Enhancing Out-of-Distribution Detection with Extended Logit Normalization
通过扩展对数归一化增强分布外检测
机构 * Linköping University(林霍普大学) ; Imperial College London(伦敦帝国学院)
AI总结 本文提出ELogitNorm方法,通过引入特征距离感知损失改进分布外检测并提升分布内置信度校准。
Comments CVPR 2026
高校专区
通过扩展对数归一化增强分布外检测
机构 * Linköping University(林霍普大学) ; Imperial College London(伦敦帝国学院)
AI总结 本文提出ELogitNorm方法,通过引入特征距离感知损失改进分布外检测并提升分布内置信度校准。
Comments CVPR 2026
MultiDiffSense: 基于扩散的多模态视觉-触觉图像生成,基于物体形状和接触姿态
机构 * Department of Bioengineering, Imperial-X Initiative, Imperial College London(生物工程系、Imperial-X计划、帝国理工学院伦敦分校) ; CAMS-Oxford Institute, University of Oxford(CAMS-牛津研究所、牛津大学)
AI总结 MultiDiffSense是一种基于扩散的多模态视觉-触觉图像生成模型,通过双条件化实现可控且物理一致的多模态生成,提升了触觉传感数据集的生成效率和跨模态学习能力。
Comments Accepted by 2026 ICRA
模块化磁性微机器人多模态运动与形状重构设计与控制
机构 * Department of Bioengineering, Imperial College London(帝国理工学院生物工程系)
AI总结 本研究提出一种模块化磁性微机器人平台,通过多模块协同实现多模态运动与形状重构,展示了在受限环境中稳健控制的潜力。
Comments Accepted by 2026 ICRA
关注CTC:用于统一语音识别的快速且稳健的伪标签方法
机构 * NatWest AI Research(NatWest人工智能研究) ; Imperial College London(伦敦帝国理工学院)
AI总结 本文提出USR 2.0,通过CTC驱动的教师强制和混合采样提升统一语音识别的训练效率和鲁棒性,实现训练时间减半并在多个基准上取得最佳性能。
Comments ICLR 2026. Code: https://github.com/ahaliassos/usr2
在皮肤病学中考虑 artefacts 的真菌检测:一种基于实时变换器的 KOH 显微镜方法
机构 * Yildiz Technical University(伊兹密尔技术大学) ; Imperial College London(帝国理工学院伦敦分校) ; Istanbul Research and Training Hospital(伊斯坦布尔研究与培训医院) ; Medicana Atakoy Hospital(梅迪卡纳阿塔科伊医院)
AI总结 本研究提出基于实时变换器的 KOH 显微镜方法,用于准确检测真菌,通过高精度定位提升皮肤病学诊断的可靠性。
基于物理的复合板冲击定位与力估计及不确定性量化
机构 * Department of Aeronautics, Imperial College London(航空系,帝国理工学院伦敦分校)
AI总结 本文提出了一种结合物理模型与机器学习的复合板冲击定位与力估计方法,通过不确定性量化提高鲁棒性和效率。
Comments 37 pages (including the appendix and references), 16 figures. Composite Structures (2026)
MAPS算法:用于监督学习的快速模型无关和分布无关的预测区间
机构 * Department of Mathematics, Imperial College London(帝国理工学院伦敦数学系) ; Great Ormond Street Institute of Child Health(大奥蒙街儿童健康研究所) ; Instituto de Ingeniería Biomédica, Universidad de Buenos Aires(布宜诺斯艾利斯大学生物医学工程研究所)
AI总结 MAPS算法通过提升预测模型,提供快速、模型无关且分布无关的预测区间,适用于高维监督学习中的条件覆盖问题。
Comments 28 pages, 3 algorithms, 5 figures, 3 tables
如何做到?
