arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of California, San Diego(加州大学圣迭戈分校)

2026-08-04 至 2026-08-04 共收录 7
2608.02441 2026-08-04 cs.AI 新提交

Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce

智能体商业世界:一种可审计可验证的氛围式商业环境

Shicheng Fan, Mingdai Yang, Duohao Wang, Canyu Chen, Yongfeng Zhang, Hua Wei, Manling Li, Julian McAuley, Kun Zhang, Philip S. Yu, Kejing Yu, Zhiwei Liu

机构 * University of Illinois at Chicago(伊利诺伊大学芝加哥分校) Springbrand(斯普林布兰德公司) Northwestern University(西北大学) Rutgers University(罗格斯大学) Arizona State University(亚利桑那州立大学) University of California San Diego(加州大学圣迭戈分校) Carnegie Mellon University(卡内基梅隆大学) MBZUAI(Mohamed bin Zayed 人工智能大学) Microsoft AI(微软人工智能部门)

AI总结 该研究提出智能体商业世界(ACWorld)环境,通过氛围式商业协议(VCP)实现可审计可验证的氛围式商业智能体评估,构建含两类轨道的基准并验证模型性能,分析得出过程级证据对评估智能体的必要性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.02433 2026-08-04 cs.LG 新提交

Foundations of Reinforcement Learning and Control:Connections and New Perspectives

强化学习与控制的基础:联系与新视角

Claire Vernade, Onno Eberhard, Martha White, Florian Dörfler, Csaba Szepesvári, Miroslav Krstic, Michael Muehlebach

机构 * University of Technology Nuremberg(纽伦堡工业大学) Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) University of Alberta(阿尔伯塔大学) ETH Zürich(苏黎世联邦理工学院) University of California San Diego(加州大学圣迭戈分校)

AI总结 本教程围绕强化学习与控制理论的联系与差异,介绍自适应控制、演员-评论家强化算法及二者结合的新方法,助力跨领域专家理解对方工具方法。

Comments INFORMS tutorial

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.02404 2026-08-04 cs.CV cs.DL 新提交

Loggia dei Lanzi: AI Thermography Enhancement Comparisons through 3D Photogrammetry

兰齐凉廊:基于三维摄影测量的AI热成像增强对比研究

Scott McAvoy, Jonathan Klingspon, George Bent, Dave Pfaff, Aviral Agarwal, Maurizio Seracini, Falko Kuester

机构 * University of California San Diego(加利福尼亚大学圣迭戈分校) Washington and Lee University(华盛顿与李大学) Editech(爱迪泰克公司)

AI总结 该研究以佛罗伦萨兰齐凉廊为对象,通过对比原生分辨率、FLIR UltraMax硬件超分辨率及AI上采样模型的热成像效果,为文化遗产热成像摄影测量工作流程提供了硬件与AI超分辨率的直接对比数据,相关数据集公开并集成到扩展现实应用中。

Comments 19 pages, 10 figures, to be presented at the 8th International Symposium on Cultural Heritage Conservation by Digitization (CHCD2026) in Beijing

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00909 2026-08-04 cs.CL cs.AR 新提交

FinHardBench: Can LLMs Generate Latency-Aware Hardware for Financial Computing?

FinHardBench:大语言模型能否生成面向金融计算的延迟感知硬件?

Weimin Fu, Hejia Zhang, Minghao Shao, Zeng Wang, Johann Knechtel, Ozgur Sinanoglu, Muhammad Shafique, Ramesh Karri, Xiaolong Guo

机构 * Lehigh University(里海大学) University of California, San Diego(加利福尼亚大学圣迭戈分校) NYU Tandon School of Engineering(纽约大学坦登工程学院) NYU Abu Dhabi(纽约大学阿布扎比分校)

AI总结 本文提出面向金融FPGA设计的开源基准FinHardBench,通过三类实验评估6种大语言模型,发现其在功能正确性、系统级配置优化等方面存在差异,策略级规格变更问题仍待解决。

Comments 16 pages (10 pages main text). Published as a conference paper at COLM 2026. Code and benchmark: https://github.com/owenfucell/FinHardBench

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13246 2026-08-04 cs.LG cs.AI 版本更新

Reassessing Muon for Matrix Factorization

重新评估用于矩阵分解的Muon优化器

Ali Parviz, Gal Mishne, Alex Cloninger

机构 * Halicioğlu Data Science Institute, UC San Diego(加州大学圣地亚哥分校哈利西奥卢数据科学研究所) Department of Mathematics, UC San Diego(加州大学圣地亚哥分校数学系)

AI总结 研究在低秩矩阵分解问题上重新评估Muon优化器,通过与精心调整的自适应基线对比,发现Muon在此设置下不始终优于AdamW,一些优势对超参数选择敏感,更细致地展现谱感知正交化何时有益,主张在受控问题上评估优化器。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.24310 2026-08-04 cs.CL cs.LG

Discovering Lexical Gaps Using Embeddings from Multilingual LLMs

利用多语言大语言模型的嵌入发现词汇空缺

Yoonwon Jung, Aaron S. Cohen, Benjamin K. Bergen

机构 * Department of Cognitive Science, University of California San Diego(加州大学圣地亚哥分校认知科学系)

AI总结 提出一种数据驱动框架,通过多语言大语言模型的上下文嵌入计算语义相似度,以识别跨语言词汇空缺,在韩英和英韩方向上分别达到0.81和0.76的AUC。

Comments CoNLL 2026

Journal ref Yoonwon Jung, Aaron S. Cohen, and Ben Bergen. 2026. Discovering Lexical Gaps Using Embeddings from Multilingual LLMs. In Proceedings of the 30th Conference on Computational Natural Language Learning, pages 641-660

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.04923 2026-08-04 quant-ph cs.AI cs.LG

Artificial intelligence for representing and characterizing quantum systems

Yuxuan Du, Yan Zhu, Yuan-Hang Zhang, Min-Hsiu Hsieh, Patrick Rebentrost, Weibo Gao, Ya-Dong Wu, Jens Eisert, Giulio Chiribella, Dacheng Tao, Barry C. Sanders

机构 * College of Computing Data Science, Nanyang Technological University, Singapore 639798, Singapore Computation Initiative, Department of Computer Science, The University of Hong Kong, Pokfulam Road, Hong Kong Department of Physics, University of California, San Diego, La Jolla, CA 92093, USA Hon Hai (Foxconn) Research Institute, Taipei, Taiwan Centre for Quantum Technologies, National University of Singapore Department of Computer Science, National University of Singapore School of Electrical \& Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China Dahlem Center for Complex Quantum Systems, Freie Universitat Berlin, 14195 Berlin, Germany Department of Computer Science, Parks Road, Oxford, OX1 3QD, United Kingdom Perimeter Institute for Theoretical Physics, Waterloo, Ontario N2L 2Y5, Canada Institute for Quantum Science Technology, University of Calgary, Alberta T2N 1N4, Canada

Comments 32 pages. Comments are welcome

Journal ref Nature Reviews Physics (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