arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of California, Berkeley(加州大学伯克利分校)

2026-06-19 至 2026-06-19 共收录 13
2606.20536 2026-06-19 cs.CV 新提交

The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation

FID 彩票:量化生成模型评估中的隐藏随机性

Nicolas Dufour, Alexei A. Efros, Patrick Pérez

机构 * Kyutai UC Berkeley(加州大学伯克利分校)

AI总结 研究FID作为随机变量在训练和生成种子上的方差,发现重训练比重采样导致更大FID波动,提出新评估协议:使用每类最优引导、报告多个训练种子的误差条。

Comments Website: https://kyutai.org/fid-lottery

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20008 2026-06-19 cs.LG 新提交

VIMPO: Value-Implicit Policy Optimization for LLMs

VIMPO: 值隐式策略优化用于大语言模型

Zhewei Kang, Aosong Feng, Sergey Levine, Dawn Song, Xuandong Zhao

机构 * UC Berkeley(加州大学伯克利分校) Yale University(耶鲁大学)

AI总结 提出VIMPO方法,通过KL正则化强化学习的最优条件导出策略隐含值函数,无需训练评论家,实现细粒度信用分配,在数学推理基准上优于GRPO。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19980 2026-06-19 cs.AI 新提交

ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

ENPIRE: 现实世界中智能体机器人策略的自我改进

Wenli Xiao, Jia Xie, Tonghe Zhang, Haotian Lin, Letian "Max" Fu, Haoru Xue, Jalen Lu, Yi Yang, Cunxi Dai, Zi Wang, Jimmy Wu, Guanzhi Wang, S. Shankar Sastry, Ken Goldberg, Linxi "Jim" Fan, Yuke Zhu, Guanya Shi

机构 * NVIDIA(英伟达) CMU(卡内基梅隆大学) UC Berkeley(加州大学伯克利分校)

AI总结 提出ENPIRE框架,通过环境重置、策略执行、结果验证和迭代优化的闭环反馈,使编码智能体自主改进机器人操作策略,在灵巧操作任务上达到99%成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19911 2026-06-19 cs.AI cs.CL cs.IR 新提交

Multi-Agent Transactive Memory

多智能体交互记忆

To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz

机构 * Carnegie Mellon University(卡内基梅隆大学) University of California, Berkeley(加州大学伯克利分校)

AI总结 提出MATM框架,通过共享存储和检索智能体轨迹,实现异构智能体群体间的知识复用,提升下游任务性能并减少交互步骤。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19544 2026-06-19 cs.CL 新提交

Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias

无效度的可靠性:LLM-as-a-Judge 模型在一致性、稳定性和偏差上的系统性大规模评估

Justin D. Norman, Michael U. Rivera, D. Alex Hughes

机构 * UC Berkeley School of Information(加州大学伯克利分校信息学院)

AI总结 本研究通过大规模系统性评估(21个裁判模型、118次运行、约54.1万次判断),发现LLM-as-a-Judge在一致性、稳定性和偏差方面存在普遍问题,包括kappa通缩、排名偏移、高重测信度与严重位置偏差并存,并提出了最小可行验证协议。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19419 2026-06-19 cs.RO cs.AI 新提交

Playful Agentic Robot Learning

趣味性具身机器人学习

Junyi Zhang, Jiaxin Ge, Hanjun Yoo, Letian Fu, Zihan Yang, Yaowei Liu, Raj Saravanan, Shaofeng Yin, Justin Yu, Dantong Niu, Zirui Wang, Roei Herzig, Ken Goldberg, Yutong Bai, David M. Chan, Ion Stoica, Angjoo Kanazawa, Jiahui Lei, Haiwen Feng, Trevor Darrell

机构 * University of California, Berkeley(加州大学伯克利分校) Impossible Research

AI总结 提出RATs框架,让机器人通过自主探索学习可复用技能,在LIBERO-PRO和MolmoSpaces上分别提升20.6和17.0个百分点。

Comments Project page: https://playful-rats.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20082 2026-06-19 math.OC cs.DS cs.LG 新提交

Beyond Averaging in John Ellipsoid Approximation: High-Accuracy Algorithms in the Leverage-Score Model

超越John椭球逼近中的平均化:杠杆分数模型中的高精度算法

Xiaoyu Li, Junwei Yu, Jiaojiao Jiang, Junbin Gao, Andi Han

机构 * University of New South Wales(新南威尔士大学) University of California, Berkeley(加州大学伯克利分校) University of Sydney(悉尼大学)

