arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Michigan(密歇根大学安娜堡分校)

共收录 1281
2404.00424 2026-02-24 q-fin.MF cs.AI cs.CE

Quantformer: from attention to profit with a quantitative transformer trading strategy

Quantformer: 通过量化Transformer交易策略实现从注意力到盈利

Zhaofeng Zhang, Banghao Chen, Shengxin Zhu, Nicolas Langrené

机构 * Guangdong Provincial/Zhuhai Key Laboratory of Interdisciplinary Research and Application for Data Science, Beijing Normal-Hong Kong Baptist University(广东省珠海交叉学科与数据科学应用重点实验室,北京师范大学-香港 Baptist大学) Advanced Institute of Natural Science, Beijing Normal University(北京师范大学自然科学研究院) Department of Mathematical Sciences, Beijing Normal-Hong Kong Baptist University(北京师范大学-香港 Baptist大学数学科学系) Department of Statistics and Data Science, Beijing Normal-Hong Kong Baptist University(北京师范大学-香港 Baptist大学统计与数据科学系) Department of Mathematics, University of Michigan(密歇根大学数学系) Department of Biomedical Informatics, Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学 Yong Loo Lin 医学院生物医学信息学系)

AI总结 Quantformer通过结合Transformer模型和市场情绪信息,提升量化交易策略的预测准确性。

Comments The implementation details and code is available on https://github.com/zhangmordred/QuantFormer

Journal ref Expert Systems with Applications 313 131567 (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.07520 2026-02-24 math.OC cs.AI cs.MA cs.RO cs.SY eess.SY

Resource-Aware Distributed Submodular Maximization: A Paradigm for Multi-Robot Decision-Making

面向资源的分布式子模极大化:多机器人决策制定的范式

Zirui Xu, Vasileios Tzoumas

机构 * Department of Aerospace Engineering, University of Michigan(航空航天工程系,密歇根大学) Robotics Institute, University of Michigan(机器人研究所,密歇根大学)

AI总结 本文提出了一种面向资源的分布式子模极大化算法,用于多机器人决策制定,平衡集中化与去中心化的资源需求与全局最优性。

Comments Updated presentation. Accepted to the 2022 IEEE Conference on Decision and Control (CDC)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.18258 2026-02-23 cs.RO cs.CV

RoEL: Robust Event-based 3D Line Reconstruction

RoEL: 基于事件的稳健3D线条重建

Gwangtak Bae, Jaeho Shin, Seunggu Kang, Junho Kim, Ayoung Kim, Young Min Kim

机构 * Dept. of Electrical and Computer Engineering, Seoul National University(电子与计算机工程系,首尔国立大学) Dept. of Future Automotive Mobility, Seoul National University(未来汽车移动系,首尔国立大学) Dept. of Mechanical Engineering, Seoul National University(机械工程系,首尔国立大学) University of Michigan(密歇根大学)

AI总结 RoEL通过稳健的3D线条重建方法,提升事件相机在复杂环境中的映射与姿态估计性能。

Comments IEEE Transactions on Robotics (T-RO)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.17832 2026-02-23 cs.LG cs.RO

MePoly: Max Entropy Polynomial Policy Optimization

MePoly:最大熵多项式策略优化

Hang Liu, Sangli Teng, Maani Ghaffari

机构 * University of Michigan, Ann Arbor(密歇根大学,安阿伯分校) University of California, Berkeley(加州大学伯克利分校)

AI总结 MePoly通过多项式能量模型实现最大熵策略优化,有效捕捉复杂非凸流形并在多种基准上优于基线方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.25860 2026-02-23 cs.AI cs.CL cs.HC

Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters

通过裁判之眼:推断的思考轨迹提升LLM评分器的可靠性

Xingjian Zhang, Tianhong Gao, Suliang Jin, Tianhao Wang, Teng Ye, Eytan Adar, Qiaozhu Mei

机构 * University of Michigan(密歇根大学) University of California, San Diego(加州大学圣地亚哥分校) University of Minnesota(明尼苏达大学)

AI总结 通过人与LLM协作框架推断思考轨迹,提升LLM评分器的可靠性及人类与LLM之间的一致性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2112.05128 2026-02-23 stat.ML cs.LG

Fair Community Detection and Structure Learning in Heterogeneous Graphical Models

