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 1290
2511.21741 2025-12-01 cs.CL cs.LG stat.ML

A Multiscale Geometric Method for Capturing Relational Topic Alignment

一种多尺度几何方法用于捕捉关系主题对齐

Conrad D. Hougen, Karl T. Pazdernik, Alfred O. Hero

机构 * University of Michigan(密歇根大学) Pacific Northwest National Laboratory(太平洋西北国家实验室)

AI总结 本文提出一种多尺度几何方法,结合多模态文本和合著者网络数据,以捕捉关系主题对齐并识别罕见话题结构。

Comments 5 pages, 3 figures, 2025 IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14495 2025-12-01 cs.CL cs.AI cs.LG

Temporal Consistency for LLM Reasoning Process Error Identification

LLM推理过程错误识别中的时序一致性

Jiacheng Guo, Yue Wu, Jiahao Qiu, Kaixuan Huang, Xinzhe Juan, Ling Yang, Mengdi Wang

机构 * Department of Electrical & Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系) AI Lab, Princeton University(普林斯顿大学人工智能实验室) Department of Computer Science & Engineering, University of Michigan(密歇根大学计算机科学与工程系)

AI总结 本文提出了一种基于时序一致性的LLM推理过程错误识别方法,通过迭代自我反思提升验证准确性,在多个基准测试中实现了优于基线方法的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20841 2025-11-27 cs.RO

OVAL-Grasp: Open-Vocabulary Affordance Localization for Task Oriented Grasping

OVAL-Grasp:面向任务的开放词汇表征定位抓取

Edmond Tong, Advaith Balaji, Anthony Opipari, Stanley Lewis, Zhen Zeng, Odest Chadwicke Jenkins

机构 * University of Michigan, Ann Arbor, MI, USA(密歇根大学) J.P. Morgan AI Research(摩根大通AI研究)

AI总结 OVAL-Grasp通过结合大语言模型和视觉-语言模型,实现面向任务的开放词汇表征抓取,有效识别物体部分并提高抓取成功率。

Comments 10 pages, 7 figures, 3 tables. Presented at the 2025 International Symposium on Experimental Robotics (ISER)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.18477 2025-11-27 cs.IR cs.AI cs.LG

Personalized Image Generation for Recommendations Beyond Catalogs

推荐超越目录的个性化图像生成

Gabriel Patron, Zhiwei Xu, Ishan Kapnadak, Felipe Maia Polo

机构 * University of Michigan(密歇根大学)

AI总结 REBECA通过直接学习隐含反馈信号实现高效个性化图像生成,无需微调扩散模型,提升大规模用户群体的个性化效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20501 2025-11-26 cs.CV cs.LG

A Physics-Informed Loss Function for Boundary-Consistent and Robust Artery Segmentation in DSA Sequences

一种用于DSA序列中边界一致且鲁棒动脉分割的物理信息损失函数

Muhammad Irfan, Nasir Rahim, Khalid Mahmood Malik

机构 * College of Innovation and Technology(创新与技术学院) University of Michigan-Flint(密歇根大学弗林特分校)

AI总结 本文提出了一种基于物理的损失函数,用于提高DSA序列中动脉分割的边界一致性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20467 2025-11-26 cs.RO cs.SY eess.SY

Power-Efficient Autonomous Mobile Robots

低功耗自主移动机器人

Liangkai Liu, Weisong Shi, Kang G. Shin

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

AI总结 本文提出pNav系统,通过联合优化自主移动机器人物理和网络子系统,显著提升其功率效率,实测显示功率消耗降低38.1%。

Comments 13 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19984 2025-11-26 cs.LG

Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization

重新思考基于扩散距离引导的压力主要化的消息传递神经网络

Haoran Zheng, Renchi Yang, Yubo Zhou, Jianliang Xu

机构 * Hong Kong Baptist University(香港 Baptist 大学) University of Michigan(密歇根大学)

AI总结 本文提出DDSM模型,通过引入扩散距离和压力主要化技术,解决MPNNs中的过度平滑和相关性问题,并在多种图结构上取得优异性能。

Comments Accepted by SIGKDD 2026. The code is available at https://github.com/HaoranZ99/DDSM

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04774 2025-11-26 cs.LG cs.AR

SLOFetch: Compressed-Hierarchical Instruction Prefetching for Cloud Microservices

SLOFetch:面向云微服务的压缩分层指令预取

Zerui Bao, Di Zhu, Liu Jiang, Shiqi Sheng, Ziwei Wang, Haoyun Zhang

机构 * University of Michigan(密歇根大学) Santa Clara University(圣克拉拉大学) Carnegie Mellon University(卡内基梅隆大学) University of Pennsylvania(宾夕法尼亚大学)

AI总结 SLOFetch通过压缩分层指令预取技术,优化云微服务的指令预取效率,减少芯片状态并提升网络化服务的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.01772 2025-11-26 eess.IV cs.AI cs.CV

