{"id":"https://openalex.org/W7160207210","doi":"https://doi.org/10.1109/iccv51701.2025.00202","title":"LlaVA-CoT: Let Vision Language Models Reason Step-By-Step","display_name":"LlaVA-CoT: Let Vision Language Models Reason Step-By-Step","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160207210","doi":"https://doi.org/10.1109/iccv51701.2025.00202"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.00202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110957712","display_name":"Guowei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guowei Xu","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135263235","display_name":"Peng Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jin","raw_affiliation_strings":["Shenzhen Graduate School, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072643715","display_name":"Ziang Wu","orcid":"https://orcid.org/0009-0005-6203-4550"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziang Wu","raw_affiliation_strings":["Shenzhen Graduate School, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065859286","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-9198-3951"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":["Shenzhen Graduate School, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068034476","display_name":"Yibing Song","orcid":"https://orcid.org/0000-0003-3667-531X"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Yibing Song","raw_affiliation_strings":["DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135205046","display_name":"Lichao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["Computer Science and Engineering, Lehigh University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129742071","display_name":"Li Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yuan","raw_affiliation_strings":["Shenzhen Graduate School, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2087","last_page":"2098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4124999940395355,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.4124999940395355,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.257099986076355,"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":0.04529999941587448,"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/natural-language","display_name":"Natural language","score":0.33180001378059387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2872999906539917},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.27309998869895935},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.25060001015663147}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47679999470710754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2930999994277954},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.00202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44865626096725464}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2307512708","https://openalex.org/W2561715562","https://openalex.org/W2963115613","https://openalex.org/W3037763555","https://openalex.org/W3120043490","https://openalex.org/W3159959439","https://openalex.org/W4285255856","https://openalex.org/W4308784724","https://openalex.org/W4312846625","https://openalex.org/W4366548330","https://openalex.org/W4378805076","https://openalex.org/W4385571011","https://openalex.org/W4386065691","https://openalex.org/W4389523706","https://openalex.org/W4392326400","https://openalex.org/W4393156643","https://openalex.org/W4402671875","https://openalex.org/W4402713111","https://openalex.org/W4402726948","https://openalex.org/W4402727885","https://openalex.org/W4402754165","https://openalex.org/W4402754220","https://openalex.org/W4403081466","https://openalex.org/W4403706679","https://openalex.org/W4403791888","https://openalex.org/W4404575065","https://openalex.org/W4411119825","https://openalex.org/W4411725552","https://openalex.org/W4412886751","https://openalex.org/W4415798312","https://openalex.org/W7133193597","https://openalex.org/W7133224126","https://openalex.org/W7133230326"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2026-05-05T00:00:00"}