公平社区检测与异质图模型中的结构学习

Davoud Ataee Tarzanagh, Laura Balzano, Alfred O. Hero

机构 * Department of Electrical Engineering and Computer Science, University of Michigan(电气工程与计算机科学系,密歇根大学)

AI总结 本文提出了一种基于ℓ₁正则化的伪似然方法,用于在异质图模型中实现公平的社区检测和结构学习。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.17030 2026-02-20 cs.CV cs.RO

Patch-Based Spatial Authorship Attribution in Human-Robot Collaborative Paintings

基于补丁的空间作者归属在人类-机器人协作绘画中

Eric Chen, Patricia Alves-Oliveira

机构 * Robotics, University of Michigan, Ann Arbor, Michigan, United States(机器人学,密歇根大学,安娜堡,密歇根,美国)

AI总结 本文提出了一种基于补丁的空间作者归属方法,用于人类-机器人协作绘画,通过实验验证在数据稀缺情况下有效区分混合作者身份。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16846 2026-02-20 cs.RO

Sound of Touch: Active Acoustic Tactile Sensing via String Vibrations

触觉之声:通过弦振动实现主动声学触觉感知

Xili Yi, Ying Xing, Zachary Manchester, Nima Fazeli

机构 * University of Michigan(密歇根大学) MIT(麻省理工学院)

AI总结 通过振动弦实现主动声学触觉感知,提供轻量级硬件、物理模拟工具和实时推理管道,用于机器人表面的触觉感知与滑动检测。

Comments 12 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.21862 2026-02-20 cs.CV

Towards Scalable Language-Image Pre-training for 3D Medical Imaging

面向3D医学影像的语言-图像预训练的可扩展性

Chenhui Zhao, Yiwei Lyu, Asadur Chowdury, Edward Harake, Akhil Kondepudi, Akshay Rao, Xinhai Hou, Honglak Lee, Todd Hollon

机构 * University of Michigan(密歇根大学)

AI总结 HLIP通过引入层次注意力机制,实现对3D医学影像的可扩展语言-图像预训练,提升脑部MRI和头部CT的性能表现。

Comments TMLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.16033 2026-02-19 cs.HC cs.AI

Transforming GenAI Policy to Prompting Instruction: An RCT of Scalable Prompting Interventions in a CS1 Course

将生成式AI政策转化为提示指令:一项在CS1课程中可扩展的提示干预随机对照试验

Ruiwei Xiao, Runlong Ye, Xinying Hou, Jessica Wen, Harsh Kumar, Michael Liut, John Stamper

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Toronto(多伦多大学) University of Michigan(密歇根大学) University of Toronto Mississauga(多伦多大学滑铁卢分校)

AI总结 本研究通过随机对照试验验证了基于ICAP框架的提示干预在提升学生提示技能和考试成绩方面的有效性,为生成式AI教育政策的改进提供了理论和实践指导。

Comments 11 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15955 2026-02-19 cs.LG stat.AP

Adaptive Semi-Supervised Training of P300 ERP-BCI Speller System with Minimum Calibration Effort

自适应半监督训练的P300 ERP-BCI拼写系统:最小校准努力

Shumeng Chen, Jane E. Huggins, Tianwen Ma

机构 * Department of Biostatistics and Bioinformatics(生物统计学与生物信息学系) Rollins School of Public Health, Emory University(埃默里大学罗林斯公共卫生学院) Department of Physical Medicine and Rehabilitation(物理医学与康复系) Department of Biomedical Engineering(生物医学工程系) University of Michigan(密歇根大学)

AI总结 本文提出了一种自适应半监督学习框架,通过最小化校准努力提升P300 ERP-BCI拼写系统的实时拼写效率。

Comments 8 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10531 2026-02-19 stat.ML cs.LG math.ST stat.TH

From Collapse to Improvement: Statistical Perspectives on the Evolutionary Dynamics of Iterative Training on Contaminated Sources

从崩溃到改进:对迭代训练在受污染源上演变动力学的统计视角

Soham Bakshi, Sunrit Chakraborty

机构 * Department of Statistics, University of Michigan, Ann Arbor(统计系,密歇根大学,安娜堡) Department of Statistical Science, Duke University(统计科学系,杜克大学)

