arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Texas at Austin(得克萨斯大学奥斯汀分校)

2026-06-09 至 2026-06-09 共收录 19
2606.09266 2026-06-09 cs.SD cs.AI 新提交

Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design

物理引导的序列生成框架用于声学超材料逆向设计

Yijie Li, Jiahao Xu, Ching-Chih Tsao, Lili Qiu, Jingxian Wang

机构 * National University of Singapore(新加坡国立大学) UT Austin(德克萨斯大学奥斯汀分校)

AI总结 提出MetaSeq框架,将声学超材料表示为结构化序列,通过序列到序列模型结合物理求解器和强化学习,实现宽带逆向设计,误差降低45%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.08512 2026-06-09 cs.CY cs.CL 新提交

Friend or Foe? Language as an ideological switch in open-weight LLMs under Russian disinformation stress

朋友还是敌人?俄罗斯虚假信息压力下开放权重大语言模型中的语言意识形态开关

Anna Małgorzata Kamińska, Tetiana Klynina

机构 * Institute of Culture Studies, University of Silesia in Katowice(文化研究学院,卡托维察大学) University of Texas at Austin(德克萨斯大学奥斯汀分校) National Aviation University(国家航空大学)

AI总结 本文通过控制实验发现,针对不同语言社区微调的大语言模型在俄罗斯虚假信息压力下,其抵抗能力与预期文化对齐方向相反,揭示了微调悖论。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.08432 2026-06-09 cs.AI 新提交

Trajectory-Refined Distillation

轨迹精炼蒸馏

Li Jiang, Haoran Xu, Yichuan Ding, Amy Zhang

机构 * McGill University(麦吉尔大学) Mila Quebec AI Institute(米拉魁北克人工智能研究所) UT Austin(德克萨斯大学奥斯汀分校)

AI总结 提出轨迹精炼蒸馏(TRD),通过教师指导修正学生轨迹中的前缀错误,解决在线策略蒸馏中的前缀失败问题,提升大语言模型的单次准确率和推理覆盖。

Comments under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.00384 2026-06-09 cs.AI cs.CL cs.CV cs.LG stat.CO 版本更新

VESTA: Visual Exploration with Statistical Tool Agents

VESTA: 基于统计工具代理的视觉探索

William Rudman, Abhishek Divekar, Kanishk Jain, Sebastian Joseph, Stella S. R. Offner, Matthew Lease, Kyle Mahowald, Greg Durrett, Junyi Jessy Li

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) New York University(纽约大学)

AI总结 提出VESTA框架,通过动态增长的工具集指导数据变换、假设驱动可视化和统计检验,提升视觉语言模型在复杂统计建模任务上的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26078 2026-06-09 cs.LG 版本更新

Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning

Wasserstein策略梯度在熵正则化强化学习中的全局收敛性

Zhaoyu Zhu, Rui Gao, Shuang Li

机构 * Shanghai Jiao Tong University(上海交通大学) The University of Texas at Austin(德克萨斯大学奥斯汀分校) The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

AI总结 本文通过利用熵正则化强化学习的Bellman结构,证明了Wasserstein策略梯度(WPG)方法的全局收敛性,并建立了分布Polyak-Łojasiewicz条件。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14949 2026-06-09 cs.LG stat.ML

On the Convergence and Straightness of Rectified Flow

关于校正流的收敛性与直线性

Vansh Bansal, Saptarshi Roy, Alessandro Rinaldo, Purnamrita Sarkar

机构 * Department of Statistics and Data Sciences, UT Austin(统计与数据科学系,德克萨斯大学奥斯汀分校)

AI总结 本文提出Piecewise Straightness参数γ₂,T,建立首个流模型离散误差与γ₂,T的Wasserstein收敛界,证明最小曲率是实现高保真单步采样的关键,同时为RF的直线性分析提供了理论框架。

Comments 37 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.14285 2026-06-09 eess.IV cs.LG 版本更新

ForcingDAS: Unified and Robust Data Assimilation via Diffusion Forcing

通过扩散强迫实现统一且稳健的数据同化:ForcingDAS

Yixuan Jia, Siyi Chen, Yida Pan, Xiao Li, Lianghe Shi, Chanyong Jung, Haijie Yuan, Ismail Alkhouri, Yue Cynthia Wu, Saiprasad Ravishankar, Jeffrey A Fessler, Qing Qu