AI总结 本文分离了John椭球逼近算法中的认证、识别和精度三种成本,证明精度依赖仅为双对数,并提出了加速方法和阻尼牛顿法,在杠杆分数模型中实现了高精度逼近。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19539 2026-06-19 astro-ph.SR cs.AI 新提交

Review of Machine Learning Models for Solar Energetic Particle Prediction

太阳高能粒子预测的机器学习模型综述

Spiridon Kasapis, Pouya Hosseinzadeh, Kathryn Whitman, Ricky Egeland, Manolis Georgoulis, Angelos Vourlidas, Athanasios Papaioannou, Eleni Lavasa, Anastasios Anastasiadis, Giorgos Giannopoulos, Andres Munoz-Jaramillo, Bala Poduval, Irina N. Kitiashvili, Alexander G. Kosovichev, Viacheslav Sadykov, Soukaina Filali Boubrahimi, Tate T. Hutchins, Hameedullah A. Farooki, Manuel E. Cuesta, Leng Y. Khoo, Sungmin Pak, Robert Czarnota, Jamie S. Rankin, Jamey Szalay, Mitchell M. Shen, Georgios Livadiotis, Zigong Xu, David J. McComas, Nikolaos Sarlis, Dionissios Hristopulos, Arik Posner, Alec J. Engell, Mohammed AbuBakr Ali, Ali G. A. Abdelkawy, Abdelrazek M. K. Shaltout, M. M. Beheary, Christina O. Lee, Sigiava Aminalragia-Giamini, Constantinos Papadimitriou, Ingmar Sandberg, Savvas Raptis, Shah Muhammad Hamdi, Monica Laurenza, Mirko Stumpo, Sumanth A. Rotti, India Jackson, Aatiya Ali, Atilim Gunes Baydin, Nathan Schwadron, Subhamoy Chatterjee, Maher A. Dayeh, Gelu M. Nita, Patrick M. O'Keefe, Chun Jie Chong, Paul Kosovich, Russell D. Marroquin, Berkay Aydin, Petrus C. Martens, Lulu Zhao, Yang Chen, Yian Yu, Monica G. Bobra, Ward Manchester, Tamas Gombosi, Ming Zhang, Jesse Torres, Philip K. Chan, Mohamed Nedal, Kamen Kozarev, Peijin Zhang, Kimberly Moreland, Hazel M. Bain, Samuel Hart, Michael J. Starkey, Alan G. Ling, Simone Benella

机构 * Department of Astrophysical Sciences, Princeton University, Princeton, NJ, USA Computational Physics Branch, NASA Ames Research Center, Moffett Field, CA, USA Department of Computer Science, Utah State University, Logan, UT, USA Space Radiation Analysis Group, NASA Johnson Space Center, Houston, TX, USA Johns Hopkins Applied Physics Lab, 11100 Johns Hopkins Rd, Laurel, MD 20723, United States Research Center for Astronomy Applied Mathematics of the Academy of Athens, 4 Soranou Efesiou Street, Athens 11527, Greece Institute for Astronomy, Astrophysics, Space Applications Southwest Research Institute, Boulder, CO, USA Space Science Center, University of New Hampshire, Durham, NH, USA Department of Physics, New Jersey Institute of Technology, Newark, NJ, USA Astronomy Department, Georgia State University, Atlanta, GA, USA Department of Computer Science, Princeton University, Princeton, NJ, USA Department of Mathematics, Rowan University, Glassboro, NJ, USA Astronomy, California Institute of Technology, Pasadena, CA, USA Department of Physics, National Kapodistrian University of Athens, Athens, Greece School of Electrical Computer Engineering, Technical University of Crete, Chania, Greece Department of Astronomy Meteorology, Faculty of Science, Al-Azhar University, Cairo, Egypt Space Sciences Lab, University of California, Berkeley, CA, USA Research Consultancy, Athens, Greece Institute for Space Astrophysics Department of Physics Astronomy, Georgia State University, Atlanta, GA 30303, USA Aryabhatta Research Institute of Observational Sciences (ARIES), Manora Peak, Nainital-263001, Uttarakhand, India Department of Computer Science, Oxford University, Oxford, England Southwest Research Institute, San Antonio, TX, USA Computer Science Department, New Jersey Institute of Technology, Newark, NJ, USA Department of Physics, University of California San Diego, La Jolla, CA 92093, USA Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA Department of Climate Engineering, University of Michigan, Ann Arbor, MI, USA Department of Statistics, University of Michigan, Ann Arbor, MI, USA Department of Electrical Engineering Computer Science, Florida Institute of Technology, Melbourne, FL, USA Astrophysics Section, School of Cosmic Physics, Dublin Institute for Advanced Studies, DIAS Dunsink Observatory, Dublin D15 XR2R, Ireland Institute of Astronomy of the Bulgarian Academy of Sciences, Sofia, Bulgaria Center for Solar-Terrestrial Research, New Jersey Institute of Technology, Newark, NJ 07102, USA Cooperative Programs for the Advancement of Earth System Science, University Corporation for Atmospheric Research, Boulder, CO, USA CIRES, University of Colorado Boulder, Boulder, CO, USA Space Weather Prediction Center, NOAA, Boulder, CO, USA Astronomy, College of Science, The University of Texas at San Antonio, San Antonio, TX, USA Space Weather Prediction Center, National Oceanic The University of Texas at San Antonio, San Antonio, TX, USA Environmental Research, Inc., MA, USA