AI总结 本文从统计学角度研究了在受污染数据上迭代训练生成模型的演变动力学,发现通过适当样本量训练可避免崩溃并恢复真实分布。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15767 2026-02-18 cs.RO cs.AI cs.HC

Robot-Assisted Social Dining as a White Glove Service

机器人辅助社交用餐作为白手套服务

Atharva S Kashyap, Ugne Aleksandra Morkute, Patricia Alves-Oliveira

机构 * University of Michigan(密歇根大学) Leiden University(莱顿大学)

AI总结 本研究通过参与设计和AI工具,提出机器人辅助社交用餐的白手套服务理念,强调多模态输入、情境敏感行为及角色扩展,以提升残疾人在野外社交用餐中的独立性和尊严。

Comments 20 pages, 9 figures. Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17900 2026-02-18 cs.CL

MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation

MedPlan: 一种基于RAG的双阶段系统,用于个性化医疗计划生成

Hsin-Ling Hsu, Cong-Tinh Dao, Luning Wang, Zitao Shuai, Thao Nguyen Minh Phan, Jun-En Ding, Chun-Chieh Liao, Pengfei Hu, Xiaoxue Han, Chih-Ho Hsu, Dongsheng Luo, Wen-Chih Peng, Feng Liu, Fang-Ming Hung, Chenwei Wu

机构 * National Chengchi University(国立政治大学) National Yang Ming Chiao Tung University(国立阳明交通大学) Can Tho University(庆坚大学) University of Michigan(密歇根大学) Stevens Institute of Technology(史泰文斯理工学院) Far Eastern Memorial Hospital(东方纪念医院) Florida International University(佛罗里达国际大学)

AI总结 MedPlan通过双阶段RAG框架,结合SOAP方法,提升个性化医疗计划生成的准确性和结构化质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.14506 2026-02-17 cs.LG

Covariance-Aware Transformers for Quadratic Programming and Decision Making

具有协方差意识的变换器用于二次规划和决策制定

Kutay Tire, Yufan Zhang, Ege Onur Taga, Samet Oymak

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Michigan(密歇根大学)

AI总结 本文提出Time2Decide方法,通过显式利用协方差矩阵提升变换器在二次规划和决策制定中的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.12922 2026-02-16 cs.CV

Beyond Benchmarks of IUGC: Rethinking Requirements of Deep Learning Methods for Intrapartum Ultrasound Biometry from Fetal Ultrasound Videos

超越IUGC基准:重新思考深度学习方法在胎儿超声视频中的产程超声生物测量需求

Jieyun Bai, Zihao Zhou, Yitong Tang, Jie Gan, Zhuonan Liang, Jianan Fan, Lisa B. Mcguire, Jillian L. Clarke, Weidong Cai, Jacaueline Spurway, Yubo Tang, Shiye Wang, Wenda Shen, Wangwang Yu, Yihao Li, Philippe Zhang, Weili Jiang, Yongjie Li, Salem Muhsin Ali Binqahal Al Nasim, Arsen Abzhanov, Numan Saeed, Mohammad Yaqub, Zunhui Xian, Hongxing Lin, Libin Lan, Jayroop Ramesh, Valentin Bacher, Mark Eid, Hoda Kalabizadeh, Christian Rupprecht, Ana I. L. Namburete, Pak-Hei Yeung, Madeleine K. Wyburd, Nicola K. Dinsdale, Assanali Serikbey, Jiankai Li, Sung-Liang Chen, Zicheng Hu, Nana Liu, Yian Deng, Wei Hu, Cong Tan, Wenfeng Zhang, Mai Tuyet Nhi, Gregor Koehler, Rapheal Stock, Klaus Maier-Hein, Marawan Elbatel, Xiaomeng Li, Saad Slimani, Victor M. Campello, Benard Ohene-Botwe, Isaac Khobo, Yuxin Huang, Zhenyan Han, Hongying Hou, Di Qiu, Zheng Zheng, Gongning Luo, Dong Ni, Yaosheng Lu, Karim Lekadir, Shuo Li

