arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Northeastern University(东北大学)

共收录 1238
2512.09742 2025-12-11 cs.CL cs.AI cs.CR cs.LG

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

奇怪的泛化与归纳后门:新方法腐蚀大语言模型

Jan Betley, Jorio Cocola, Dylan Feng, James Chua, Andy Arditi, Anna Sztyber-Betley, Owain Evans

机构 * Northeastern University(东北大学) Warsaw University of Technology(华沙技术大学)

AI总结 通过狭窄微调,大语言模型可能产生不可预测的广泛泛化,包括偏离和后门,展示了微调对模型行为的深远影响。

Comments 70 pages, 47 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.09375 2025-12-11 cs.CV cs.AI

Log NeRF: Comparing Spaces for Learning Radiance Fields

Log NeRF:在学习辐射场中比较空间

Sihe Chen, Luv Verma, Bruce A. Maxwell

机构 * Northeastern University(东北大学)

AI总结 Log NeRF通过在log RGB空间中学习辐射场,提升了渲染质量、场景鲁棒性和低光条件下的表现。

Comments The 36th British Machine Vision Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.09289 2025-12-11 cs.CV

MelanomaNet: Explainable Deep Learning for Skin Lesion Classification

MelanomaNet:用于皮肤病变分类的可解释深度学习

Sukhrobbek Ilyosbekov

机构 * Northeastern University(东北大学)

AI总结 MelanomaNet通过结合EfficientNet V2、GradCAM++、ABCDE标准提取、FastCAV和蒙特卡洛Dropout,实现了皮肤病变分类的高准确率和可解释性,推动临床应用。

Comments 7 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04221 2025-12-11 cs.CV

MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis

MoReGen:基于代码领域的文本到视频合成多智能体运动-推理引擎

Xiangyu Bai, He Liang, Bishoy Galoaa, Utsav Nandi, Shayda Moezzi, Yuhang He, Sarah Ostadabbas

机构 * Northeastern University(东北大学) University of Oxford(牛津大学) Microsoft Research(微软研究院)

AI总结 MoReGen通过整合多智能体大语言模型、物理模拟器和渲染器,实现了基于代码领域的文本到视频合成,强调物理精度和运动一致性,为生成符合物理原理的视频提供了一种新的方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.10476 2025-12-10 cs.CV

Spike-EVPR: Deep Spiking Residual Networks with SNN-Tailored Representations for Event-Based Visual Place Recognition

Spike-EVPR:基于事件视觉地点识别的深度脉冲残差网络

Zuntao Liu, Yaohui Li, Chenming Hu, Delei Kong, Junjie Jiang, Zheng Fang

机构 * Faculty of Robot Science and Engineering, Northeastern University(机器人科学与工程学院,东北大学) School of Artificial Intelligence and Robotics, Hunan University(人工智能与机器人学院,湖南大学)

AI总结 Spike-EVPR通过引入两种互补的事件表示和深度脉冲残差架构,实现了高效的事件视觉地点识别,提升了召回率并降低了能耗。

Comments 8 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08038 2025-12-10 cs.CV

SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification

SSplain: 用于早产儿视网膜病变分类的稀疏平滑解释器

Elifnur Sunger, Tales Imbiriba, Peter Campbell, Deniz Erdogmus, Stratis Ioannidis, Jennifer Dy

机构 * Northeastern University(东北大学) University of Massachusetts Boston(马萨诸塞大学波士顿分校) Oregon Health & Science University(俄勒冈健康与科学大学)

AI总结 SSplain通过稀疏和平滑解释方法提升早产儿视网膜病变分类的可解释性与准确性

Comments 20 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07969 2025-12-10 cs.RO cs.CV

Sparse Variable Projection in Robotic Perception: Exploiting Separable Structure for Efficient Nonlinear Optimization

稀疏变量投影在机器人感知中的应用:利用可分离结构实现高效的非线性优化

Alan Papalia, Nikolas Sanderson, Haoyu Han, Heng Yang, Hanumant Singh, Michael Everett

