科学与医疗

医学 AI

医学智能、临床 AI、医学影像、病理、诊断和医疗健康大模型。

2026-03-05 至 2026-03-05 共收录 3 篇信号源：cs.CV, cs.LG, q-bio, eess.IV, eess.SP

1. 医学数据与评测 3 篇

2511.03441 2026-03-05 cs.CL cs.AI 78%

CareMedEval dataset: Evaluating Critical Appraisal and Reasoning in the Biomedical Field

CareMedEval 数据集：评估生物医学领域中的批判性评估与推理

Doria Bonzi, Alexandre Guiggi, Frédéric Béchet, Carlos Ramisch, Benoit Favre

专题命中医学数据与评测：biomedical(title,abstract)

AI总结 CareMedEval数据集用于评估生物医学领域中LLM的批判性评估与推理能力，揭示了现有模型在专业领域中的局限性。

Comments Accepted at LREC 2026. To access the dataset, see https://github.com/bonzid/CareMedEval

2603.03398 2026-03-05 cs.CR cs.AI 78%

Zero-Knowledge Federated Learning with Lattice-Based Hybrid Encryption for Quantum-Resilient Medical AI

基于格的混合加密的零知识联邦学习用于量子安全的医疗AI

Edouard Lansiaux

机构 * Department of Emergency Medicine & STaR-AI Research Group（急诊医学系及STaR-AI研究组）

专题命中医学数据与评测：medical AI(title,abstract)

AI总结 ZKFL-PQ通过抗量子加密和零知识证明，实现医疗AI模型在量子安全下的隐私保护与鲁棒性。

2507.15796 2026-03-05 cs.AI 50%

From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0

从隐私到信任在代理时代：通过信任报告2.0的视角，对可信联邦学习中挑战的分类

Nuria Rodríguez-Barroso, Mario García-Márquez, M. Victoria Luzón, Francisco Herrera

机构 * Department of Computer Science and Artificial Intelligence, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada（计算机科学与人工智能系，数据科学与计算智能安达卢西亚研究 institute，格拉纳达大学）； Department of Software Engineering, Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada（软件工程系，数据科学与计算智能安达卢西亚研究 institute，格拉纳达大学）

专题命中医学数据与评测：diagnosis(abstract)

AI总结本文通过信任报告2.0提出可信联邦学习的挑战分类，强调信任作为持续维持的操作条件，并引入协调蓝图以处理跨要求的权衡和治理对齐。

Comments Already published in Information Fusion

Journal ref Rodríguez-Barroso, et. al. (2026). From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0. Information Fusion, 104236