机构 * Department of Cardiovascular Surgery, The First Affiliated Hospital of Jinan University, Jinan University, Guangzhou, China Auckland Bioengineering Institute, The University of Auckland, Auckland, New Zealand School of Computer Science, University of Sydney, Sydney, Australia Neonatology, Sydney Medical School Nepean, University of Sydney Nepean Hospital, Penrith, New South Wales, Australia Discipline of Medical Imaging, Faculty of Medicine Health, Susan Wakil Health Building, University of Sydney, Camperdown, New South Wales, Australia Medical Imaging, Orange Health Service, Orange, New South Wales, Australia University of Electronic Science Henan Kaifeng College of Science Technology Changchun University of Science University of Western Brittany, Brest, France Sichuan University, Chengdu, China Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Masdar, Abu Dhabi College of Computer Science Engineering, Chongqing University of Technology, Chongqing, China Oxford Machine Learning in NeuroImaging Lab, Department of Computer Science, University of Oxford, Oxford, United Kingdom Visual Geometry Group, University of Oxford, Oxford, United Kingdom School of Computer Science Engineering, Nanyang Technological University, Singapore The University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China College of Computer Information Science, Chongqing Normal University, Chongqing, China The University of Manchester, Manchester, United Kingdom Southwest University, Chongqing, China Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany Department of Electronic Computer Engineering, The Hong Kong University of Science Chief Medical Officer Deepecho Ibn Rochd CHU, Hassan II University, Casablanca, Morocco Department of Radiography, School of Biomedical Allied Health Sciences, College of Health Sciences, University of Ghana, Accra Department of Human Biology, Biomedical Engineering Research Center, University of Cape Town, Cape Town, South Africa Gynecology Center, Zhujiang Hospital, Southern Medical University, Guangzhou, China Department of Obstetrics Gynecology, Third Affiliated Hospital of Sun Yat-sen University, Guangzhou, China Gynecology, The First Affiliated Hospital of Jinan University, Guangzhou, China Children's Medical Center, Guangdong Provincial Clinical Research Center for Child Health, Guangzhou, China Engineering Division, King Abdullah University of Science Shenzhen University, Shenzhen, China Artificial Intelligence in Medicine Lab (BCN-AIM), Barcelona, Spain School of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA

AI总结 本研究提出了一种多任务自动测量框架,用于产程超声生物测量,旨在解决资源有限环境下超声技师短缺的问题,并通过公开数据集和基准结果促进该领域的发展。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.12587 2026-02-16 cs.LG

Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers

多头注意力作为MoE变换器中灾难性遗忘的来源

Anrui Chen, Ruijun Huang, Xin Zhang, Fang Dong, Hengjie Cao, Zhendong Huang, Yifeng Yang, Mengyi Chen, Jixian Zhou, Mingzhi Dong, Yujiang Wang, Jinlong Hou, Qin Lv, Robert P. Dick, Yuan Cheng, Tun Lu, Fan Yang, Li Shang

机构 * Fudan University, Shanghai, China(复旦大学) University of Bath, Bath, United Kingdom(巴斯大学) Oxford Suzhou Centre for Advanced Research, Suzhou, China(牛津苏滁研究中心) Shanghai Innovation Institute, Shanghai, China(上海创新研究院) Department of Computer Science, University of Colorado Boulder, Colorado, USA(计算机科学系,科罗拉多大学博尔德分校) Department of Electrical Engineering and Computer Science, University of Michigan(电气工程与计算机科学系,密歇根大学)

AI总结 本文提出MH-MoE方法,通过头级路由减少MoE变换器中的灾难性遗忘,有效降低连续学习中的遗忘率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.12556 2026-02-16 cs.LG cs.AI

SD-MoE: Spectral Decomposition for Effective Expert Specialization

SD-MoE:通过谱分解实现有效的专家专业化

Ruijun Huang, Fang Dong, Xin Zhang, Hengjie Cao, Zhendong Huang, Anrui Chen, Jixian Zhou, Mengyi Chen, Yifeng Yang, Mingzhi Dong, Yujiang Wang, Jinlong Hou, Qin Lv, Robert P. Dick, Yuan Cheng, Fan Yang, Tun Lu, Chun Zhang, Li Shang

