{"id":"https://openalex.org/W7225235243","doi":"https://doi.org/10.48550/arxiv.2611.04012","title":"SurgEye: Instruction Tuning-Free Perception-Reasoning Framework for Surgical Scene Understanding","display_name":"SurgEye: Instruction Tuning-Free Perception-Reasoning Framework for Surgical Scene Understanding","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225235243","doi":"https://doi.org/10.48550/arxiv.2611.04012"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.04012","doi":"https://doi.org/10.48550/arxiv.2611.04012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04012","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.04012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160662575","display_name":"Qing Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Qing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160613399","display_name":"Xiechen Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xiechen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160690657","display_name":"Xianjian He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xianjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160677200","display_name":"Guqiao Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Guqiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141689476","display_name":"\u67f4\u5b50\u6653","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Zixiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160601729","display_name":"Jiale Qin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Jiale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160665167","display_name":"Yifan Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160712183","display_name":"Siyi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Siyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160644506","display_name":"Tian Yuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160630111","display_name":"Yiwei Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160665933","display_name":"Ziheng Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Ziheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160683322","display_name":"Zhen Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9976000189781189,"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":0.9976000189781189,"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/T10916","display_name":"Surgical Simulation and Training","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/surgical-scene-understanding","display_name":"surgical scene understanding","score":0.996999979019165},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7799999713897705},{"id":"https://openalex.org/keywords/compositional-reasoning","display_name":"compositional reasoning","score":0.8009999990463257},{"id":"https://openalex.org/keywords/vision-foundation-models","display_name":"vision foundation models","score":0.7329999804496765},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.746999979019165},{"id":"https://openalex.org/keywords/temporal-memory","display_name":"temporal memory","score":0.7749999761581421},{"id":"https://openalex.org/keywords/computer-assisted-surgery","display_name":"computer-assisted surgery","score":0.8840000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506999969482422},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.507099986076355},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562000036239624},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39239999651908875},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3571000099182129},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3337000012397766},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.04012","doi":"https://doi.org/10.48550/arxiv.2611.04012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04012","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":"doi:10.48550/arxiv.2611.04012","doi":"https://doi.org/10.48550/arxiv.2611.04012","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04012","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7136540880","https://openalex.org/W7161134425","https://openalex.org/W4414684022","https://openalex.org/W7209346065","https://openalex.org/W4415133778","https://openalex.org/W7134235588","https://openalex.org/W4401201546","https://openalex.org/W4407450063","https://openalex.org/W7133343086","https://openalex.org/W4416039125"],"abstract_inverted_index":{"Surgical":[0],"scene":[1],"understanding":[2],"is":[3],"pivotal":[4],"for":[5,130],"computer-assisted":[6],"intervention,":[7],"yet":[8],"demands":[9],"compositional":[10],"reasoning":[11,48],"across":[12,109],"instruments,":[13],"anatomy,":[14],"and":[15,33,80,101,111],"workflow.":[16],"Existing":[17],"surgical":[18,122,141],"vision-language":[19],"models":[20],"rely":[21],"on":[22],"instruction":[23,55],"tuning":[24],"with":[25,127],"large-scale":[26],"question-answer":[27],"pairs,":[28],"entailing":[29],"laborious":[30],"data":[31],"curation":[32],"costly":[34],"retraining.":[35],"To":[36],"bridge":[37],"this":[38],"gap,":[39],"we":[40,58,117],"propose":[41],"SurgEye,":[42],"a":[43,50,92],"perception-reasoning":[44],"framework":[45],"that":[46,64,90,136],"grounds":[47],"in":[49,140],"vision":[51,67],"foundation":[52,68],"model":[53,69,96],"without":[54],"tuning.":[56],"Specifically,":[57],"devise":[59],"Routed":[60],"Multi-Task":[61],"Perception":[62],"(RMP)":[63],"routes":[65],"the":[66],"through":[70],"task-specific":[71],"pathways":[72],"learned":[73],"from":[74],"public":[75],"perception":[76,128],"labels,":[77],"producing":[78],"spatial":[79],"temporal":[81,102],"evidence.":[82],"We":[83],"further":[84],"introduce":[85],"Agentic":[86],"Compositional":[87],"Reasoning":[88],"(ACR)":[89],"employs":[91],"frozen":[93],"large":[94],"language":[95],"to":[97],"coordinate":[98],"RMP":[99],"specialists":[100],"memory":[103],"as":[104],"callable":[105],"tools,":[106],"composing":[107],"evidence":[108],"tasks":[110],"time":[112],"into":[113],"grounded":[114],"answers.":[115],"Moreover,":[116],"construct":[118],"SurgEye-Bench":[119],"spanning":[120],"eight":[121],"procedures,":[123],"pairing":[124],"each":[125],"question":[126],"labels":[129],"verifiable":[131],"evaluation.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"SurgEye":[137],"outperforms":[138],"state-of-the-arts":[139],"reasoning.":[142],"The":[143],"source":[144],"code":[145],"will":[146],"be":[147],"available.":[148]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}