机构 * Imperial College London, London, United Kingdom(伦敦帝国学院)
AI总结 本文研究了学生与LLM聊天机器人对话中程序性问题的主导地位,发现其在总结性评估中更为突出,但现有分类方案存在局限性。
Comments 14 pages, 2 figures
自适应GR(1)规范修复用于强化学习中的存活保持防护
机构 * Imperial College London(伦敦帝国理工学院) ; Universidad de Buenos Aires(布宜诺斯艾利斯大学)
AI总结 本文提出基于GR(1)规范的自适应防护框架,通过在线修复规范实现环境假设违反时的安全与存活保持。
在TinyML中实现去中心化的资源共享:用于协作学习的无线双层 gossip 平行 SGD
机构 * Department of Computing, Imperial College London(帝国理工学院伦敦分校计算机系) ; Nottingham Trent University(诺丁汉特伦特大学) ; Trasna-Solutions Ltd.(Trasna-Solutions有限公司) ; Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County(马里兰大学巴尔的摩县计算机科学与电气工程系) ; Department of Electrical and Computer Engineering, Johns Hopkins University(约翰霍普金斯大学电气与计算机工程系)
AI总结 本文提出了一种双层gossip平行SGD框架,用于在资源受限的边缘设备上实现去中心化的联邦学习,通过高效模型聚合和通信结构,提升协作学习的准确性和效率。
Journal ref IEEE Pervasive Computing, 2026
光学传感电织带执行器(OS-ERA)
机构 * Soft BioRobotics and Perception Lab of the Istituto Italiano di Tecnologia(意大利技术研究院软生物机器人与感知实验室) ; Open University Affiliated Research Centre at Istituto Italiano di Tecnologia(意大利技术研究院开放大学附属研究中心) ; Department of Bioengineering, Imperial College London(伦敦帝国理工学院生物工程系)
AI总结 OS-ERA通过光学传感实现高精度弯曲状态分类,解决ERAs的传感精度瓶颈,实现快速且可重复的闭环控制
Comments 6 pages, 5 figures, accepted for 9th IEEE-RAS International Conference on Soft Robotics (RoboSoft 2026)
附件锚点:一种用于结直肠手术腹腔镜抓取点预测的新框架
机构 * Technical University of Munich, TUM School of Medicine and Health, TUM University Hospital rechts der Isar, Department of Surgery, Research Group MITI(慕尼黑技术大学,TUM医学与健康学院,TUM慕尼黑大学医院rechts der Isar,外科部,MITI研究组) ; Technical University of Munich, TUM School of Medicine and Health, TUM University Hospital rechts der Isar, Chair for AI in Healthcare and Medicine Munich(慕尼黑技术大学,TUM医学与健康学院,TUM慕尼黑大学医院rechts der Isar,人工智能在医疗与健康中的chair) ; Department of Computing, Imperial College London(伦敦帝国学院计算系)
AI总结 本文提出附件锚点框架,通过编码组织与解剖附件的局部几何和机械关系,提升结直肠手术中抓取点预测的准确性。
使用混合整数规划精确认证数据中毒攻击
机构 * Department of Computing, Imperial College London(帝国理工学院伦敦分校计算机系) ; The Alan Turing Institute(阿兰·图灵研究院)
AI总结 本文提出了一种基于混合整数规划的框架,用于精确认证神经网络训练期间的数据中毒攻击的鲁棒性。
Comments Accepted to the 23rd International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR)
节点学习:一种适应性、去中心化和协作的网络边缘AI框架
机构 * Nottingham Trent University(诺丁汉特伦特大学) ; Imperial College London(帝国理工学院伦敦分校)
AI总结 Node Learning是一种去中心化的边缘AI框架,通过节点间的协作与自主学习,解决边缘计算中的资源约束和异构性问题。
Comments 16 pages, 3 figures, 3 tables, this paper introduces a new concept
在线性二次随机微分博弈中学习分布式均衡:一种α-势方法
机构 * Department of Mathematics, Imperial College London(伦敦帝国理工学院数学系)
AI总结 本文提出一种α-势方法,用于在线性二次随机微分博弈中实现分布式均衡学习,通过理论分析和实验验证了该方法在对称和不对称交互下的收敛性与有效性。
AMBER:一种可 tether 部署的抓取爬行器,配备顺应性微刺,用于树冠操作
机构 * eAviation Laboratory, TUM School of Engineering and Design(eAviation实验室,技术大学工程与设计学院) ; Laboratory of Sustainability Robotics, EMPA(可持续机器人实验室,EMPA) ; Laboratory of Sustainability Robotics, EPFL(可持续机器人实验室,瑞士联邦理工学院) ; Aerial Robotics Laboratory, Imperial College London(空域机器人实验室,伦敦帝国理工学院) ; Bristol University(布里斯托大学)
AI总结 AMBER是一种可空中部署的抓取爬行器,利用顺应性微刺轨道和双轨道旋转夹具,在树冠中实现自适应移动和操作,具备低功耗、高机动性的特点。