机构 * Northeastern University, USA(东北大学) University of Michigan(密歇根大学) Harvard University(哈佛大学)

AI总结 本文提出了一种针对具有规范对称性的机器人感知问题的变量投影方法,通过利用可分离性和稀疏性,提高了非线性优化的效率和准确性。

Comments 8 pages, submitted for review

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07168 2025-12-09 cs.SD cs.AI cs.LG eess.AS

JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention

JEPA作为一种神经令牌化器:利用密度自适应注意力学习鲁棒的语音表示

Georgios Ioannides, Christos Constantinou, Aman Chadha, Aaron Elkins, Linsey Pang, Ravid Shwartz-Ziv, Yann LeCun

机构 * Carnegie Mellon University(卡内基梅隆大学) Amazon GenAI(亚马逊生成人工智能) James Silberrad Brown Center for Artificial Intelligence(詹姆斯·西伯拉德·布朗人工智能中心) University of Bristol(布里斯托大学) Stanford University(斯坦福大学) Northeastern University(东北大学) New York University(纽约大学)

AI总结 本文提出了一种结合JEPA和密度自适应注意力机制的两阶段自监督框架,用于高效学习鲁棒的语音表示,通过令牌化和高保真重建实现高效压缩。

Comments UniReps: Unifying Representations in Neural Models (NeurIPS 2025 Workshop)

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06888 2025-12-09 cs.CV

Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation

克服基于视频的婴儿呼吸估计中小数据限制

Liyang Song, Hardik Bishnoi, Sai Kumar Reddy Manne, Sarah Ostadabbas, Briana J. Taylor, Michael Wan

机构 * Northeastern University(东北大学)

AI总结 本文提出了一种基于视频的婴儿呼吸估计方法,通过引入新的标注数据集和可重复的处理流程,解决了小数据限制问题,并建立了相关基准。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06589 2025-12-09 cs.CR cs.CV

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation

OmniSafeBench-MM:多模态 jailbreak 攻击-防御评估的统一基准和工具箱

Xiaojun Jia, Jie Liao, Qi Guo, Teng Ma, Simeng Qin, Ranjie Duan, Tianlin Li, Yihao Huang, Zhitao Zeng, Dongxian Wu, Yiming Li, Wenqi Ren, Xiaochun Cao, Yang Liu

机构 * Nanyang Technological University, Singapore(南洋理工大学) BraneMatrix AI, China(BraneMatrix AI) Chongqing University, China(重庆大学) Xi’an Jiaotong University, China(西安交通大学) Northeastern University, China(东北大学) Sun Yat-sen University, China(中山大学) Alibaba, China(阿里巴巴) National University of Singapore, Singapore(新加坡国立大学) ByteDance, China(字节跳动)

AI总结 OmniSafeBench-MM提供一个多模态jailbreak攻击-防御评估的统一基准和工具箱,整合13种攻击方法、15种防御策略及广泛数据集,通过三维评估协议深入分析安全与效用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04213 2025-12-05 cs.CV

Look Around and Pay Attention: Multi-camera Point Tracking Reimagined with Transformers

环顾四周并关注:基于Transformer的多摄像机点跟踪重新构想

Bishoy Galoaa, Xiangyu Bai, Shayda Moezzi, Utsav Nandi, Sai Siddhartha Vivek Dhir Rangoju, Somaieh Amraee, Sarah Ostadabbas

机构 * Northeastern University(东北大学)

AI总结 LAPA通过基于Transformer的架构,结合注意力机制和几何约束,实现多摄像机点跟踪的高效准确追踪,优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04018 2025-12-04 cs.RO

FPC-VLA: A Vision-Language-Action Framework with a Supervisor for Failure Prediction and Correction

FPC-VLA:一个带有监督器的视觉-语言-动作框架,用于故障预测和纠正

Yifan Yang, Zhixiang Duan, Tianshi Xie, Fuyu Cao, Pinxi Shen, Peili Song, Piaopiao Jin, Guokang Sun, Shaoqing Xu, Yangwei You, Jingtai Liu