LoRA-based methods on Unet for transfer learning in Subarachnoid Hematoma Segmentation

基于LoRA的方法在Unet上的应用用于亚急性硬膜下出血的迁移学习

Cristian Minoccheri, Matthew Hodgman, Haoyuan Ma, Rameez Merchant, Emily Wittrup, Craig Williamson, Kayvan Najarian

机构 * University of Michigan(密歇根大学)

AI总结 本研究提出基于LoRA的Unet方法,用于亚急性硬膜下出血的迁移学习,通过参数高效的方法提升分割性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.15447 2025-11-26 cs.CV cs.RO

LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene Reconstruction

LiHi-GS:基于LiDAR监督的高斯点云法用于高速公路场景重建

Pou-Chun Kung, Xianling Zhang, Katherine A. Skinner, Nikita Jaipuria

机构 * Latitude AI Department of Robotics, University of Michigan(机器人学系,密歇根大学)

AI总结 LiHi-GS通过LiDAR监督提升高速公路场景重建与合成,解决传统方法在高速场景和LiDAR利用上的不足。

Comments RA-L 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14533 2025-11-26 stat.ME cs.LG

The Traveling Bandit: A Framework for Bayesian Optimization with Movement Costs

旅行窃贼:具有移动成本的贝叶斯优化框架

Qiyuan Chen, Raed Al Kontar

机构 * University of Michigan(密歇根大学)

AI总结 本文提出了一种具有移动成本的贝叶斯优化框架,通过整合旅行商问题解决方法,有效降低移动成本并保持与传统方法相当的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.07154 2025-11-26 cs.LG cs.AI

Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning

重新思考扩展测试时间计算时的微调:限制置信度可提升数学推理

Feng Chen, Allan Raventos, Nan Cheng, Surya Ganguli, Shaul Druckmann

机构 * Stanford University(斯坦福大学) University of Michigan(密歇根大学)

AI总结 通过限制模型置信度改进数学推理,研究发现传统交叉熵损失与测试时间策略pass@N存在不一致,提出改进的训练损失以提升性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19427 2025-11-25 cs.SE cs.AI

Prompt Less, Smile More: MTP with Semantic Engineering in Lieu of Prompt Engineering

无需提示,微笑更多:通过语义工程替代提示工程的MTP

Jayanaka L. Dantanarayana, Savini Kashmira, Thakee Nathees, Zichen Zhang, Krisztian Flautner, Lingjia Tang, Jason Mars

机构 * University of Michigan(密歇根大学) Jaseci Labs(Jaseci实验室)

AI总结 通过语义工程替代提示工程,提升AI集成编程中提示的准确性与开发者效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19066 2025-11-25 cs.LG cs.AI

Mitigating Participation Imbalance Bias in Asynchronous Federated Learning

缓解异步联邦学习中的参与不平衡偏差

Xiangyu Chang, Manyi Yao, Srikanth V. Krishnamurthy, Christian R. Shelton, Anirban Chakraborty, Ananthram Swami, Samet Oymak, Amit Roy-Chowdhury

机构 * University of California, Riverside(加州大学河滨分校) Indian Institute of Science(印度科学研究院) University of Michigan, Ann Arbor(密歇根大学安娜堡分校) DEVCOM Army Research Laboratory(陆军研究实验室)

AI总结 本文提出ACE和ACED方法,通过立即非缓冲更新缓解异步联邦学习中的参与不平衡偏差,提升模型鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18640 2025-11-25 cs.CV cs.AI cs.LG

Health system learning achieves generalist neuroimaging models

健康系统学习实现通用神经影像模型

Akhil Kondepudi, Akshay Rao, Chenhui Zhao, Yiwei Lyu, Samir Harake, Soumyanil Banerjee, Rushikesh Joshi, Anna-Katharina Meissner, Renly Hou, Cheng Jiang, Asadur Chowdury, Ashok Srinivasan, Brian Athey, Vikas Gulani, Aditya Pandey, Honglak Lee, Todd Hollon

机构 * Machine Learning in Neurosurgery Lab University of Michigan(密歇根大学机器学习神经外科实验室) University of Michigan Computational Medicine and Bioinformatics(密歇根大学计算医学与生物信息学) University of Michigan Computer Science and Engineering(密歇根大学计算机科学与工程) University of Michigan Radiology(密歇根大学放射学)

AI总结 NeuroVFM通过健康系统学习范式,在临床MRI和CT影像上训练,实现高性能通用神经影像模型,提升放射学诊断和报告生成的准确性与临床实用性。

Comments 53 pages, 4 main figures, 10 extended data figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02387 2025-11-25 cs.RO cs.SY eess.SY