可验证的FL:使用exclaves进行联邦学习的可验证声明
机构 * Imperial College London(伦敦帝国学院) ; Azure Research(Azure研究院) ; Microsoft Security Response Center(微软安全响应中心)
AI总结 VerifiableFL通过exclaves实现联邦学习模型的可验证声明,减少12%的开销,增强训练过程的透明性和安全性。
Uni-Flow:一种统一的自回归-扩散模型用于复杂多尺度流体
机构 * Centre for Computational Science, University College London, London, UK ; Department of Earth Science ; Engineering, Imperial College London, London, UK ; Department of Chemical Engineering, University College London, London, UK ; Department of Physics, Eindhoven University of Technology, Eindhoven, Netherlands ; School of Civil \& Environmental Engineering, Queensland University of Technology, Brisbane, Australia ; Australian Centre for Water ; Environmental Biotechnology, The University of Queensland, Brisbane, Australia ; Institute for Mechanics, Computational Mechanics Group, Technical University of Darmstadt, Germany ; Centre for Advanced Research Computing, University College London, London, UK
AI总结 Uni-Flow通过统一自回归-扩散模型,实现复杂多尺度流体的高效建模与高分辨率重构。
增强人类平衡的通用冗余机器人肢体
机构 * Bioengineering Department, Imperial College of Science, Technology and Medicine(生物工程系,帝国理工学院科学、技术与医学学院)
AI总结 本文提出了一种通用框架,通过冗余机器人肢体增强人类平衡,通过三级分层架构实现安全有效的平衡控制。
通过基于恢复的防护机制实现安全强化学习
机构 * Imperial College London, Department of Computing(伦敦帝国学院计算机系)
AI总结 本文提出一种基于高斯过程的恢复防护机制,用于在未知非线性系统中实现安全强化学习,通过动态恢复和内部模型采样实现安全与高效的学习。
Comments Accepted at AAMAS 2026
语义搜索中拓扑量化歧义性
机构 * Avantia London(阿文提亚伦敦) ; Imperial College London(帝国理工学院伦敦)
AI总结 该研究利用持续同调度量量化语义搜索中查询的歧义性,通过模拟和实证验证展示了拓扑方法在检测语义不连续性中的有效性。
神经与数值方法用于接触Calabi-Yau 7维流形上的G₂结构
机构 * Abdus Salam Centre for Theoretical Physics(阿布杜·萨拉姆理论物理中心) ; Imperial College London(帝国理工学院伦敦分校)
AI总结 本文提出神经与数值方法,用于近似接触Calabi-Yau 7维流形上的G₂结构3形式,通过训练神经网络直接学习3形式及其度量,验证其torsion。
Comments 8+5 pages, 9 figures
M6:多生成器、多领域、多语言及文化、多类型、多乐器机器生成音乐检测数据库
机构 * Imperial College London(帝国理工学院伦敦分校) ; Shandong University(山东大学)
AI总结 M6数据库通过多维度涵盖多种生成器、领域、语言等,为机器生成音乐检测提供大规模基准数据,助力更高效的检测方法研发。
Comments Accepted at Scientific reports
扩散对齐超越KL:方差最小化作为有效的策略优化器
机构 * Imperial College London(帝国理工学院伦敦分校) ; Samsung R&D Institute UK(三星英国研发中心)
AI总结 本文提出方差最小化策略优化方法,通过最小化对数重要权重的方差来实现扩散对齐,超越传统KL优化,提供新的设计方向。
基于变压器的深度核融合
机构 * Imperial College London(帝国理工学院伦敦分校) ; University of Cambridge(剑桥大学)
AI总结 本研究提出DeepFusionKernel,通过深度融合内核减少HBM流量并提高缓存复用,实现大语言模型在长上下文推理中的性能提升。
自动化胎儿脑MRI分割与生物测量的进展:来自FeTA 2024挑战的见解
机构 * organization= Department of Radiology, Lausanne University Hospital ; University of Lausanne , city= Lausanne , country= Switzerland ; organization= CIBM Center for Biomedical Imaging , city= Lausanne , country= Switzerland ; organization= Department of Early Life Imaging, School of Biomedical Engineering \& Imaging Sciences, King’s College London , city= London , country= UK ; organization= Smart Imaging Lab, University Hospital Erlangen , city= Erlangen , country= Germany ; organization= Center for MR-Research, University Children’s Hospital Zurich, University of Zurich , city= Zurich , country= Switzerland ; organization= Neuroscience Center Zurich, University