机构 * The Institute of Robotics and Automatic Information System(机器人与自动信息系统研究所) Tianjin Key Laboratory of Intelligent Robotics(智能机器人天津重点实验室) TBI Center, Nankai University, Tianjin 300350, China(南开大学天津中心) Faculty of Robot Science and Engineering, Northeastern University, Shenyang 110819, China(机器人科学与工程学院) The State Key Laboratory of Internet of Things for Smart City(智能城市物联网国家重点实验室) Centre for Artificial Intelligence(人工智能中心) Department of Electromechanical Engineering, University of Macau, Macau SAR, China(机电工程系,澳门大学)

AI总结 FPC-VLA 提出了一种双模型框架,结合视觉-语言-动作模块与监督器,用于预测和纠正机器人操作中的故障,提升了自主系统的可靠性和泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.06911 2025-12-03 cs.NI cs.AI eess.SP

Beyond Connectivity: An Open Architecture for AI-RAN Convergence in 6G

超越连接性:6G中AI-RAN融合的开放式架构

Michele Polese, Niloofar Mohamadi, Salvatore D'Oro, Leonardo Bonati, Tommaso Melodia

机构 * Institute for the Wireless Internet of Things, Northeastern University(无线物联网研究所,东北大学)

AI总结 本文提出了一种开放式架构,用于6G中AI-RAN与电信融合,通过模块化和云原生特性支持异构AI部署,并引入AI-RAN Orchestrator和AI-RAN站点实现灵活的编排和实时处理能力。

Comments Submitted to IEEE for publication, copyright may change without notice. 8 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05235 2025-12-03 astro-ph.CO astro-ph.GA cs.LG

IAEmu: Learning Galaxy Intrinsic Alignment Correlations

IAEmu:学习星系固有对齐相关性

Sneh Pandya, Yuanyuan Yang, Nicholas Van Alfen, Jonathan Blazek, Robin Walters

机构 * Department of Physics, Northeastern University, Boston, MA 02115, USA(东北大学物理系) NSF AI Institute for Artificial Intelligence(国家科学基金会人工智能研究所) Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA(东北大学计算机科学学院)

AI总结 IAEmu通过神经网络模拟器高效预测星系固有对齐相关性,实现高精度且快速的宇宙学推断。

Comments Published in the Open Journal of Astrophysics

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01657 2025-12-02 cs.CV

DB-KAUNet: An Adaptive Dual Branch Kolmogorov-Arnold UNet for Retinal Vessel Segmentation

DB-KAUNet: 一种自适应双分支Kolmogorov-Arnold UNet用于视网膜血管分割

Hongyu Xu, Panpan Meng, Meng Wang, Dayu Hu, Liming Liang, Xiaoqi Sheng

机构 * School of Computer Science and Software Engineering, Southwest University(西南大学计算机科学与软件工程学院) Innovation Centre of Ministry of Education for Development and Diseases, the Sixth Affiliated Hospital, School of Medicine, South China University of Technology(华南理工大学医学院附属第六医院) Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学 Yong Loo Lin 医学院创新与精准眼科健康中心) Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学 Yong Loo Lin 医学院眼科部) College of Medicine and Biological Information Engineering, Northeastern University(东北大学医学院与生物信息工程学院) School of Electrical Engineering Automation, Jiangxi University of Science and Technology(江西理工大学电气工程自动化学院) School of Future Technology, South China University of Technology(华南理工大学未来技术学院)

AI总结 DB-KAUNet通过自适应双分支结构结合CNN和Transformer,提升视网膜血管分割的准确性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00072 2025-12-02 cs.RO

Reconfigurable Auxetic Devices (RADs) for Robotic Surface Manipulation

可重构各向同性装置(RADs)用于机器人表面操控

Jacob Miske, Ahyan Maya, Ahnaf Inkiad, Jeffrey Ian Lipton

机构 * Department of Mechanical and Industrial Engineering, Northeastern University(机械与工业工程系,东北大学) Department of Mathematics, Northeastern University(数学系,东北大学) Khoury College of Computer Sciences, Northeastern University(计算机科学学院,东北大学)