机构 * College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China(复旦大学计算机科学与人工智能学院) University of Bath, Bath, United Kingdom(巴斯大学) Oxford Suzhou Centre for Advanced Research, Suzhou, China(牛津苏泽研究中心) Department of Electrical Engineering and Computer Science, University of Michigan(密歇根大学电气工程与计算机科学系) Shanghai Innovation Institute, Shanghai, China(上海创新研究院) Department of Computer Science, University of Colorado Boulder, Colorado, USA(科罗拉多大学博尔德分校计算机科学系) Research Institute of Tsinghua University in Shenzhen, Shenzhen, China(清华大学深圳研究院) Greater Bay Area National Center of Technology Innovation, Research Institute of Tsinghua University in Shenzhen, Shenzhen, China(粤港澳大湾区国家技术创新中心,清华大学深圳研究院) School of Microelectronics, Fudan University, Shanghai, China(复旦大学微电子学院)

AI总结 SD-MoE通过谱分解解决MoE中专家专业化不足的问题,提升模型性能并兼容多种现有架构。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.12351 2026-02-16 cs.RO cs.CV

LongNav-R1: Horizon-Adaptive Multi-Turn RL for Long-Horizon VLA Navigation

LongNav-R1: 基于水平自适应的多轮强化学习用于长周期视觉语言导航

Yue Hu, Avery Xi, Qixin Xiao, Seth Isaacson, Henry X. Liu, Ram Vasudevan, Maani Ghaffari

机构 * University of Michigan(密歇根大学)

AI总结 LongNav-R1通过多轮强化学习提升长周期视觉语言导航性能,实现高效样本利用和多样化导航行为。

Comments VLA, Navigation

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.07909 2026-02-16 cs.LG cs.AI cs.CV

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning

解释并缓解对比多模态学习中的模态差距

Can Yaras, Siyi Chen, Peng Wang, Qing Qu

机构 * Department of Electrical Engineering \& Computer Science, University of Michigan

AI总结 本文通过分析对比多模态学习中的模态差距成因,提出通过温度调度和模态交换等策略缓解模态差距,从而提升多模态任务性能。

Comments The first two authors contributed equally to this work

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.04112 2026-02-16 cs.LG cs.AI eess.SP stat.ML

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

深度过参数化低秩学习与适应中的可压缩动力学

Can Yaras, Peng Wang, Laura Balzano, Qing Qu

机构 * Department of Electrical Engineering \& Computer Science, University of Michigan

AI总结 本研究提出Deep LoRA方法,通过深度过参数化低秩学习与适应中的可压缩动力学,提升语言模型微调效率并减少过拟合。

Comments Accepted at ICML'24 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.17592 2026-02-16 cs.IR cs.LG stat.ML

Low-Rank Online Dynamic Assortment with Dual Contextual Information

低秩在线动态搭配与双上下文信息

Seong Jin Lee, Will Wei Sun, Yufeng Liu

机构 * Department of Statistics and Operations Research, University of North Carolina, Chapel Hill(统计与运筹学系,北卡罗来纳大学 Chapel Hill 分校) Daniels School of Business, Purdue University(Daniels 商学院,普渡大学) Department of Statistics, University of Michigan(统计系,密歇根大学)

AI总结 本文提出一种低秩动态搭配模型,通过利用双上下文信息和上置信界方法,有效解决高维环境下在线决策中的探索-利用权衡问题,并在理论和实验上均表现出优越性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11401 2026-02-13 cs.CV cs.LG

Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation

潜在强制:重新排列扩散轨迹以生成像素空间图像

Alan Baade, Eric Ryan Chan, Kyle Sargent, Changan Chen, Justin Johnson, Ehsan Adeli, Li Fei-Fei

机构 * stanford(斯坦福大学) umich(密歇根大学)

AI总结 本文提出潜在强制方法,通过重新排列扩散轨迹提升像素空间图像生成效率,实现端到端建模优势,取得ImageNet上的新突破。

Comments 8 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11185 2026-02-13 cs.LG cs.AI

Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy

Spectra: 重新思考在谱各向异性下大语言模型的优化器

Zhendong Huang, Hengjie Cao, Fang Dong, Ruijun Huang, Mengyi Chen, Yifeng Yang, Xin Zhang, Anrui Chen, Mingzhi Dong, Yujiang Wang, Jinlong Hou, Qin Lv, Robert P. Dick, Yuan Cheng, Fan Yang, Tun Lu, Li Shang

