{"id":"https://openalex.org/W4404691768","doi":"https://doi.org/10.1007/978-3-031-73030-6_3","title":"ViGoR: Improving Visual Grounding of\u00a0Large Vision Language Models with\u00a0Fine-Grained Reward Modeling","display_name":"ViGoR: Improving Visual Grounding of\u00a0Large Vision Language Models with\u00a0Fine-Grained Reward Modeling","publication_year":2024,"publication_date":"2024-11-24","ids":{"openalex":"https://openalex.org/W4404691768","doi":"https://doi.org/10.1007/978-3-031-73030-6_3"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-73030-6_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73030-6_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5100736121","display_name":"Siming Yan","orcid":"https://orcid.org/0000-0002-1031-9205"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siming Yan","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101526995","display_name":"Min Bai","orcid":"https://orcid.org/0000-0002-5529-6676"},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Bai","raw_affiliation_strings":["AWS AI, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, San Francisco, USA","institution_ids":["https://openalex.org/I4210156496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113676982","display_name":"Weifeng Chen","orcid":"https://orcid.org/0000-0001-6767-3099"},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weifeng Chen","raw_affiliation_strings":["AWS AI, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, San Francisco, USA","institution_ids":["https://openalex.org/I4210156496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100971139","display_name":"Xiong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Zhou","raw_affiliation_strings":["AWS AI, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, San Francisco, USA","institution_ids":["https://openalex.org/I4210156496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056540212","display_name":"Qixing Huang","orcid":"https://orcid.org/0000-0001-6365-8051"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qixing Huang","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053710007","display_name":"Li Erran Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156496","display_name":"Uber AI (United States)","ror":null,"country_code":"US","type":null,"lineage":["https://openalex.org/I4210156496"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Erran Li","raw_affiliation_strings":["AWS AI, San Francisco, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AWS AI, San Francisco, USA","institution_ids":["https://openalex.org/I4210156496"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100736121"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.4623,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89534044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"53"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976999759674072,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.85430908203125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5173965692520142},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45030534267425537},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4352600574493408},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4107479751110077},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3304562568664551},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09020841121673584},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.05623522400856018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85430908203125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5173965692520142},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45030534267425537},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4352600574493408},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4107479751110077},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3304562568664551},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09020841121673584},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.05623522400856018},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-73030-6_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-73030-6_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2560730294","https://openalex.org/W2737258237","https://openalex.org/W2963622213","https://openalex.org/W3106859150","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W4226278401","https://openalex.org/W4296406182","https://openalex.org/W4306820534","https://openalex.org/W4312956471","https://openalex.org/W4376312115","https://openalex.org/W4384918448","https://openalex.org/W4385714029","https://openalex.org/W4389523832","https://openalex.org/W4402670859","https://openalex.org/W4404612908","https://openalex.org/W6600008909","https://openalex.org/W6600234944","https://openalex.org/W6778883912","https://openalex.org/W6796581206"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}