RGBSQGrasp: Inferring Local Superquadric Primitives from Single RGB Image for Graspability-Aware Bin Picking

RGBSQGrasp: 从单张RGB图像推断局部超二次曲面原语以实现抓取感知的托盘拾取

Yifeng Xu, Fan Zhu, Ye Li, Sebastian Ren, Xiaonan Huang, Yuhao Chen

机构 * University of Michigan(密歇根大学) University of Waterloo(滑铁卢大学) Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学) University College London(伦敦大学学院)

AI总结 RGBSQGrasp通过单目RGB图像推断抓取姿态,利用超二次曲面原语提升托盘拾取任务的抓取稳定性和适应性。

Comments 8 pages, 6 figures, IROS2025 RGMCW Best Workshop Paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2202.02419 2025-11-25 eess.SY cs.LG cs.SY

Learning to Admit Optimally in an $M/M/k/k+N$ Queueing System with Unknown Service Rate

在具有未知服务速率的$M/M/k/k+N$排队系统中学习最优接纳

Saghar Adler, Mehrdad Moharrami, Vijay Subramanian

机构 * TikTok University of Iowa(爱荷华大学) University of Michigan(密歇根大学)

AI总结 在具有未知服务速率的$M/M/k/k+N$排队系统中,通过参数学习方法设计最优调度策略以最大化长期平均奖励。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13827 2025-11-24 cs.CL cs.AI

Bridging the Semantic Gap: Contrastive Rewards for Multilingual Text-to-SQL with GRPO

弥合语义鸿沟:基于GRPO的多语言文本到SQL的对比奖励

Ashish Kattamuri, Ishita Prasad, Meetu Malhotra, Arpita Vats, Rahul Raja, Albert Lie

机构 * Independent Researcher(独立研究者) University of Michigan(密歇根大学) Harrisburg University of Science(哈里斯堡科学大学) Forward Labs AI

AI总结 本研究提出基于GRPO的对比奖励方法,提升多语言文本到SQL系统的执行与语义准确性,通过对比奖励信号实现语义对齐,实验表明小模型在少量数据下表现优于大模型。

Comments 20th International Workshop on Semantic and Social Media Adaptation & Personalization

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15994 2025-11-21 cs.AI cs.CL

CARE-RAG - Clinical Assessment and Reasoning in RAG

CARE-RAG - 临床评估与推理中的RAG

Deepthi Potluri, Aby Mammen Mathew, Jeffrey B DeWitt, Alexander L. Rasgon, Yide Hao, Junyuan Hong, Ying Ding

机构 * Department of Computer Science(计算机科学系) University of Texas at Austin(德克萨斯大学奥斯汀分校) Behavioral Science and Psychiatry(行为科学与精神病学) Department of Statistics(统计学系) University of Michigan(密歇根大学) School of Information(信息学院)

AI总结 CARE-RAG研究了检索增强生成在临床环境中的推理能力,提出评估框架以确保推理的准确性和一致性。

Comments The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15105 2025-11-20 cs.RO

Painted Heart Beats

Angshu Adhya, Cindy Yang, Emily Wu, Rishad Hasan, Abhishek Narula, Patrícia Alves-Oliveira

机构 * University of Michigan(密歇根大学)

Comments 4 pages, 2 figures, ICRA 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14784 2025-11-20 stat.ML cs.LG math.ST stat.CO stat.ME stat.TH

Convex Clustering Redefined: Robust Learning with the Median of Means Estimator

Sourav De, Koustav Chowdhury, Bibhabasu Mandal, Sagar Ghosh, Swagatam Das, Debolina Paul, Saptarshi Chakraborty

机构 * Indian Statistical Institute, Kolkata(印度统计研究院,科希马) Department of Statistics and Data Science, University of Texas at Austin(德克萨斯大学奥斯汀分校统计与数据科学系) Electronics and Communication Sciences, Indian Statistical Institute, Kolkata(印度统计研究院,科希马电子与通信科学) Department of Statistics, University of Oxford(牛津大学统计系) Department of Statistics, University of Michigan(密歇根大学统计系)

Comments Accepted in AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02249 2025-11-20 cs.RO cs.AI

Natural Selection via Foundation Models for Soft Robot Evolution

Changhe Chen, Xiaohao Xu, Xiangdong Wang, Xiaonan Huang

机构 * University of Michigan-Ann Arbor(密歇根大学安娜堡分校)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.14086 2025-11-19 cs.CV cs.AI cs.CL

Error-Driven Scene Editing for 3D Grounding in Large Language Models

Yue Zhang, Zun Wang, Han Lin, Jialu Li, Jianing Yang, Yonatan Bitton, Idan Szpektor, Mohit Bansal

机构 * UNC Chapel Hill(北卡罗来纳大学教堂山分校) University of Michigan(密歇根大学) Google Research(谷歌研究)

