arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Chinese Academy of Sciences(中国科学院大学)

2026-07-29 至 2026-07-29 共收录 5
2602.15353 2026-07-29 cs.CL cs.AI 版本更新

NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

NeuroSymActive:基于主动探索的可微神经符号推理用于知识图谱问答

Rong Fu, Yang Li, Zeyu Zhang, Jiekai Wu, Yaohua Liu, Shuaishuai Cao, Yangchen Zeng, Yuhang Zhang, Xiaojing Du, Simon Fong

机构 * University of Macau(澳门大学) University of Chinese Academy of Sciences(中国科学院大学) The Australian National University(澳大利亚国立大学) Juntendo University(静冈大学) Guangdong Institute of Intelligence Science and Technology(广东智能科学与技术研究院) Central South University(中南大学) Southeast University(东南大学) China Agricultural University(中国农业大学) Adelaide University(阿德莱德大学)

AI总结 NeuroSymActive结合可微神经符号推理层和主动探索控制器,通过软统一流程模块和神经路径评估器提升知识图谱问答的准确性和效率。

Comments 26 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15355 2026-07-29 cs.CV 版本更新

DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles

DAV-GSWT:基于扩散优先的主动视角采样用于数据高效的高斯溅射瓦片

Rong Fu, Jiekai Wu, Yee Tan Jia, Yang Li, Xiaowen Ma, Wangyu Wu, Simon Fong

机构 * University of Macau(澳门大学) Juntendo University(立命馆大学) Tongji University(同济大学) Renmin University of China(中国人民大学) University of Chinese Academy of Sciences(中国科学院大学) Zhejiang University(浙江大学) University of Liverpool(利物浦大学)

AI总结 本文提出DAV-GSWT框架,利用扩散先验和主动视角采样,从少量输入观测合成高保真高斯溅射瓦片,减少数据需求并保持视觉质量和交互性能。

Comments 16 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15021 2026-07-29 astro-ph.SR astro-ph.GA cs.LG 版本更新

Generalization from Low- to Moderate-Resolution Spectra with Neural Networks for Stellar Parameter Estimation: A Case Study with DESI

利用神经网络从低分辨率到中等分辨率光谱进行泛化:恒星参数估计的案例研究

Xiaosheng Zhao, Yuan-Sen Ting, Rosemary F. G. Wyse, Alexander S. Szalay, Yang Huang, László Dobos, Tamás Budavári, Viska Wei

机构 * Department of Physics \& Astronomy, The Johns Hopkins University, Baltimore, MD 21218, USA Department of Astronomy, The Ohio State University, 140 West 18th Avenue, Columbus, OH 43210, USA Center for Cosmology AstroParticle Physics (CCAPP), The Ohio State University, Columbus, OH 43210, USA Department of Computer Science, The Johns Hopkins University, Baltimore, MD 21218, USA School of Astronomy Space Science, University of Chinese Academy of Sciences, Beijing 100049, People's Republic of China National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, People's Republic of China Department of Information Systems, E\"otv\"os Lor\' University, Budapest 1117, Hungary Department of Applied Mathematics \& Statistics, Johns Hopkins University, Baltimore, MD 21218, USA

AI总结 本研究利用神经网络从低分辨率到中等分辨率光谱进行泛化,通过预训练和微调策略提升恒星参数估计的准确性。

Comments 22 pages, 13 figures, 4 tables. Accepted for publication in ApJ. Comments welcome

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03443 2026-07-29 math.OC cs.LG stat.ML 版本更新

A Support-Set Algorithm for Optimization Problems with Nonnegative and Orthogonal Constraints

一种用于具有非负和正交约束的优化问题的支持集算法

Lei Wang, Xin Liu, Xiaojun Chen

机构 * The Hong Kong Polytechnic University(香港理工大学) Chinese Academy of Sciences(中国科学院) University of Chinese Academy of Sciences(中国科学院大学) State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science(数学科学国家重点实验室)

AI总结 研究具有非负和正交约束的优化问题,提出支持集算法,通过固定支持集提高计算效率,证明其收敛到一阶驻点且迭代复杂度为\(O (\epsilon^{-2})\),数值结果表明该算法在实际应用中表现良好。

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.03291 2026-07-29 cs.CV 版本更新

DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers

DopQ-ViT:面向视觉Transformer的分布友好型和离群值感知的模型后训练量化

Lianwei Yang, Haisong Gong, Haokun Lin, Yichen Wu, Caifeng Shan, Zhenan Sun, Qingyi Gu

机构 * Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)

AI总结 针对视觉Transformer高计算成本及后训练量化性能易降问题,提出DopQ-ViT方法,通过引入Tan量化器保留幂律分布、MAD引导的最优缩放因子选择,在分类和检测任务上优于先前PTQ方法。

Comments Accepted by Machine Intelligence Research

详情

展开后加载摘要…

URL PDF HTML 收藏