AI总结 综述了用于太阳高能粒子预测的机器学习模型,包括数据集、架构、输入输出比较,并提出了未来研究建议。

Comments Review Paper, Maine text: 23 pages, References: 5 pages, Appendix: 42 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03199 2026-06-19 cs.CV 版本更新

Does Head Pose Correction Improve Biometric Facial Recognition?

姿态校正是否能提升生物特征面部识别?

Justin Norman, Hany Farid

机构 * University of California, Berkeley(加州大学伯克利分校)

AI总结 研究探讨了AI驱动的头部姿态校正与图像修复对面部识别准确率的影响,发现选择性应用CFR-GAN与CodeFormer可提升识别性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.07328 2026-06-19 cs.LG 版本更新

How to sketch a learning algorithm

如何勾勒学习算法

Sam Gunn

机构 * UC Berkeley(伯克利大学)

AI总结 提出一种数据删除方案,基于稳定性假设,通过随机复方向的高阶导数局部勾勒算术电路,实现深度学习模型输出预测的误差和失败概率可忽略,且预计算和推理仅慢对数因子。

Comments Improved presentation and simplified Algorithm 4

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.04531 2026-06-19 cs.RO 版本更新

PTLD: Sim-to-real Privileged Tactile Latent Distillation for Dexterous Manipulation

PTLD: 从仿真到现实的触觉潜在知识蒸馏用于灵巧操作

Rosy Chen, Mustafa Mukadam, Michael Kaess, Tingfan Wu, Francois R Hogan, Jitendra Malik, Akash Sharma

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Washington(华盛顿大学) FAIR at Meta(Meta的FAIR团队) UC Berkeley(伯克利大学)

AI总结 提出PTLD方法,通过真实世界触觉策略数据蒸馏鲁棒状态估计器,解决触觉仿真困难问题,在灵巧操作任务中相比纯本体感策略提升182%和57%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.04037 2026-06-19 cs.LG cs.RO 版本更新

DADP: Domain Adaptive Diffusion Policy

DADP: 领域自适应扩散策略

Pengcheng Wang, Qinghang Liu, Haotian Lin, Yiheng Li, Guojian Zhan, Masayoshi Tomizuka, Yixiao Wang

机构 * University of California, Berkeley, California, USA(加州大学伯克利分校) Peking University, Beijing, China(北京大学) Tsinghua University, Beijing, China(清华大学)

AI总结 提出DADP,通过无监督解耦和领域感知扩散注入,实现跨动态环境的鲁棒零样本适应,在运动与操控任务上超越先前方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.15769 2026-06-19 math.ST cs.LG stat.ME stat.TH 版本更新

Benign overfitting beyond prediction: The ordinary least squares interpolator

超越预测的良性过拟合:普通最小二乘插值器

Dennis Shen, Dogyoon Song, Peng Ding, Jasjeet S. Sekhon

机构 * Department of Data Sciences & Operations, University of Southern California(数据科学与运营系,南加州大学) Department of Statistics, University of California, Davis(统计学系,加州大学戴维斯分校) Department of Statistics, University of California, Berkeley(统计学系,加州大学伯克利分校) Google DeepMind(谷歌DeepMind)

AI总结 本文研究过参数化线性模型中最小ℓ2范数OLS插值器的参数估计与推断性质,推导了留k法、遗漏变量偏误公式和Frisch-Waugh-Lovell定理的过参数化版本,并扩展了高斯-马尔可夫定理。

Comments This work is accepted for publication in Biometrika

详情

展开后加载摘要…

URL PDF HTML 收藏