{"id":"https://openalex.org/W7162402624","doi":"https://doi.org/10.48550/arxiv.2605.24799","title":"Divide-and-Conquer Inference for Large-Scale Visual Recognition with Multimodal Large Language Models","display_name":"Divide-and-Conquer Inference for Large-Scale Visual Recognition with Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162402624","doi":"https://doi.org/10.48550/arxiv.2605.24799"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24799","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.24799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039638579","display_name":"Zhipeng Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zhipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136997215","display_name":"Jiaqi Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137037489","display_name":"Feng Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136993923","display_name":"Qiufeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qiufeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137070555","display_name":"Yikang Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Yikang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137055608","display_name":"Dawei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Dawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137071603","display_name":"Xihang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137005483","display_name":"Qian Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7573000192642212,"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":0.7573000192642212,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06159999966621399,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.02669999934732914,"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/inference","display_name":"Inference","score":0.6414999961853027},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5697000026702881},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48240000009536743},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.45019999146461487},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38429999351501465},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.3765999972820282},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.37139999866485596},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.3474000096321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175999879837036},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5791000127792358},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5697000026702881},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3400999903678894},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24799","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":"doi:10.48550/arxiv.2605.24799","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24799","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"demonstrated":[6],"strong":[7],"capabilities":[8],"across":[9],"a":[10,34,57,82,99,123,160,216],"wide":[11],"range":[12],"of":[13,230],"vision":[14],"language":[15],"tasks.":[16],"However,":[17],"when":[18,86],"applied":[19],"to":[20,80,127,139,201],"large":[21,176],"scale":[22,177],"image":[23],"classification,":[24],"their":[25],"performance":[26],"degrades":[27],"significantly":[28],"as":[29,38,185],"the":[30,61,66,77,129,136,147,227],"label":[31],"space":[32],"expands":[33],"phenomenon":[35],"we":[36,50,94],"define":[37],"Performance":[39],"Collapse":[40],"in":[41,152,175,232],"Long":[42],"Sequence":[43],"Recognition.":[44],"Through":[45],"an":[46,222],"information":[47,63],"theoretic":[48],"analysis,":[49],"reveal":[51],"that":[52,190],"this":[53],"collapse":[54],"stems":[55],"from":[56],"fundamental":[58],"conflict":[59],"between":[60],"escalating":[62],"entropy":[64],"and":[65,70,121,142,171,187],"prominent":[67],"attention":[68,73],"dilution":[69,150],"decay":[71],"within":[72],"mechanisms,":[74],"which":[75],"impairs":[76],"model's":[78],"ability":[79],"maintain":[81],"sufficient":[83],"signal-to-noise":[84],"ratio":[85,141],"processing":[87],"extremely":[88],"long":[89],"prompts.":[90],"To":[91],"mitigate":[92],"this,":[93],"propose":[95],"Divide-and-Conquer":[96],"Inference":[97],"(DCI),":[98],"novel":[100],"test-time":[101],"scaling":[102,169,226],"strategy":[103],"for":[104,225],"visual":[105],"recognition":[106],"with":[107],"MLLMs.":[108],"DCI":[109,165,191,220],"recursively":[110],"decomposes":[111],"complex":[112],"global":[113],"classification":[114,178,194],"tasks":[115],"into":[116],"multiple":[117],"simpler,":[118],"localized":[119],"subproblems":[120],"employs":[122],"dynamic":[124],"pruning":[125],"mechanism":[126],"compress":[128],"search":[130],"space.":[131],"This":[132,196],"method":[133],"effectively":[134],"improves":[135,193],"local":[137],"signal":[138],"noise":[140],"model":[143],"accuracy":[144],"by":[145],"mitigating":[146],"inherent":[148],"weight":[149],"issues":[151],"long-sequence":[153],"inference.":[154],"Moreover,":[155],"while":[156],"traditional":[157],"self-attention":[158],"incurs":[159],"prohibitive":[161],"quadratic":[162],"computational":[163],"complexity,":[164],"achieves":[166],"more":[167],"favorable":[168],"behavior":[170],"substantially":[172],"accelerates":[173],"inference":[174],"scenarios.":[179,234],"Extensive":[180],"experiments":[181],"on":[182],"benchmarks":[183],"such":[184],"ImageNet-1K":[186],"ImageNet-21K":[188],"demonstrate":[189],"consistently":[192],"accuracy.":[195],"enables":[197],"lightweight":[198],"open-source":[199],"models":[200],"rival":[202],"or":[203,213],"even":[204],"surpass":[205],"frontier":[206],"closed-source":[207],"giants":[208],"without":[209],"any":[210],"additional":[211],"training":[212],"fine-tuning.":[214],"As":[215],"model-agnostic,":[217],"plug-and-play":[218],"paradigm,":[219],"offers":[221],"efficient":[223],"approach":[224],"inferential":[228],"precision":[229],"MLLMs":[231],"large-scale":[233]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-27T00:00:00"}