{"id":"https://openalex.org/W4414881574","doi":"https://doi.org/10.1109/iccv51701.2025.02001","title":"Constructing Ophthalmic MLLM for Positioning-Diagnosis Collaboration Through Clinical Cognitive Chain Reasoning","display_name":"Constructing Ophthalmic MLLM for Positioning-Diagnosis Collaboration Through Clinical Cognitive Chain Reasoning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414881574","doi":"https://doi.org/10.1109/iccv51701.2025.02001"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.17539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005910215","display_name":"Xinyao Liu","orcid":"https://orcid.org/0000-0002-2454-7436"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyao Liu","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":null,"display_name":"Diping Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diping Song","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005910215"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24659468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21547","last_page":"21556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8878999948501587,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.8878999948501587,"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/T10350","display_name":"Electronic Health Records Systems","score":0.8241999745368958,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7860000133514404,"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/bridging","display_name":"Bridging (networking)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.48330000042915344},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.42410001158714294},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.40689998865127563},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.39719998836517334},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.38960000872612},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.34310001134872437},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.33469998836517334},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.33169999718666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805000066757202},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.39719998836517334},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C92298750","wikidata":"https://www.wikidata.org/wiki/Q17008161","display_name":"Cognitive computing","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02001","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.17539","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17539","pdf_url":"https://arxiv.org/pdf/2507.17539","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.17539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.17539","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.17539","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17539","pdf_url":"https://arxiv.org/pdf/2507.17539","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"demonstrate":[5],"significant":[6],"potential":[7],"in":[8,19,33,118,135,171,201],"the":[9,26,61,100,115,123,127,167,198],"field":[10],"of":[11,28,126,144],"medical":[12],"diagnosis.":[13],"However,":[14],"they":[15],"face":[16],"critical":[17],"challenges":[18],"specialized":[20],"domains":[21],"such":[22],"as":[23],"ophthalmology,":[24],"particularly":[25],"fragmentation":[27],"annotation":[29],"granularity":[30],"and":[31,68,81,159,192],"inconsistencies":[32],"clinical":[34,142],"reasoning":[35,52,105,183],"logic,":[36],"which":[37],"hinder":[38],"precise":[39],"cross-modal":[40],"understanding.":[41],"This":[42],"paper":[43],"introduces":[44],"FundusExpert,":[45,107],"an":[46],"ophthalmology-specific":[47],"MLLM":[48,191],"with":[49,55,109,181],"integrated":[50],"positioning-diagnosis":[51],"capabilities,":[53],"along":[54],"FundusGen,":[56,113],"a":[57,86,93,141,153,188,194],"dataset":[58],"constructed":[59],"through":[60],"intelligent":[62],"Fundus-Engine":[63,65],"system.":[64],"automates":[66],"localization":[67,180],"leverages":[69],"MLLM-based":[70],"semantic":[71],"expansion":[72],"to":[73,102],"integrate":[74],"global":[75],"disease":[76],"classification,":[77],"local":[78],"object":[79],"detection,":[80],"fine-grained":[82],"feature":[83],"analysis":[84],"within":[85],"single":[87],"fundus":[88],"image.":[89],"Additionally,":[90],"by":[91,130],"constructing":[92],"clinically":[94],"aligned":[95],"cognitive":[96,168],"chain,":[97],"it":[98],"guides":[99],"model":[101,160],"generate":[103],"interpretable":[104],"paths.":[106],"fine-tuned":[108],"instruction":[110],"data":[111,157,174],"from":[112],"achieves":[114],"best":[116],"performance":[117],"ophthalmic":[119],"question-answering":[120],"tasks,":[121,139],"surpassing":[122],"average":[124],"accuracy":[125],"40B":[128],"MedRegA":[129],"26.6%.":[131],"It":[132],"also":[133],"excels":[134],"zero-shot":[136],"report":[137],"generation":[138],"achieving":[140],"consistency":[143],"77.0%,":[145],"significantly":[146],"outperforming":[147],"GPT-4o's":[148],"47.6%.":[149],"Furthermore,":[150],"we":[151],"reveal":[152],"scaling":[154],"law":[155],"between":[156],"quality":[158],"capability":[161],"($L":[162],"\\propto":[163],"N^{0.068}$),":[164],"demonstrating":[165],"that":[166],"alignment":[169],"annotations":[170],"FundusGen":[172],"enhance":[173],"utilization":[175],"efficiency.":[176],"By":[177],"integrating":[178],"region-level":[179],"diagnostic":[182],"chains,":[184],"our":[185],"work":[186],"develops":[187],"scalable,":[189],"clinically-aligned":[190],"explores":[193],"pathway":[195],"toward":[196],"bridging":[197],"visual-language":[199],"gap":[200],"specific":[202],"MLLMs.":[203],"Our":[204],"project":[205],"can":[206],"be":[207],"found":[208],"at":[209],"https://github.com/MeteorElf/FundusExpert.":[210]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}