of Zurich , city= Zurich , country= Switzerland ; organization= National Heart \& Lung Institute, Imperial College London , city= London , country= UK ; organization= University of California, San Francisco ; UCSF Benioff Children’s Hospital , city= San Francisco , state= California , country= USA ; organization= Department of Quantitative Biomedicine, University of Zurich , city= Zurich , country= Switzerland ; organization= Department of Informatics, Technical University of Munich , city= Munich , country= Germany ; organization= Boston Children’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA ; organization= Neuroimaging Unit, Scientific Institute IRCCS E. Medea , city= Bosisio Parini , country= Italy ; organization= Department of Informatics, Systems ; Communication, University of Milano Bicocca , city= Milan , country= Italy ; organization= Research Institute of Computer Vision ; organization= BCN MedTech, Department of Engineering, Universitat Pompeu Fabra , city= Barcelona , country= Spain ; organization= Department of Information Engineering, University of Padova , city= Padova , country= Italy ; organization= Institut Pasteur, Université Paris Cité, CNRS UMR 3571, Decision ; organization= Inria, HeKA, PariSantéCampus , city= Paris , country= France ; organization= L. D. College of Engineering , city= Gujarat , country= India ; organization= Medical Faculty Heidelberg, Heidelberg University , addressline= Pattern Analysis ; Learning Group, Department of Radiation Oncology, Heidelberg University Hospital , city= Heidelberg , country= Germany ; organization= Canon Medical Systems (China) Co., Ltd , city= , country= China ; organization= Faculty of Electrical Engineering, University of Ljubljana , city= Ljubljana , country= Slovenia ; organization= Department of Radiology, Seoul National University Hospital , city= Seoul , country= South Korea ; organization= School of Mechanical ; Electrical Engineering, University of Electronic Science ; organization= School of Computer Science, Wuhan University , city= Wuhan , country= China ; Developmental Science Center, Boston Children’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA ; organization= Hawkes Institute, Department of Computer Science, University College London , city= London , country= UK ; organization= Laboratory for Computational Neuroimaging, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital/Harvard Medical School , city= Charlestown , state= Massachusetts , country= USA ; organization= Department of Biomedical Imaging ; Image-guided Therapy, Computational Imaging Research Lab (CIR), Early Life Image Analysis Group, Medical University of Vienna , city= Vienna , country= Austria ; organization= University Research Priority Project Adaptive Brain Circuits in Development ; Learning (AdaBD), University of Zurich , city= Zurich , country= Switzerland ; organization= Sagol Brain Institute, Tel Aviv Sourasky Medical Center ; School of EE, Tel-Aviv University , city= Tel-Aviv , country= Israel ; organization= Department of Medical Imaging Sciences, The Faculty of Social Welfare ; Health Sciences, University of Haifa , city= Haifa , country= Israel ; Faculty of Medicine ; Sagol School of Neuroscience, Tel-Aviv University , city= Tel-Aviv , country= Israel ; organization= Department Woman-Mother-Child, CHUV , city= Lausanne , country= Switzerland ; organization= BCNatal Fetal Medicine Research Center (Hospital Clínic ; Hospital Sant Joan de Déu), Universitat de Barcelona , city= Barcelona , country= Spain ; organization= German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing , city= Heidelberg , country= Germany ; organization= Helmholtz Imaging, German Cancer Research Center (DKFZ) , city= Heidelberg , country= Germany ; organization= Faculty of Mathematics ; Computer Science, Heidelberg University , city= Heidelberg , country= Germany ; organization= University of Zurich , city= Zurich , country= Switzerland ; organization= Croatian Institute for Brain Research, School of Medicine, University of Zagreb , city= Zagreb , country= Croatia ; organization= Department of Biomedical Engineering, School of Biomedical Engineering \& Imaging Sciences, King’s College , city= London , country= United Kingdom ; Musculoskeletal Radiology, Medical University of Vienna , city= Vienna , country= Austria ; organization= Division of Newborn Medicine, Boston Children’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA ; organization= Department of Radiology, Boston Children’s Hospital, Harvard Medical School , city= Boston , state= Massachusetts , country= USA
AI总结 FeTA 2024挑战通过引入生物测量预测和低场MRI数据,推动了胎儿脑MRI分割与生物测量的自动化进展,揭示了拓扑差异和成像系统对分割性能的影响。
知更鸟的回声:审计大语言模型生成合成文本的隐私风险
机构 * Imperial College London(帝国理工学院伦敦分校) ; Microsoft(微软公司) ; National University of Singapore(新加坡国立大学)
AI总结 本文提出通过设计具有分布内前缀和高困惑度后缀的知更鸟,提高基于数据的MIAs的威力,以更准确评估LLM生成合成数据的隐私风险。
Comments 42nd International Conference on Machine Learning (ICML 2025)
Journal ref Proc. Mach. Learn. Res. 267 (2025) 43557-43580
检索与论证增强的多智能体大语言模型用于判断性预测(含补充材料)
机构 * Imperial College London(帝国理工学院伦敦分校) ; King's College London(国王学院伦敦分校)
AI总结 本文提出一种多智能体框架,结合检索与论证增强技术,提升判断性预测的准确性与可解释性。
Comments 24 pages, 3 figures, Accepted to AAMAS 2026
变形-恢复扩散模型(DRDM):实例变形用于图像处理与合成
机构 * The Kennedy Institute of Rheumatology, University of Oxford, U.K. ; Chinese Academy of Medical Sciences Oxford Institute, University of Oxford, U.K. ; Big Data Institute, University of Oxford, U.K. ; edited MRC Laboratory of Medical Sciences, Imperial College London, U.K. ; Department of Computer Science, University of Oxford, Oxford, U.K. [12.5pt] Project page: -5pt
AI总结 DRDM通过变形场生成解剖学合理的图像变形,提升医学影像的数据增强与合成效果。
Comments accepted by Medical Image Analysis
LiveMedBench: 一个无污染的医疗基准测试,用于具有自动评分评估的LLM
机构 * Lehigh University(莱维大学) ; Harvard University(哈佛大学) ; Imperial College London(伦敦帝国学院) ; Massachusetts General Hospital(麻省总医院) ; Harvard Medical School(哈佛医学院)
AI总结 LiveMedBench通过持续更新和自动评分框架,提供无污染的医疗基准测试,验证LLM在临床推理中的性能,揭示数据污染和上下文适应性问题。