AI总结 本研究提出了一种可重构各向同性装置,通过可重构锁定或嵌入伺服电机实现形状控制,以实现机器人表面操控中的可变表面收缩和扩展。

Comments 13 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19105 2025-12-01 cs.RO

Spectral Signature Mapping from RGB Imagery for Terrain-Aware Navigation

基于RGB影像的光谱签名映射用于地形感知导航

Sarvesh Prajapati, Ananya Trivedi, Nathaniel Hanson, Bruce Maxwell, Taskin Padir

机构 * Northeastern University(东北大学) Massachusetts Institute of Technology(麻省理工学院)

AI总结 本文提出RS-Net,通过RGB影像预测光谱签名,用于机器人地形感知导航和摩擦系数估计。

Comments 8 pages, 11 figures, accepted to Robotic Computing & Communication

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.14652 2025-12-01 cs.CY cs.AI cs.HC cs.SI

Reranking partisan animosity in algorithmic social media feeds alters affective polarization

算法社交媒体信息流中重新排序偏见影响情感极化

Tiziano Piccardi, Martin Saveski, Chenyan Jia, Jeffrey T. Hancock, Jeanne L. Tsai, Michael Bernstein

机构 * Johns Hopkins University(约翰霍普金斯大学) University of Washington(华盛顿大学) Northeastern University(东北大学) Stanford University(斯坦福大学)

AI总结 通过实时重新排序信息流,研究暴露于反民主内容如何影响情感极化,提供因果证据并建立独立评估方法。

Journal ref Science; Volume 390 | Issue 6776; 27 November 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09185 2025-12-01 cs.CV cs.AI

A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality

面向增强现实的认知攻击检测的神经符号框架

Rongqian Chen, Allison Andreyev, Yanming Xiu, Joshua Chilukuri, Shunav Sen, Mahdi Imani, Bin Li, Maria Gorlatova, Gang Tan, Tian Lan

机构 * George Washington University(乔治华盛顿大学) Duke University(杜克大学) Pennsylvania State University(宾夕法尼亚州立大学) Northeastern University(东北大学)

AI总结 本文提出CADAR框架,结合神经网络与符号推理,用于增强现实中的认知攻击检测,通过多模态表示和统计推理提升检测的可解释性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17561 2025-12-01 cs.RO

Robot-mediated physical Human-Human Interaction in Neurorehabilitation: a position paper

机器人介导的神经康复中的人与人物理互动:一种立场论文

Lorenzo Vianello, Matthew Short, Julia Manczurowsky, Emek Barış Küçüktabak, Francesco Di Tommaso, Alessia Noccaro, Laura Bandini, Shoshana Clark, Alaina Fiorenza, Francesca Lunardini, Alberto Canton, Marta Gandolla, Alessandra L. G. Pedrocchi, Emilia Ambrosini, Manuel Murie-Fernandez, Carmen B. Roman, Jesus Tornero, Natacha Leon, Andrew Sawers, Jim Patton, Domenico Formica, Nevio Luigi Tagliamonte, Georg Rauter, Kilian Baur, Fabian Just, Christopher J. Hasson, Vesna D. Novak, Jose L. Pons

机构 * Shirley Ryan AbilityLab(施里尔·瑞安能力实验室) Northwestern University(西北大学) Northeastern University(东北大学) University of Cincinnati(辛辛那提大学) Università Campus Bio-Medico di Roma(罗马大学生物医学校园) Fondazione Santa Lucia(圣拉齐乌斯基金会) University of Genoa(热那亚大学) University of Illinois in Chicago(芝加哥伊利诺伊大学) Canarian Foundation Institute of Neurological Sciences(加那利基金会神经科学研究所) Chalmers University of Technology(挑战者技术大学) Swiss Federal Institute of Technology(瑞士联邦理工学院) University of Basel(巴塞尔大学) Politecnico di Milano(米兰理工大学) Hospital Los Madroños(洛斯马德罗尼斯医院) Universidad Carlos III de Madrid(马德里卡洛斯三世大学) Newcastle University(新castle大学)