机构 * University of Michigan(密歇根大学) University of California, Berkeley(加州大学伯克利分校) Stanford University(斯坦福大学) Massachusetts Institute of Technology(麻省理工学院) University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 本文提出ForcingDAS,一种基于扩散强迫的统一数据同化框架,能够捕捉长时序依赖并减少误差积累,同时在推理时无需重新训练即可实现滤波到平滑的全谱应用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08479 2026-06-09 cs.CL 版本更新

AI generates well-liked but templatic empathic responses

AI生成受欢迎但模板化的共情回应

Emma S. Gueorguieva, Hongli Zhan, Jina Suh, Javier Hernandez, Tatiana Lau, Junyi Jessy Li, Desmond C. Ong

机构 * Department of Psychology, The University of Texas at Austin(心理学系,德克萨斯大学奥斯汀分校) Department of Linguistics, The University of Texas at Austin(语言学系,德克萨斯大学奥斯汀分校) Department of Computer Science and Engineering, The University of Washington(计算机科学与工程系,华盛顿大学) Microsoft Research(微软研究院) Toyota Research Institute(丰田研究院)

AI总结 研究发现LLM生成的共情回应高度模板化,采用10种共情语言策略,覆盖81-92%的回应内容,而人类写作则更多样。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18493 2026-06-09 eess.IV cs.AI cs.CV 版本更新

SAGE: Shape-Adapting Gated Experts for Adaptive Histopathology Image Segmentation

SAGE:适应性组织病理图像分割的形状自适应门控专家

Gia Huy Thai, Hoang-Nguyen Vu, Anh-Minh Phan, Quang-Thinh Ly, Thi-Ngoc-Truc Nguyen, Nhat Ho

机构 * University of Science, VNU-HCM(越南国家大学科学学院) Trivita AI University of Technology, VNU-HCM(越南国家大学技术学院) Michigan State University, USA(美国密歇根州立大学) The University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 SAGE通过动态专家路由框架提升异构视觉网络中细胞形态变化的适应性,实现高精度分割与稳健泛化。

Comments Accepted to CVPR 2026 (Findings Track). Project Page: https://oxyzgiahuy.github.io/sage/

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.10370 2026-06-09 cs.LG cs.AI math-ph math.MP math.OC stat.ML

Geometric structure of shallow neural networks and constructive ${\mathcal L}^2$ cost minimization

浅层神经网络的几何结构与构造性${\mathcal L}^2$成本最小化

Thomas Chen, Patrícia Muñoz Ewald

机构 * Department of Mathematics, University of Texas at Austin(德克萨斯大学奥斯汀分校数学系)

AI总结 本文研究浅层ReLU网络在欠参数化情况下的成本最小化问题,通过构造上界揭示分类数据的几何结构,不依赖梯度下降。证明了成本函数最小值的上界与训练数据信噪比相关,并确定了特定子空间的构造性训练网络。

Comments AMS Latex, 29 pages. Experimental evidence added. To appear in Physica D: Nonlinear Phenomena

Journal ref Phys. D, 490, Article No. 135176 (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23592 2026-06-09 cs.RO cs.HC cs.SY eess.SY

Human-Exoskeleton Kinematic Calibration to Improve Hand Tracking for Dexterous Teleoperation

人-外骨骼运动学校准以提高手部跟踪用于灵巧遥操作

Haiyun Zhang, Stefano Dalla Gasperina, Saad N. Yousaf, Toshimitsu Tsuboi, Tetsuya Narita, Ashish D. Deshpande

机构 * Walker Department of Mechanical Engineering, The University of Texas at Austin(德克萨斯大学机械工程系) Sony Group Corporation, Tokyo, Japan(索尼集团公司,日本东京) Meta Reality Labs Research, Redmond, WA, USA(Meta现实实验室研究)

AI总结 本文提出一种针对手部外骨骼的个性化校准框架,通过残差加权优化估计虚拟链接参数,减少关节和指尖跟踪误差,提升遥操作精度。

Comments 8 pages, 10 figures, 1 supplementary video, submitted to RA-L

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10172 2026-06-09 astro-ph.IM cs.AI 版本更新

Cosmo3DFlow: Wavelet Flow Matching for Spatial-to-Spectral Compression in Reconstructing the Early Universe

Cosmo3DFlow:用于重建早期宇宙的空间到光谱压缩的小波流匹配

Md. Khairul Islam, Zeyu Xia, Ryan Goudjil, Jialu Wang, Arya Farahi, Judy Fox

机构 * Department of Computer Science University of Virginia(计算机科学系弗吉尼亚大学) Department of Statistics and Data Sciences The University of Texas at Austin(统计与数据科学系德克萨斯大学奥斯汀分校) School of Data Science(数据科学学院)

