}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3762000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2059552065","https://openalex.org/W2552837936","https://openalex.org/W2746097825","https://openalex.org/W2962931774","https://openalex.org/W2963047368","https://openalex.org/W2964211610","https://openalex.org/W2986685865","https://openalex.org/W3004268082","https://openalex.org/W3034758614","https://openalex.org/W3035574168","https://openalex.org/W3087871082","https://openalex.org/W3120043490","https://openalex.org/W3173998882","https://openalex.org/W4214478598"],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"the":[2,46,105],"MIRAGE":[3,47,106],"Challenge,":[4],"a":[5],"comprehensive":[6],"benchmark":[7],"for":[8],"multimodal":[9,33,117,135],"interleaved":[10],"reasoning":[11,60],"and":[12,28,39,61,86,100,119,133,139],"generation,":[13],"to":[14,21,25,71],"ACM":[15],"MM":[16,109],"2025.":[17],"The":[18,41,77],"challenge":[19,42,78],"aims":[20],"evaluate":[22],"models'":[23],"abilities":[24],"both":[26,131],"understand":[27],"generate":[29],"content":[30],"from":[31,69],"complex,":[32],"contexts":[34],"consisting":[35],"of":[36,130],"interlinked":[37],"images":[38],"text.":[40],"is":[43],"accompanied":[44],"by":[45],"Dataset,":[48],"comprising":[49],"263.7K":[50],"high-quality":[51],"instruction-response":[52],"pairs":[53,64],"across":[54],"35":[55],"tasks":[56],"in":[57,115,123],"two":[58],"tracks:":[59],"generation.":[62],"These":[63],"span":[65],"20":[66],"diverse":[67],"scenarios,":[68],"surveillance":[70],"artistic":[72],"creation,":[73],"ensuring":[74],"broad":[75,121],"coverage.":[76],"includes":[79],"seven":[80],"major":[81],"categories:":[82],"Multi-Image":[83,92],"Reasoning,":[84],"Document":[85],"Knowledge-Based":[87],"Understanding,":[88],"Interactive":[89],"Multi-Modal":[90],"Communication,":[91],"Discrimination,":[93],"Sequential":[94],"Visual":[95,101],"Generation,":[96],"Material-based":[97],"Image":[98],"Coloring,":[99],"Reference":[102],"Customization.":[103],"Hosting":[104],"Challenge":[107,137],"at":[108,144],"2025":[110],"will":[111],"drive":[112],"significant":[113],"progress":[114],"unified":[116],"learning":[118],"inspire":[120],"involvement":[122],"developing":[124],"more":[125],"versatile":[126],"AI":[127],"systems":[128],"capable":[129],"understanding":[132],"generating":[134],"content.":[136],"details":[138],"participation":[140],"information":[141],"are":[142],"available":[143],"https://mm25mirage.github.io/mirage/.":[145]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}
