{"id":"https://openalex.org/W4417328209","doi":"https://doi.org/10.48550/arxiv.2510.21501","title":"GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs","display_name":"GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4417328209","doi":"https://doi.org/10.48550/arxiv.2510.21501"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2510.21501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21501","pdf_url":"https://arxiv.org/pdf/2510.21501","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.21501","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080373270","display_name":"Guanghao Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Guanghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031734772","display_name":"Bowen Shi","orcid":"https://orcid.org/0000-0003-0931-3866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111983309","display_name":"Mingxing Xu","orcid":"https://orcid.org/0009-0000-3878-315X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Mingxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014042408","display_name":"Ruoyu Sun","orcid":"https://orcid.org/0009-0002-6052-0051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Ruoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083795433","display_name":"Peisen Zhao","orcid":"https://orcid.org/0000-0002-3787-193X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Peisen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433022","display_name":"Zhibo Zhang","orcid":"https://orcid.org/0000-0003-1186-4990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045342512","display_name":"Wenrui Dai","orcid":"https://orcid.org/0000-0003-2522-5778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Wenrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016006337","display_name":"Junni Zou","orcid":"https://orcid.org/0000-0002-9694-9880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Junni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Hongkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667567","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0002-0092-6474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719124","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0001-8595-8979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Qi","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":0.9430999755859375,"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":0.9430999755859375,"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/T10028","display_name":"Topic Modeling","score":0.00989999994635582,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007899999618530273,"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/exploit","display_name":"Exploit","score":0.5656999945640564},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.550000011920929},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4830999970436096},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44670000672340393},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.428600013256073},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3968000113964081},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.38749998807907104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37720000743865967},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3698999881744385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6686000227928162},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.21501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21501","pdf_url":"https://arxiv.org/pdf/2510.21501","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.2510.21501","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21501","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.21501","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21501","pdf_url":"https://arxiv.org/pdf/2510.21501","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0,72],"encoders":[1,28,207],"are":[2,40],"indispensable":[3],"for":[4,172],"allowing":[5],"impressive":[6],"performance":[7],"of":[8,50,58,155],"Multi-modal":[9],"Large":[10,83],"Language":[11,84],"Models":[12,85],"(MLLMs)":[13],"in":[14,42,159,174],"vision":[15,27,157,167,191,206],"language":[16],"tasks":[17],"such":[18],"as":[19],"visual":[20,153],"question":[21],"answering":[22],"and":[23,55,101,162,170,208,225],"reasoning.":[24],"However,":[25],"existing":[26,205],"focus":[29],"on":[30,135,189,220],"global":[31],"image":[32],"representations":[33],"but":[34],"overlook":[35],"fine-grained":[36,76,133,141,221],"regional":[37,196],"analysis.":[38],"They":[39],"limited":[41],"fine":[43,51,60,116],"grained":[44,52,61,117],"perception":[45],"due":[46],"to":[47,82,112,131,145,147,150,165,193,212],"the":[48,56,140,156,160,175,190],"scarcity":[49],"annotated":[53],"data":[54],"lack":[57],"a":[59,70,96,122,127,180],"pre-training":[62],"paradigm.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,120],"propose":[68],"GranViT,":[69],"novel":[71],"Transformer":[73],"that":[74,184,202],"integrates":[75],"feature":[77,168],"extraction":[78],"with":[79,105,126],"semantic":[80],"alignment":[81],"(LLMs)":[86],"via":[87],"region":[88],"level":[89],"autoregressive":[90],"training.":[91],"We":[92,137,177],"first":[93],"construct":[94],"Gran-29M,":[95],"dataset":[97],"comprising":[98],"2million":[99],"natural":[100],"OCR":[102,226],"images":[103],"paired":[104],"over":[106],"180":[107],"million":[108],"high-quality":[109],"region-level":[110],"annotations,":[111],"enable":[113],"large":[114],"scale":[115],"pretraining.":[118],"Consequently,":[119],"develop":[121],"pretraining-adaptation":[123],"framework":[124],"along":[125],"self":[128,181],"distillation":[129,182],"mechanism":[130,183],"train":[132],"GranViT":[134,203],"Gran-29M.":[136],"sufficiently":[138],"exploit":[139],"annotations":[142],"from":[143],"Gran-29M":[144],"resort":[146],"bounding-box-to-caption":[148],"regression":[149,164],"enhance":[151],"localized":[152],"representation":[154],"encoder":[158,192],"pretraining":[161],"caption-to-bounding-box":[163],"improve":[166],"utilization":[169],"localization":[171,187],"LLM":[173],"adaptation.":[176],"further":[178],"incorporate":[179],"imposes":[185],"explicit":[186],"constraints":[188],"strengthen":[194],"its":[195],"reasoning":[197],"capability.":[198],"Extensive":[199],"experiments":[200],"show":[201],"surpasses":[204],"attains":[209],"strong":[210],"transferability":[211],"varying":[213],"LLMs.":[214],"Remarkably,":[215],"it":[216],"achieves":[217],"state-of-the-art":[218],"results":[219],"recognition,":[222],"multimodal":[223],"VQA,":[224],"understanding.":[227]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-28T00:00:00"}