AI总结 提出Cosmo3DFlow框架,结合3D离散小波变换与流匹配,通过空间到光谱压缩解决高维宇宙结构重建中的维度和稀疏性瓶颈,实现比扩散模型快46倍的采样速度。

Journal ref KDD '26: Proc. 32nd ACM SIGKDD Conf. on Knowledge Discovery and Data Mining V.2, 11153-11164 (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.07098 2026-06-09 cs.LG cs.AI math-ph math.MP math.OC stat.ML

Interpretable global minima of deep ReLU neural networks on sequentially separable data

可解释的深度ReLU神经网络在依次可分数据上的全局极小值

Thomas Chen, Patrícia Muñoz Ewald

机构 * Department of Mathematics, University of Texas at Austin(德克萨斯大学奥斯汀分校数学系)

AI总结 本文通过构造零损失分类器,利用累积参数确定截断映射,研究了在小且分离的簇数据及依次线性可分等价类情况下,深度ReLU网络的全局极小值描述。

Comments AMS Latex, 31 pages, 3 figures

Journal ref J. Mach. Learn. Res., 26 (173): 1-31 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12744 2026-06-09 stat.ML cs.LG math.ST stat.CO stat.ME stat.TH 版本更新

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps

混合测度的树状图用于Softmax门控高斯混合专家:无需模型扫描的一致性

Do Tien Hai, Trung Nguyen Mai, TrungTin Nguyen, Nhat Ho, Binh T. Nguyen, Christopher Drovandi

机构 * Faculty of Mathematics and Computer Science, University of Science, Ho Chi Minh City, Vietnam(越南胡志明市科学大学数学与计算机科学学院) Vietnam National University Ho Chi Minh City, Vietnam(越南胡志明市国家大学) Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam(越南胡志明市科学大学信息技术学院) ARC Centre of Excellence for the Mathematical Analysis of Cellular Systems(细胞系统数学分析 excellence 中心) School of Mathematical Sciences, Queensland University of Technology, Brisbane City, Australia(昆士兰科技大学数学科学学院) Department of Statistics and Data Science, University of Texas at Austin, Austin, USA(德克萨斯大学奥斯汀分校统计与数据科学系)

AI总结 针对softmax门控高斯混合专家模型,提出基于Voronoi损失函数的统一统计框架,解决参数非可识别性和模型选择问题,并引入混合测度树状图实现一致且无需多尺寸训练的专家数选择。

Comments Do Tien Hai, Trung Nguyen Mai, and TrungTin Nguyen are co-first authors. In Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, AISTATS 2026 Spotlight, Acceptance rate 2.5% over 2102 submissions

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.15494 2026-06-09 cs.LG physics.data-an 版本更新

Multi-resolution Enhancement for Full Spectrum Neural Representations

全频谱神经表示的多分辨率增强

Yuan Ni, Zhantao Chen, Shizhou Xu, Cheng Peng, Rajan Plumley, Chun Hong Yoon, Jana B. Thayer, Joshua J. Turner

机构 * Linac Coherent Light Source, SLAC National Accelerator Laboratory(直线相干光源,SLAC国家加速器实验室) Stanford Institute for Materials and Energy Sciences, Stanford University(斯坦福大学材料与能源科学研究所) Walker Department of Mechanical Engineering, The University of Texas at Austin(德克萨斯大学奥斯汀分校机械工程系) Department of Mathematics, University of California Davis(加州大学戴维斯分校数学系) Department of Physics, Carnegie Mellon University(卡内基梅隆大学物理系)

AI总结 提出WIEN-INR框架,通过分层增强网络在不同分辨率尺度上建模,提升小网络对多尺度结构和高频细节的表示能力,实现紧凑高保真表示。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20734 2026-06-09 cs.CV 版本更新

CardioMorphNet: Cardiac Motion Prediction Using a Shape-Guided Bayesian Recurrent Deep Network

CardioMorphNet: 使用形状引导的贝叶斯循环深度网络进行心脏运动预测

Reza Akbari Movahed, Abuzar Rezaee, Arezoo Zakeri, Colin Berry, Edmond S. L. Ho, Ali Gooya

机构 * University of California, San Diego(加州大学圣地亚哥分校) University of Texas at Austin(德克萨斯大学奥斯汀分校)