AI总结 本文提出机器人介导的人与人物理互动框架,结合治疗师的临床经验与机器人的准确性,旨在提升神经康复的效果。

Comments Accepted in IEEE Reviews in Biomedical Engineering

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.05089 2025-12-01 cs.CV

Nonlinear Motion-Guided and Spatio-Temporal Aware Network for Unsupervised Event-Based Optical Flow

非线性运动引导和时空感知网络用于无监督事件基光流

Zuntao Liu, Hao Zhuang, Junjie Jiang, Yuhang Song, Zheng Fang

机构 * Faculty of Robot Science and Engineering, Northeastern University(机器人科学与工程学院,东北大学)

AI总结 本文提出E-NMSTFlow网络,通过非线性运动补偿和时空感知模块,提升事件基光流估计的精度和性能。

Comments Accepted to ICRA 2025. Project Page: https://wynelio.github.io/E-NMSTFlow

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01584 2025-12-01 cs.AI cs.LG

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models

ReasoningWeekly: 一个面向大语言模型的通用知识和逻辑推理挑战

Zixuan Wu, Francesca Lucchetti, Aleksander Boruch-Gruszecki, Jingmiao Zhao, Carolyn Jane Anderson, Joydeep Biswas, Federico Cassano, Arjun Guha

机构 * Northeastern University(东北大学) Wellesley College(韦尔斯利学院) University of Texas at Austin(德克萨斯大学奥斯汀分校) Cursor

AI总结 ReasoningWeekly是一个基于NPR周日谜题挑战的通用知识和逻辑推理基准,揭示了现有评估中不明显的模型能力差距,并发现了新的推理失败类型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.08135 2025-11-27 cs.SE cs.AI cs.DC cs.PF

Leveraging AI for Productive and Trustworthy HPC Software: Challenges and Research Directions

利用AI实现高效且可信的HPC软件:挑战与研究方向

Keita Teranishi, Harshitha Menon, William F. Godoy, Prasanna Balaprakash, David Bau, Tal Ben-Nun, Abhinav Bhatele, Franz Franchetti, Michael Franusich, Todd Gamblin, Giorgis Georgakoudis, Tom Goldstein, Arjun Guha, Steven Hahn, Costin Iancu, Zheming Jin, Terry Jones, Tze Meng Low, Het Mankad, Narasinga Rao Miniskar, Mohammad Alaul Haque Monil, Daniel Nichols, Konstantinos Parasyris, Swaroop Pophale, Pedro Valero-Lara, Jeffrey S. Vetter, Samuel Williams, Aaron Young

机构 * Oak Ridge National Laboratory(奥克荷厄斯国家实验室) Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室) Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室) Carnegie Mellon University(卡内基梅隆大学) Northeastern University(东北大学) University of Maryland(马里兰大学) SpiralGen Inc.(SpiralGen公司)

AI总结 本文探讨了利用AI改进HPC软件的挑战与研究方向,提出通过Ellora和Durban项目推动AI在HPC软件发展中的应用。

Comments 12 pages, 1 Figure, Accepted at "The 1st International Workshop on Foundational Large Language Models Advances for HPC" LLM4HPC to be held in conjunction with ISC High Performance 2025

Journal ref In: Neuwirth, S., Paul, A.K., Weinzierl, T., Carson, E.C. (eds) High Performance Computing. ISC High Performance 2025. Lecture Notes in Computer Science, vol 16091. Springer, Cham

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19504 2025-11-26 cs.LG stat.ML

Position: The Complexity of Perfect AI Alignment -- Formalizing the RLHF Trilemma

位置:完美AI对齐的复杂性——形式化RLHF三重困境

Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

机构 * Berkeley AI Safety Initiative (BASIS), University of California, Berkeley(伯克利人工智能安全倡议(BASIS),加州大学伯克利分校) AWS Generative AI Innovation Center, Amazon Web Services(亚马逊网络服务生成式人工智能创新中心) Meta AI Stanford University(斯坦福大学) Northeastern University, Seattle, WA, USA(东北大学,西雅图,华盛顿州,美国)

