{"id":"https://openalex.org/W4412944664","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1247","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","display_name":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944664","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1247"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1247","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1247","pdf_url":"https://aclanthology.org/2025.findings-acl.1247.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1247.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074650489","display_name":"Omkar Thawakar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omkar Thawakar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108371642","display_name":"Dinura Dissanayake","orcid":"https://orcid.org/0009-0007-6339-1538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinura Dissanayake","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115002295","display_name":"Ketan More","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ketan Pravin More","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115860474","display_name":"Ritesh Thawkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ritesh Thawkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093925844","display_name":"Ahmed Heakl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Heakl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114415249","display_name":"Noor Ahsan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noor Ahsan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709211","display_name":"Yihong Li","orcid":"https://orcid.org/0000-0002-5476-1943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204318","display_name":"Ilmuz Zaman Mohammed Zumri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilmuz Zaman Mohammed Zumri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049890269","display_name":"Jean Lahoud","orcid":"https://orcid.org/0000-0003-0315-6484"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean Lahoud","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022929869","display_name":"Rao Muhammad Anwer","orcid":"https://orcid.org/0000-0002-9041-2214"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rao Muhammad Anwer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009362997","display_name":"Hisham Cholakkal","orcid":"https://orcid.org/0000-0002-8230-9065"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisham Cholakkal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Laptev","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215307","display_name":"Mubarak Shah","orcid":"https://orcid.org/0000-0002-8216-1128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mubarak Shah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101483979","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0002-2905-1755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Salman Khan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.7371,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98634591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24290","last_page":"24315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9918000102043152,"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":0.9918000102043152,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9890999794006348,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5622684955596924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5616954565048218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24648213386535645}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5622684955596924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5616954565048218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24648213386535645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1247","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1247","pdf_url":"https://aclanthology.org/2025.findings-acl.1247.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1247","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1247","pdf_url":"https://aclanthology.org/2025.findings-acl.1247.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6830658824","display_name":null,"funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8869864247","display_name":null,"funder_award_id":"2022-06725","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944664.pdf","grobid_xml":"https://content.openalex.org/works/W4412944664.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Omkar":[0],"Thawakar,":[1],"Dinura":[2],"Dissanayake,":[3],"Ketan":[4],"Pravin":[5],"More,":[6],"Ritesh":[7],"Thawkar,":[8],"Ahmed":[9],"Heakl,":[10],"Noor":[11],"Ahsan,":[12],"Yuhao":[13],"Li,":[14],"Ilmuz":[15],"Zaman":[16],"Mohammed":[17],"Zumri,":[18],"Jean":[19],"Lahoud,":[20],"Rao":[21],"Muhammad":[22],"Anwer,":[23],"Hisham":[24],"Cholakkal,":[25],"Ivan":[26],"Laptev,":[27],"Mubarak":[28],"Shah,":[29],"Fahad":[30],"Shahbaz":[31],"Khan,":[32],"Salman":[33],"Khan.":[34],"Findings":[35],"of":[36],"the":[37],"Association":[38],"for":[39],"Computational":[40],"Linguistics:":[41],"ACL":[42],"2025.":[43,44]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