AI总结 提出CardioMorphNet,一种基于循环变分自编码器和贝叶斯公式的3D心脏形状引导可变形配准框架,通过递归配准分割图避免强度相似性损失,在心脏运动估计中优于现有方法,并具有更低的不确定性。

Comments Published in Medical Image Analysis. Updated to match the final published version

Journal ref Medical Image Analysis, vol. 113, p. 104149, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.07065 2026-06-09 cs.LG cs.AI math-ph math.MP math.OC stat.ML

On non-approximability of zero loss global ${\mathcal L}^2$ minimizers by gradient descent in Deep Learning

关于深度学习中梯度下降无法逼近零损失全局L²最小化器的非近似性

Thomas Chen, Patricia Muñoz Ewald

机构 * Department of Mathematics, University of Texas at Austin(德克萨斯大学奥斯汀分校数学系)

AI总结 本文分析了深度学习中梯度下降算法的几何特性,指出在欠参数化网络中,零损失最小化通常无法实现,因此训练输入分布必须非典型才能产生零损失最小化器。

Comments AMS Latex, 7 pages. Typos corrected, Corollary 1.6 upgraded to Theorem, acknowledgment added

Journal ref Theor. Appl. Mech., 52 (1), 67-73 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.07833 2026-06-09 cs.DC cs.AI cs.MA cs.OS 版本更新

Harmonia: End-to-End RAG Serving Optimization

Harmonia: 端到端RAG服务优化

Saurabh Agarwal, Bodun Hu, Luis Pabon, Myungjin Lee, Jayanth Srinivasa, Aditya Akella

机构 * UT Austin(德克萨斯大学奥斯汀分校) Cisco Research(思科研究) Cisco Systems(思科系统)

AI总结 提出Harmonia框架,通过灵活管道接口、异构感知部署和闭环运行时控制器,优化RAG服务,吞吐量提升2.04倍以上,SLO违规减少78.4%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.06469 2026-06-09 cs.CL 版本更新

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

ClinicalBench: 大型语言模型能在临床预测中击败传统机器学习模型吗?

Canyu Chen, Jian Yu, Shan Chen, Che Liu, Zhongwei Wan, Shuang Zhou, Yuan Luo, Rui Zhang, Danielle Bitterman, Fei Wang, Kai Shu

机构 * Department of Computer Science Northwestern University Evanston USA(计算机科学系西北大学艾文斯顿美国) Department of Computer Science University of Texas at Austin Austin USA(计算机科学系德克萨斯大学奥斯汀美国) Boston Children's Hospital, Harvard Medical School Boston USA(波士顿儿童医院哈佛医学院波士顿美国) Department of Computer Science Imperial College London London UK(计算机科学系伦敦帝国学院伦敦英国) Department of Computer Science Ohio State University Columbus USA(计算机科学系俄亥俄州立大学哥伦布美国) Massachusetts General Hospital, Harvard Medical School Boston USA(麻省总医院哈佛医学院波士顿美国) Department of Preventive Medicine, Feinberg School of Medicine Northwestern University Chicago USA(预防医学系费因伯格医学院西北大学芝加哥美国) Division of Computational Health Sciences, Department of Surgery University of Minnesota Minneapolis USA(计算健康科学部外科部明尼苏达大学明尼阿波利斯美国) Department of Population Health Sciences, Weill Cornell Medicine Cornell University New York USA(流行病学与公共卫生系韦尔·科恩医学中心康奈尔大学纽约美国) Department of Computer Science Emory University Atlanta USA(计算机科学系埃默里大学亚特兰大美国) Northwestern University(西北大学) University of Texas at Austin(德克萨斯大学奥斯汀) Boston Children's Hospital, Harvard Medical School(波士顿儿童医院哈佛医学院) Imperial College London(伦敦帝国学院) Ohio State University(俄亥俄州立大学) Massachusetts General Hospital, Harvard Medical School(麻省总医院哈佛医学院) University of Minnesota(明尼苏达大学) Cornell University(康奈尔大学) Emory University(埃默里大学)

AI总结 构建ClinicalBench基准,通过三个临床预测任务比较14个通用和8个医学LLM与11个传统ML模型,发现LLM在临床预测上仍无法超越传统ML模型。

Comments Accepted to Proceedings of KDD 2026. The first two authors contributed equally. 12 pages for main paper, 62 pages including appendix. Project website: https://clinicalbench.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