{"id":"https://openalex.org/W4414364908","doi":"https://doi.org/10.1007/978-3-032-04981-0_32","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of\u00a0Vision-Language Models (VLMs) via\u00a0Reinforcement Learning","display_name":"MedVLM-R1: Incentivizing Medical Reasoning Capability of\u00a0Vision-Language Models (VLMs) via\u00a0Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-19","ids":{"openalex":"https://openalex.org/W4414364908","doi":"https://doi.org/10.1007/978-3-032-04981-0_32"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-04981-0_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-04981-0_32","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":"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/A5004278800","display_name":"Jiazhen Pan","orcid":"https://orcid.org/0000-0002-6305-8117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiazhen Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Che Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042162337","display_name":"Junde Wu","orcid":"https://orcid.org/0000-0001-5334-8391"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junde Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632779","display_name":"Fenglin Liu","orcid":"https://orcid.org/0009-0007-4736-8100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fenglin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119247428","display_name":"Jiayuan Zhu","orcid":"https://orcid.org/0000-0002-3641-4489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayuan Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325337","display_name":"Hongwei Li","orcid":"https://orcid.org/0000-0002-5328-6407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwei Bran Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418548","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-2104-534X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104083508","display_name":"Cheng Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Ouyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006461848","display_name":"Daniel Rueckert","orcid":"https://orcid.org/0000-0002-5683-5889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Rueckert","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9825000166893005,"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/T10028","display_name":"Topic Modeling","score":0.9735999703407288,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7002000212669373},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.2786000072956085},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.2754000127315521},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.2614000141620636},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2425999939441681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8547999858856201},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34790000319480896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2425999939441681},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.23569999635219574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-04981-0_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-04981-0_32","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2766447205","https://openalex.org/W2901466771","https://openalex.org/W3165058054","https://openalex.org/W4285618474","https://openalex.org/W4362671245","https://openalex.org/W4385571944","https://openalex.org/W4401397240","https://openalex.org/W4402774103","https://openalex.org/W4403791774","https://openalex.org/W4404509535","https://openalex.org/W4404782407"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":9}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}