[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82216-en":3,"doc-seo-82216-105":29,"detail-sidebar-cat-0-en-105":82},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82216,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",7,"Healthcare","Super-Generalist Towards Comprehensive and Accurate Medical Image Understanding via Generalist–Specialist Synergy","Medical imaging demands comprehensive, precise interpretation to support diagnosis across diverse clinical conditions. Vision-language generalist models provide broad coverage and zero-shot ability, yet often miss fine-grained anatomical and lesion awareness needed for reliable decisions and spatial interpretability. Supervised specialist models excel on specific tasks but generalize poorly across diseases and anatomies. SuG unifies generalist learning with specialist objectives using spatial priors from multiple segmentation experts and lesion-mask guided text-conditioned attention calibration. Evaluations on chest and abdominal CT benchmarks show state-of-the-art performance and robust lesion grounding, including generalization to lesion types without class-specific supervision.","arXiv :2607 .09135v1 [ cs .CV] 10 Jul 2026  \nSuper-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist–Specialist Synergy  \nShaoteng Zhang 1 ,3 Weiwei Cao 1 ,2 Wanxing Chang 1 ,2 Yutong Xie8 , Kai Cao5 , Zaiyi Liu4 , Yu Shi6 , Tingbo Liang7 , Qi Zhang7 , Ling Zhang 1 ,2 , Yong Xia3†,Jianpeng Zhang 1 ,2†  \n1DAMO Academy, Alibaba Group 2Hupan Lab  \n3Department of Radiology, Ningbo No. 2 Hospital, Ningbo, Zhejiang, China  \n4Department of Radiology, Guangdong Provincial People’s Hospital, Guangzhou, China  \n5Department of Radiology, Shanghai Institution of Pancreatic Disease, Shanghai, China  \n6Department of Radiology, Shengjing Hospital of China Medical University, Shenyang, China  \n7The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China  \n8Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates  \nAbstract  \nMedical images require comprehensive and accurate interpretation to support the  \ndiagnosis of diverse clincial conditions. Recent vision–language generalist mod  \nels offer broad task coverage and promising zero-shot capabilities, yet often lack  \nfine-grained anatomical and lesion awareness for reliable diagnosis and spatial in  \nterpretability. In contrast, supervised specialist models achieve strong performance  \non specific tasks but typically lack generalization across diseases and anatomies.  \nIn this work, we present SuG, a Super-Generalist framework that unifies generalist  \nvision–language learning with specialist objectives, enabling both broad general  \nization and specialist-level diagnostic capability. We perform specialist-enhanced  \nvision-language alignment in SuG by incorporating spatial priors from multiple  \nsegmentation experts, including anatomy, class-specific lesion and class-agnostic  \nlesion segmentors that captures lesions beyond anatomies annotated during training.  \nTo improve lesion grounding capability, we leverage lesion masks as spatial priors  \nto calibrate text-conditioned visual attention, encouraging disease-related seman  \ntics to focus on clinically relevant regions. We evaluate SuG on extensive chest  \nand abdominal CT benchmarks, including CT-RATE, Merlin, MedVL-CT69K,  \nand several in-house tumor datasets. SuG achieves state-of-the-art performance  \nacross a wide range of disease diagnosis tasks and surpasses specialist models  \non several critical tumor diagnosis benchmarks. Furthermore, SuG demonstrates  \nstrong lesion grounding capability, including robust generalization to lesion types  \nlacking class-specific supervision.  \n1 Introduction  \nToward comprehensive and accurate medical image understanding, a core challenge in modern diagnostic AI is to unify three foundational pillars: broad disease scope, specialist-competitive diagnostic performance, and interpretable lesion grounding [1–4] . A system possessing all three would combine the clinical breadth to handle diverse diseases, the precision to rival human specialists,  \n∗ Equal contribution.  \n†Corresponding author: [yxia@nwpu.edu.cn](yxia@nwpu.edu.cn), [jianpeng.zhang0@gmail.com](jianpeng.zhang0@gmail.com)  \nPreprint.  \nSpecialist  \n(a)  \n(b)  \nGeneralist (c) Super Generalist (SuG)  \nDisease scope  \nPerformance  \nGrounding  \nFigure 1: Comparison of medical AI paradigms: Specialist, Generalist, and the proposed Super Generalist (SuG). We evaluate these paradigms across three critical dimensions: disease scope (range of tasks), performance (diagnostic accuracy), and grounding (lesion localization) . (a) Specialists excel in performance and grounding but are limited to a narrow disease scope. (b) Conversely, Generalists support a wide scope but suffer from inferior performance and a lack of precise grounding.(c) Our proposed SuG overcomes these trade-offs, achieving high diagnostic accuracy and precise lesion localization across diverse diseases.  \nand the transparency required for clinical decision-making. However,","cbCaiiSCtEpI1BUB","https://ap.wps.com/l/cbCaiiSCtEpI1BUB","pdf",12571842,1,31,"English","en",105,"# Abstract\n# Introduction\n## Challenge: Unifying scope, performance, and grounding\n## Existing paradigms: Specialist vs. Generalist\n## Proposed method: Super-Generalist (SuG)\n## Synergistic components for specialist-competitive performance","[{\"question\":\"Which datasets and evaluation settings are used to assess SuG’s performance?\",\"answer\":\"SuG is evaluated on extensive chest and abdominal CT benchmarks including CT-RATE, Merlin, MedVL-CT69K, and several in-house tumor datasets, showing state-of-the-art results across disease diagnosis tasks.\"}]",1784178896,78,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":27},"super-generalist-towards-comprehensive-and-accurate-medical-image-understanding-via-generalistspecialist-synergy","",{"@graph":35,"@context":76},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/healthcare/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/super-generalist-towards-comprehensive-and-accurate-medical-image-understanding-via-generalistspecialist-synergy/82216/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"Which datasets and evaluation settings are used to assess SuG’s performance?","Question",{"text":74,"@type":75},"SuG is evaluated on extensive chest and abdominal CT benchmarks including CT-RATE, Merlin, MedVL-CT69K, and several in-house tumor datasets, showing state-of-the-art results across disease diagnosis tasks.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,106,109,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":107,"slug":108},40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general"]