Comments Code: https://github.com/zhangyuejoslin/Deer-3D

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13744 2025-11-19 cs.CV cs.AI cs.RO

nuCarla: A nuScenes-Style Bird's-Eye View Perception Dataset for CARLA Simulation

Zhijie Qiao, Zhong Cao, Henry X. Liu

机构 * Civil and Environmental Engineering, University of Michigan(密歇根大学土木与环境工程学院) Transportation Research Institute, University of Michigan(密歇根大学交通研究所)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.23530 2025-11-19 cs.CV cs.AI

Imaging-Based Mortality Prediction in Patients with Systemic Sclerosis

Alec K. Peltekian, Karolina Senkow, Gorkem Durak, Kevin M. Grudzinski, Bradford C. Bemiss, Jane E. Dematte, Carrie Richardson, Nikolay S. Markov, Mary Carns, Kathleen Aren, Alexandra Soriano, Matthew Dapas, Harris Perlman, Aaron Gundersheimer, Kavitha C. Selvan, John Varga, Monique Hinchcliff, Krishnan Warrior, Catherine A. Gao, Richard G. Wunderink, GR Scott Budinger, Alok N. Choudhary, Anthony J. Esposito, Alexander V. Misharin, Ankit Agrawal, Ulas Bagci

机构 * Department of Computer Science, Northwestern University, Evanston, IL 60208, USA Division of Pulmonary Critical Care Medicine, Northwestern University, Chicago, IL 60611, USA Machine \& Hybrid Intelligence Lab, Department of Radiology, Northwestern University, Chicago, IL 60611, USA Division of Rheumatology, Northwestern University, Chicago, IL 60611, USA Division of Rheumatology, University of Michigan, Ann Arbor, MI 48109, USA Section of Rheumatology, Allergy \& Immunology, Yale University, New Haven, CT 06520, USA Department of Electrical Computer Engineering, Northwestern University, Evanston, IL 60208, USA

Comments 11 pages, 4 figures, 1 table, accepted in MICCAI PRIME 2025

Journal ref MICCAI PRIME 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.15902 2025-11-19 cs.LG cs.AI cs.CL

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

Zheng Chen, Yushi Feng, Jisheng Dang, Yue Deng, Changyang He, Hongxi Pu, Haoxuan Li, Bo Li

机构 * Computer Science and Engineering, Hong Kong University of Science and Technology(香港科技大学计算机科学与工程学院) School of Computing and Data Science, The University of Hong Kong(香港大学计算机科学与数据科学学院) School of Information Science & Engineering, Lanzhou University(兰州大学信息科学与工程学院) Max Planck Institute for Security and Privacy(安全与隐私研究所) Computer Science, The University of Michigan(密歇根大学计算机科学系) Center for Data Science, Peking University(北京大学数据科学中心)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12682 2025-11-18 cs.LG physics.ao-ph

Attention-Enhanced Convolutional Autoencoder and Structured Delay Embeddings for Weather Prediction

Amirpasha Hedayat, Karthik Duraisamy

机构 * Department of Aerospace Engineering, University of Michigan(航空航天工程系,密歇根大学)

Comments 13 pages, 7 figures, Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10540 2025-11-18 physics.ins-det cs.LG

Edge Machine Learning for Cluster Counting in Next-Generation Drift Chambers

Deniz Yilmaz, Liangyu Wu, Julia Gonski, Dylan Rankin, Christian Herwig

机构 * Department of Physics(物理系) Stanford University(斯坦福大学) SLAC National Accelerator Laboratory(SLAC国家加速器实验室) University of Pennsylvania(宾夕法尼亚大学) University of Michigan(密歇根大学)

Comments 6 pages, 3 figures, 1 table. Machine Learning and the Physical Sciences Workshop, NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.00411 2025-11-18 cs.CV cs.AI

Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosis

Ran Tong, Jiaqi Liu, Tong Wang, Xin Hu, Su Liu, Lanruo Wang, Jiexi Xu

机构 * University of Texas at Dallas(德克萨斯大学达拉斯分校) Independent Researcher(独立研究者) Duke University(杜克大学) University of Michigan Ann Arbor(密歇根大学安娜堡分校) Georgia Institute of Technology(佐治亚理工学院) University of California, Irvine(加州大学 Irvine 分校)

Comments 6pages,3 figures.Uunder review of International Conference on Artificial Intelligence, Computer, Data Sciences and Applications

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14234 2025-11-18 cs.DS cs.LG cs.NA math.NA math.PR stat.ML

Optimal Subspace Embeddings: Resolving Nelson-Nguyen Conjecture Up to Sub-Polylogarithmic Factors

Shabarish Chenakkod, Michał Dereziński, Xiaoyu Dong

机构 * University of Michigan, Ann Arbor, MI, USA(密歇根大学) National University of Singapore(新加坡国立大学)

Comments SODA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