{"id":"https://openalex.org/W7204545495","doi":"https://doi.org/10.1007/978-3-032-37281-9_2","title":"From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation","display_name":"From Reasoning to Pixels: Grounded Medical Multimodal LLMs for VQA and Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204545495","doi":"https://doi.org/10.1007/978-3-032-37281-9_2"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-37281-9_2","doi":"https://doi.org/10.1007/978-3-032-37281-9_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-37281-9_2","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,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"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"},"volume":{"id":"https://openalex.org/W7212275729","display_name":"Computer Vision \u2013 ECCV 2026"},"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.26856","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136502567","display_name":"Haowen Gu","orcid":"https://orcid.org/0009-0003-5418-0596","observed_orcids":["https://orcid.org/0009-0003-5418-0596"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowen Gu","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China","State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-5418-0596","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082756213","display_name":"Gensheng Pei","orcid":"https://orcid.org/0000-0002-7677-7487","observed_orcids":["https://orcid.org/0000-0002-7677-7487"]},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gensheng Pei","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Korea"],"raw_orcid":"https://orcid.org/0000-0002-7677-7487","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003709886","display_name":"Junzhu Mao","orcid":"https://orcid.org/0009-0005-0831-9272","observed_orcids":["https://orcid.org/0009-0005-0831-9272"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhu Mao","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China","State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-0831-9272","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148550908","display_name":"Qiong Wang","orcid":"https://orcid.org/0000-0003-4193-0960","observed_orcids":["https://orcid.org/0000-0003-4193-0960"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiong Wang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China","State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4193-0960","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968758","display_name":"Mingwu Ren","orcid":"https://orcid.org/0000-0001-5576-3281","observed_orcids":["https://orcid.org/0000-0001-5576-3281"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingwu Ren","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China","State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5576-3281","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027545344","display_name":"Yazhou Yao","orcid":"https://orcid.org/0000-0002-0337-9410","observed_orcids":["https://orcid.org/0000-0002-0337-9410"]},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yazhou Yao","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, China","State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0337-9410","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery, Nanjing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027545344","https://openalex.org/A5102968758"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.0015,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92409816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"36"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":9.999999747378752e-05,"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/medical-visual-question-answering","display_name":"medical visual question answering","score":0.9599999785423279},{"id":"https://openalex.org/keywords/medical-image-segmentation","display_name":"medical image segmentation","score":0.7279999852180481},{"id":"https://openalex.org/keywords/spatial-localization","display_name":"spatial localization","score":0.5339999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178999781608582},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6927000284194946},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445000171661377},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6395999789237976},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5116999745368958},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3646000027656555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3375999927520752},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2676999866962433},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-032-37281-9_2","doi":"https://doi.org/10.1007/978-3-032-37281-9_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-37281-9_2","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,"listed_in":["cwts-core","jufo-1","ki-jl-1","norway-1","vabb-shw"],"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"},{"id":"pmh:oai:arXiv.org:2608.26856","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26856","pdf_url":"https://arxiv.org/pdf/2608.26856","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.26856","doi":"https://doi.org/10.48550/arxiv.2608.26856","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26856","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.26856","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26856","pdf_url":"https://arxiv.org/pdf/2608.26856","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204545495.pdf","grobid_xml":"https://content.openalex.org/works/W7204545495.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2101105183","https://openalex.org/W2901466771","https://openalex.org/W2908510526","https://openalex.org/W2910094941","https://openalex.org/W2932083555","https://openalex.org/W2979534245","https://openalex.org/W2988299447","https://openalex.org/W2991372685","https://openalex.org/W3012608737","https://openalex.org/W3015788359","https://openalex.org/W3081168214","https://openalex.org/W3093937711","https://openalex.org/W3136709974","https://openalex.org/W3165058054","https://openalex.org/W3198570286","https://openalex.org/W4321232185","https://openalex.org/W4327810158","https://openalex.org/W4386075561","https://openalex.org/W4387225871","https://openalex.org/W4390873519","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4392044798","https://openalex.org/W4402716107","https://openalex.org/W4402754134","https://openalex.org/W4402916449","https://openalex.org/W4403908285","https://openalex.org/W4403998633","https://openalex.org/W4404601423","https://openalex.org/W4404782407","https://openalex.org/W4405425529","https://openalex.org/W4405562118","https://openalex.org/W4406301628","https://openalex.org/W4407571388","https://openalex.org/W4413146561","https://openalex.org/W4413147363","https://openalex.org/W4413157966","https://openalex.org/W4413158161","https://openalex.org/W4414380821","https://openalex.org/W4416055645","https://openalex.org/W4416780398","https://openalex.org/W6948369276","https://openalex.org/W6967068517","https://openalex.org/W7106651337","https://openalex.org/W7116772418","https://openalex.org/W7124711964","https://openalex.org/W7127319731","https://openalex.org/W7133193597","https://openalex.org/W7137947075","https://openalex.org/W7138189184","https://openalex.org/W7160327811"],"related_works":["https://openalex.org/W4416243503","https://openalex.org/W4417351562","https://openalex.org/W7202188225","https://openalex.org/W7213881353","https://openalex.org/W4414348931","https://openalex.org/W7154231618","https://openalex.org/W4415434062","https://openalex.org/W4416330257","https://openalex.org/W4414349717","https://openalex.org/W7172487315"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-29T00:00:00"}