AI总结 研究提出RLHF三重困境,指出在安全、公平和稳健之间存在根本性权衡,并通过复杂性分析证明实现全球代表性需要超多项式计算资源。

Comments Accepted at NeurIPS 2025 Workshop on Socially Responsible and Trustworthy Foundation Models (ResponsibleFM)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18593 2025-11-25 cs.LG cs.SY eess.SY math.SP

Generative Myopia: Why Diffusion Models Fail at Structure

生成性短视:为何扩散模型在结构上失败

Milad Siami

机构 * Department of Electrical and Computer Engineering, Northeastern University(电气与计算机工程系,东北大学)

AI总结 本文提出谱加权扩散模型,通过有效电阻重新对齐变分目标,解决扩散模型在结构上因梯度饥饿导致的生成性短视问题,实现100%的连通性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18516 2025-11-25 cs.CV

Breaking Forgetting: Training-Free Few-Shot Class-Incremental Learning via Conditional Diffusion

打破遗忘:通过条件扩散实现无训练的少样本类增量学习

Haidong Kang, Ketong Qian, Yi Lu

机构 * Northeastern University(东北大学) School of Information and Intelligent Science(信息与智能科学学院) Whiting School of Engineering(工程学院)

AI总结 本文提出无训练的少样本类增量学习方法,通过条件扩散过程替代梯度优化,缓解灾难性遗忘并提升泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18162 2025-11-25 cs.CL

Vector Arithmetic in Concept and Token Subspaces

向量算术在概念和令牌子空间中的应用

Sheridan Feucht, Byron Wallace, David Bau

机构 * Northeastern University(东北大学)

AI总结 该研究通过概念和令牌子空间的向量算术揭示语言模型中的语义与表层信息结构。

Comments 9 pages, 6 figures. NeurIPS 2025 Mechanistic Interpretability Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13290 2025-11-25 cs.LG cs.AI

Prediction of Clinical Complication Onset using Neural Point Processes

利用神经点过程预测临床并发症发作

Sachini Weerasekara, Sagar Kamarthi, Jacqueline Isaacs

机构 * Northeastern University(东北大学)

AI总结 本研究利用神经点过程预测临床并发症的发作,通过六种先进模型和六个重症监护数据集,提升不良事件预测的可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.04919 2025-11-25 cs.LG stat.ML

Learning with Shared Representations: Statistical Rates and Efficient Algorithms

通过共享表示进行学习:统计速率和高效算法

Xiaochun Niu, Lili Su, Jiaming Xu, Pengkun Yang

机构 * Fuqua School of Business, Duke University(达特茅斯大学福克商学院) Department of Electrical and Computer Engineering, Northeastern University(东北大学电气与计算机工程系) Department of Statistics and Data Science, Tsinghua University(清华大学统计与数据科学系)

AI总结 本文提出了一种通过共享表示进行学习的方法,建立了统计误差的新界限,并设计了高效的谱估计器,揭示了协作在迁移学习中的不同最优速率阶段。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17484 2025-11-24 cs.CV

Radar2Shape: 3D Shape Reconstruction from High-Frequency Radar using Multiresolution Signed Distance Functions

Radar2Shape:基于高频雷达的多分辨率符号距离函数的3D形状重建

Neel Sortur, Justin Goodwin, Purvik Patel, Luis Enrique Martinez, Tzofi Klinghoffer, Rajmonda S. Caceres, Robin Walters

机构 * Northeastern University(东北大学) MIT Lincoln Laboratory(麻省理工学院林肯实验室) Massachusetts Institute of Technology(麻省理工学院)

AI总结 Radar2Shape通过多分辨率符号距离函数和去噪扩散模型,实现从部分观测高频雷达信号中重建任意3D形状。

详情

展开后加载摘要…

URL PDF HTML 收藏