{"id":"https://openalex.org/W7204880573","doi":"https://doi.org/10.18653/2026.findings-emnlp.163","title":"DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection","display_name":"DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204880573","doi":"https://doi.org/10.18653/2026.findings-emnlp.163"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.163","doi":"https://doi.org/10.18653/2026.findings-emnlp.163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.163","pdf_url":"https://aclanthology.org/2026.findings-emnlp.163.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.163.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122762722","display_name":"yuyang hong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyang Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123856988","display_name":"Jinhui Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhui Guo","raw_affiliation_strings":["Alibaba Token Hub , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Token Hub , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148928911","display_name":"Jiaqi Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Gu","raw_affiliation_strings":["Alibaba Token Hub , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Token Hub , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148938975","display_name":"Lubin Fan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lubin Fan","raw_affiliation_strings":["Alibaba Token Hub , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Token Hub , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148859235","display_name":"Ruixiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiang Wang","raw_affiliation_strings":["MAIS , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAIS , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101713583","display_name":"Kun Ding","orcid":"https://orcid.org/0000-0002-2256-8815","observed_orcids":["https://orcid.org/0000-0002-2256-8815","https://orcid.org/0000-0003-0657-1608"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Ding","raw_affiliation_strings":["MAIS , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAIS , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132712211","display_name":"Yue Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["Alibaba Token Hub , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Token Hub , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125684404","display_name":"Shiming Xiang","orcid":"https://orcid.org/0000-0002-2089-9733","observed_orcids":["https://orcid.org/0000-0002-2089-9733"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["MAIS , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MAIS , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148840127","display_name":"Jieping Ye","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieping Ye","raw_affiliation_strings":["Alibaba Token Hub , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Token Hub , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70563865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3452","last_page":"3472"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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":0.0,"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/visual-instruction-tuning","display_name":"visual instruction tuning","score":0.9020000100135803},{"id":"https://openalex.org/keywords/instruction-selection","display_name":"instruction selection","score":0.7089999914169312},{"id":"https://openalex.org/keywords/dataset-selection","display_name":"data selection","score":0.5889999866485596},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7699999809265137},{"id":"https://openalex.org/keywords/data-consistency","display_name":"data consistency","score":0.3919999897480011},{"id":"https://openalex.org/keywords/vision-language-alignment","display_name":"vision-language alignment","score":0.5960000157356262},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.6330000162124634}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.8172000050544739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153000235557556},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.6326000094413757},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.5760999917984009},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48170000314712524},{"id":"https://openalex.org/C122377713","wikidata":"https://www.wikidata.org/wiki/Q4422799","display_name":"Weak consistency","level":4,"score":0.4480000138282776},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C82029504","wikidata":"https://www.wikidata.org/wiki/Q4373882","display_name":"Sequential consistency","level":4,"score":0.27950000762939453},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2694000005722046}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.163","doi":"https://doi.org/10.18653/2026.findings-emnlp.163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.163","pdf_url":"https://aclanthology.org/2026.findings-emnlp.163.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.30209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.30209","pdf_url":"https://arxiv.org/pdf/2608.30209","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.2608.30209","doi":"https://doi.org/10.48550/arxiv.2608.30209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.30209","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":"doi:10.18653/2026.findings-emnlp.163","doi":"https://doi.org/10.18653/2026.findings-emnlp.163","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.163","pdf_url":"https://aclanthology.org/2026.findings-emnlp.163.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204880573.pdf","grobid_xml":"https://content.openalex.org/works/W7204880573.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415538849","https://openalex.org/W7125907692","https://openalex.org/W4402670838","https://openalex.org/W7128807805","https://openalex.org/W4409045915","https://openalex.org/W4405382875","https://openalex.org/W4406032133","https://openalex.org/W4413145959","https://openalex.org/W4416054653","https://openalex.org/W4402670537"],"abstract_inverted_index":{"Visual":[0,75],"instruction":[1,160,167],"tuning":[2],"is":[3],"crucial":[4],"for":[5],"advancing":[6],"the":[7,46,67,80,97,115,152,164,177],"vision-language":[8],"alignment":[9,81],"and":[10,85,87,121,141],"instruction-following":[11],"capabilities":[12],"of":[13,72,151,176,185],"Vision-Language":[14],"Models":[15],"(VLMs).However,":[16],"identifying":[17],"optimal":[18],"subsets":[19],"under":[20,125],"a":[21,30,61,157],"fixed":[22],"ratio":[23],"constraint":[24],"from":[25],"rapidly":[26],"expanding":[27],"datasets":[28],"remains":[29],"significant":[31],"bottleneck.While":[32],"existing":[33],"methods":[34,136],"largely":[35],"depend":[36],"on":[37],"distribution":[38],"diversity":[39,124],"or":[40],"heuristic":[41],"filtering,":[42],"they":[43],"often":[44],"overlook":[45],"internal":[47],"coherence":[48,94],"within":[49],"individual":[50],"samples.To":[51],"bridge":[52],"this":[53],"gap,":[54],"we":[55,101],"propose":[56],"Data":[57,103],"Intrinsic":[58,104],"Consistency":[59,77,90,105],"(DIC),":[60],"self-scoring":[62],"metric":[63],"designed":[64],"to":[65,96,170],"quantify":[66],"sample-level":[68],"inter-component":[69],"consistency.DIC":[70],"consists":[71],"two":[73],"modules:":[74],"Information":[76,89],"(VIC),":[78],"evaluating":[79],"between":[82,117],"visual":[83,166],"content":[84],"instructions,":[86],"Response":[88],"(RIC),":[91],"assessing":[92],"response":[93],"relative":[95],"instruction.Building":[98],"upon":[99],"DIC,":[100],"introduce":[102],"Selection":[106],"(DICS),":[107],"an":[108],"adaptive":[109],"data":[110,127],"selection":[111,168],"method":[112],"that":[113,131,162],"optimizes":[114],"trade-off":[116],"high":[118],"intrasample":[119],"consistency":[120],"global":[122],"distributional":[123],"varying":[126],"budgets.Extensive":[128],"experiments":[129],"demonstrate":[130],"DICS":[132,173],"consistently":[133],"outperforms":[134],"state-of-the-art":[135],"across":[137],"diverse":[138],"dataset":[139],"scales":[140],"model":[142],"architectures,":[143],"surpassing":[144],"full-dataset":[145],"fine-tuning":[146],"while":[147],"using":[148,181],"only":[149],"25%":[150,184],"LLaVA-1.5-665Kdata.We":[153],"further":[154],"curate":[155],"DICS-6M,":[156],"6Msample":[158],"multi-modal":[159],"corpus":[161],"enables":[163],"largest-scale":[165],"study":[169],"date;":[171],"remarkably,":[172],"reaches":[174],"94.52%":[175],"official":[178],"InternVL3-8B-Instruct":[179],"performance":[180],"less":[182],"than":[183],"its":[186],"reported":[187],"training":[188],"data.":[189]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-02T00:00:00"}