{"id":"https://openalex.org/W7128726294","doi":"https://doi.org/10.1007/s11704-025-41126-5","title":"Patching the visual ability of large multimodal models by collaborating with small models","display_name":"Patching the visual ability of large multimodal models by collaborating with small models","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128726294","doi":"https://doi.org/10.1007/s11704-025-41126-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11704-025-41126-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-025-41126-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","raw_type":"journal-article"},"type":"article","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/A5113392696","display_name":"H. Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Liang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Zhang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682975","display_name":"Meina Kan","orcid":"https://orcid.org/0000-0001-9483-875X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meina Kan","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125698332","display_name":"Shiguang Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Shan","raw_affiliation_strings":["Peng Cheng National Laboratory, Shenzhen, 518055, China","State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng National Laboratory, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102060991","display_name":"Chen Xilin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilin Chen","raw_affiliation_strings":["State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047682975"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26225898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"9","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9873999953269958,"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":0.9873999953269958,"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":0.004699999932199717,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0010999999940395355,"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/perception","display_name":"Perception","score":0.5547000169754028},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.447299987077713},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4397999942302704},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43650001287460327},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8968999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190999746322632},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5547000169754028},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5461999773979187},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4397999942302704},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2791999876499176},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11704-025-41126-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-025-41126-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7382840514183044,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2744909235","https://openalex.org/W2963622213","https://openalex.org/W4205474609","https://openalex.org/W4384071683","https://openalex.org/W4387569787","https://openalex.org/W4405399726"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-02-13T00:00:00"}