机构 * Fudan University, Shanghai, China(复旦大学) University of Bath, Bath, United Kingdom(巴斯大学) Oxford Suzhou Centre for Advanced Research, Suzhou, China(牛津苏格兰先进研究中心) Shanghai Innovation Institute, Shanghai, China(上海创新研究院) Department of Computer Science, University of Colorado Boulder, Colorado, USA(计算机科学系,科罗拉多大学博尔德分校) Department of Electrical Engineering and Computer Science, University of Michigan(电气工程与计算机科学系,密歇根大学)

AI总结 Spectra通过抑制主导低秩尖峰子空间并减少优化器状态内存,提升了大语言模型的训练效率和下游准确率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20123 2026-02-13 cs.LG cs.CV

Understanding Generalization in Diffusion Distillation via Probability Flow Distance

通过概率流距离理解扩散蒸馏中的泛化

Huijie Zhang, Zijian Huang, Siyi Chen, Jinfan Zhou, Zekai Zhang, Peng Wang, Qing Qu

机构 * University of Michigan(密歇根大学) University of Macau(澳门大学) University of Chicago(芝加哥大学)

AI总结 本研究通过引入概率流距离(PFD)度量标准,揭示了扩散蒸馏中泛化能力的关键行为,包括从记忆到泛化的缩放、双下降动态和偏差-方差分解。

Comments 41 pages, 15 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.21088 2026-02-13 cs.LG cs.CR cs.CV

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models

浅层扩散:通过扩散模型中低维子空间实现的鲁棒且不可见的水印技术

Wenda Li, Huijie Zhang, Qing Qu

机构 * University of Michigan(密歇根大学)

AI总结 本文提出Shallow Diffuse,一种通过扩散模型中低维子空间实现鲁棒且不可见水印的技术,提升了水印的检测性和数据生成的一致性。

Comments NeurIPS 2025 Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.09181 2026-02-13 cs.CV

Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures

通过多阶段框架和定制多解码器架构提高扩散模型的效率

Huijie Zhang, Yifu Lu, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu

机构 * University of Michigan(密歇根大学) Michigan State University(密歇根州立大学)

AI总结 本文提出多阶段框架和定制多解码器架构,以提高扩散模型的训练和采样效率。

Comments The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11004 2026-02-12 cs.CV cs.AI cs.RO cs.SY eess.SY

Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception

增强自动驾驶车辆感知的多租户DNN推理可预测性

Liangkai Liu, Kang G. Shin, Jinkyu Lee, Chengmo Yang, Weisong Shi

机构 * Department of Electrical Engineering and Computer Science, University of Michigan(电气工程与计算机科学系,密歇根大学) Department of Computer Science and Engineering, Yonsei University(计算机科学与工程系,延世大学) Department of Computer and Information Sciences, University of Delaware(计算机与信息科学系,特拉华大学)

AI总结 PP-DNN通过动态选择关键帧和ROIs提升自动驾驶车辆感知的DNN推理可预测性。

Comments 13 pages, 12 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10261 2026-02-12 cs.LG stat.AP stat.ML

Kernel-Based Learning of Chest X-ray Images for Predicting ICU Escalation among COVID-19 Patients

基于核方法的胸片学习用于预测新冠患者ICU升级

Qiyuan Shi, Jian Kang, Yi Li

机构 * University of Michigan(密歇根大学) Department of Biostatistics(生物统计学系)

AI总结 本文提出GLIMARK方法,通过多核学习扩展以处理指数族输出变量,用于预测新冠患者ICU升级并提取临床特征。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05252 2026-02-12 cs.CL

Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks

版权侦探:一种用于证据LLM闪烁版权泄露风险的取证系统

Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi Ma, Yun Huang, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang

机构 * Pine AI The University of Texas at Austin(德克萨斯大学奥斯汀分校) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Duke University(杜克大学) University of Michigan(密歇根大学) Stevens Institute of Technology(史蒂文斯理工学院) Johns Hopkins University(约翰霍普金斯大学) University of Notre Dame(圣母大学) The Pennsylvania State University(宾夕法尼亚州立大学)

AI总结 Copyright Detective 是一种交互式系统,用于检测和可视化LLM输出中的版权风险,通过整合多种检测方法实现系统性审计。

详情

展开后加载摘要…

URL PDF HTML 收藏