arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Washington(华盛顿大学)

2025-12-30 至 2025-12-30 共收录 6
2507.04749 2025-12-30 cs.CV

MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images

MatDecompSDF:从多视角图像中恢复高保真3D形状和PBR材质分解

Chengyu Wang, Isabella Bennett, Henry Scott, Liang Zhang, Mei Chen, Hao Li, Rui Zhao

机构 * San Francisco State University 1600 Holloway Avenue San Francisco California USA 94132 Department of Electrical \& Computer Engineering, Boston University 8 Saint Mary’s Street Boston MA USA 02215 University of California, Berkeley 2150 Shattuck Avenue Berkeley California USA 94704 Stanford University 450 Serra Mall Stanford California USA 94305 Carnegie Mellon University 5000 Forbes Avenue Pittsburgh Pennsylvania USA 15213 University of Washington 185 Stevens Way Seattle Washington USA 98195 San Francisco State University Department of Electrical \& Computer Engineering, Boston University University of California, Berkeley Stanford University Carnegie Mellon University University of Washington

AI总结 MatDecompSDF通过联合优化SDF、神经场和MLP模型,实现从多视角图像中高保真3D形状和PBR材质的分解。

Comments 12 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.17479 2025-12-30 cs.AI cs.CY cs.HC cs.LG

Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning

文化适应的道德机器:通过逆强化学习让AI隐式学习人类价值观系统

Nigini Oliveira, Jasmine Li, Koosha Khalvati, Rodolfo Cortes Barragan, Katharina Reinecke, Andrew N. Meltzoff, Rajesh P. N. Rao

机构 * Paul G. Allen School of Computer Science and Engineering, University of Washington(保罗·G·阿伦计算机科学与工程学院,华盛顿大学) Institute for Learning and Brain Sciences, University of Washington(学习与脑科学研究所,华盛顿大学)

AI总结 本文提出通过逆强化学习让AI隐式学习不同文化的价值观,展示AI能从人类行为中习得文化适应的道德系统。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22392 2025-12-30 cs.CV

iOSPointMapper: RealTime Pedestrian and Accessibility Mapping with Mobile AI

iOSPointMapper: 基于移动AI的实时行人及可达性制图

Himanshu Naidu, Yuxiang Zhang, Sachin Mehta, Anat Caspi

机构 * University of Washington(华盛顿大学) Paul G. Allen School of Computer Science and Engineering(保罗·G·艾伦计算机科学与工程学院)

AI总结 iOSPointMapper通过移动AI实现实时人行道制图,结合语义分割、LiDAR和GPS数据,提供隐私保护的数据收集与多模式交通数据整合,提升行人基础设施的可达性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22248 2025-12-30 cs.LG

Amortized Inference for Model Rocket Aerodynamics: Learning to Estimate Physical Parameters from Simulation

模型火箭气动学的 amortized 推断:从仿真中学习估计物理参数

Rohit Pandey, Rohan Pandey

机构 * bellevue High School(贝尔维尤高中) University of Washington(华盛顿大学)

AI总结 本文提出了一种基于仿真的 amortized 推断方法,通过训练神经网络在合成飞行数据上,实现对模型火箭气动参数的高效估计,显著提升了真实飞行中的预测精度。

Comments 5 pages, 2 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19486 2025-12-30 cs.LG cs.AI

Efficient Inference Using Large Language Models with Limited Human Data: Fine-Tuning then Rectification

利用有限人类数据高效推理:微调后再校正

Lei Wang, Zikun Ye, Jinglong Zhao

机构 * Foster School of Business, University of Washington(华盛顿大学福斯特商学院) Questrom School of Business, Boston University(波士顿大学questrom商学院)

AI总结 本文提出一种两阶段框架,结合微调与校正,并优化有限标记样本的分配,以提高估计和推理性能,实现成本节约。

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.00654 2025-12-30 cs.CV cs.CL cs.LG

ICONS: Influence Consensus for Vision-Language Data Selection

ICONS: 视觉-语言数据选择中的影响共识

Xindi Wu, Mengzhou Xia, Rulin Shao, Zhiwei Deng, Pang Wei Koh, Olga Russakovsky

机构 * Princeton University(普林斯顿大学) University of Washington(华盛顿大学) Google DeepMind(谷歌DeepMind) Allen Institute for AI(人工智能研究院)

AI总结 ICONS通过影响共识方法高效选择视觉-语言数据,保持高性能并支持多任务泛化。

详情

展开后加载摘要…

URL PDF HTML 收藏