arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Science and Technology of China(中国科学技术大学)

2025-12-16 至 2025-12-16 共收录 11
2507.19929 2025-12-16 physics.soc-ph cs.AI

DynamiX: Large-Scale Dynamic Social Network Simulator

DynamiX: 大规模动态社交网络模拟器

Yanhui Sun, Wu Liu, Wentao Wang, Hantao Yao, Jiebo Luo, Yongdong Zhang

机构 * School of Information Science and Technology, University of Science and Technology of China(信息科学与技术学院,中国科学技术大学) Department of Computer Science, University of Rochester(计算机科学系,罗切斯特大学)

AI总结 DynamiX通过动态层级模块和不同用户类型的社交关系建模策略,提升了大规模动态社交网络模拟的准确性与实用性。

Comments Social and Information Networks

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12809 2025-12-16 cs.NE cs.AI

OPAL: Operator-Programmed Algorithms for Landscape-Aware Black-Box Optimization

OPAL: 用于景观感知的黑盒优化运算符-程序算法

Junbo Jacob Lian, Mingyang Yu, Kaichen Ouyang, Shengwei Fu, Rui Zhong, Yujun Zhang, Jun Zhang, Huiling Chen

机构 * McCormick School of Engineering, Northwestern University(麦科姆ick工程学院,西北大学) College of Artificial Intelligence, Nankai University(南开大学人工智能学院) School of Mathematics, University of Science and Technology of China(中国科学技术大学数学系) Guizhou University(贵州大学) School of New Energy, Jingchu University of Technology(荆楚科技学院新能源学院) Information Initiative Center, Hokkaido University(北海道大学信息初始化中心) School of Computer Science and Artificial Intelligence, Wenzhou University(温州大学计算机科学与人工智能学院)

AI总结 OPAL通过运算符程序化和景观感知的方法,实现了在黑盒优化中的高效优化,优于传统方法。

Comments Source code, experiment scripts, and results are publicly available at https://github.com/junbolian/OPAL. The real-world application part hasn't been done yet

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12387 2025-12-16 cs.LG

Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment

在时间和群体维度上锚定值以实现流匹配模型对齐

Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Wei Zhai, Yang Cao, Zheng-Jun Zha

机构 * University of Science and Technology of China(中国科学技术大学) Tongyi Lab(通义实验室)

AI总结 VGPO通过在时间和群体维度上锚定值,改进流匹配模型对齐,提升图像生成质量与任务准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.10309 2025-12-16 q-bio.MN cs.LG physics.bio-ph

Tracking large chemical reaction networks and rare events by neural networks

通过神经网络追踪大规模化学反应网络和罕见事件

Jiayu Weng, Xinyi Zhu, Jing Liu, Linyuan Lü, Pan Zhang, Ying Tang

机构 * Institute of Data Science, University of Hong Kong, Hong Kong(数据科学研究所,香港大学) Department of Systems Science, Faculty of Arts and Sciences, Beijing Normal University, Zhuhai 519087, China(艺术与科学学院系统科学系,北京师范大学) School of Physics, University of Electronic Science and Technology of China, Chengdu 611731, China(电子科学与技术大学物理学院) School of Physical Science and Technology, Beijing University of Posts and Telecommunications, Beijing 102206, China(邮电大学物理科学与技术学院) Institute of Theoretical Physics, Chinese Academy of Sciences, Beijing 100190, China(中国科学院理论物理研究所) School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230027, China(科学技术大学网络科学与技术学院) School of Fundamental Physics and Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS, Hangzhou 310024, China(杭州高等研究院基础物理与数学科学学院) Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China(电子科学与技术大学基础与前沿科学研究所) Non-classical Information Science Basic Discipline Research Center of Sichuan Province, University of Electronic Science and Technology of China, Chengdu 611731, China(四川省非经典信息科学基础学科研究中心,电子科学与技术大学)

AI总结 本文提出通过神经网络高效追踪大规模化学反应网络及罕见事件的方法,结合优化算法和增强采样策略,实现显著加速和高精度建模。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08648 2025-12-16 cs.CV

Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank

Repulsor:利用对比记忆库加速生成建模

Shaofeng Zhang, Xuanqi Chen, Ning Liao, Haoxiang Zhao, Xiaoxing Wang, Haoru Tan, Sitong Wu, Xiaosong Jia, Qi Fan, Junchi Yan

机构 * School of Artificial Intelligence and Data Science, University of Science and Technology of China(人工智能与数据科学学院,中国科学技术大学) Shanghai Jiao Tong University(上海交通大学) HKU(香港大学) CUHK(香港大学) Fudan University(复旦大学) Nanjing University(南京大学)

AI总结 Repulsor通过对比记忆库机制,无需外部编码器,实现高效的生成建模,显著提升收敛速度和生成质量。

Comments 19 pages, 19 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03738 2025-12-16 cs.CV

FACM: Flow-Anchored Consistency Models

FACM:基于流的一致性模型

Yansong Peng, Kai Zhu, Yu Liu, Pingyu Wu, Hebei Li, Xiaoyan Sun, Feng Wu

机构 * University of Science and Technology of China(中国科学技术大学) Tongyi Lab(通义实验室)

AI总结 FACM通过流锚定方法解决连续时间一致性模型的训练不稳定性问题,实现高效生成和稳定训练。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23583 2025-12-16 cs.LG

Improving Time Series Forecasting via Instance-aware Post-hoc Revision

通过实例感知的后处理修正提升时间序列预测

Zhiding Liu, Mingyue Cheng, Guanhao Zhao, Jiqian Yang, Qi Liu, Enhong Chen

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学)

AI总结 本文提出PIR框架,通过后处理修正提升时间序列预测的实例可靠性。

Comments Accepted by NeurIPS 2025 as a poster

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19700 2025-12-16 cs.CL cs.AI

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models

利用重要性采样将对齐模块从大语言模型中分离出来

Yi Liu, Dianqing Liu, Mingye Zhu, Junbo Guo, Yongdong Zhang, Zhendong Mao

机构 * State Key Laboratory of Communication Content Cognition, People’s Daily Online(通信内容认知国家重点实验室,人民在线) University of Science and Technology of China(中国科学技术大学)

AI总结 本文提出残差对齐模型(RAM),通过重要性采样将对齐模块与大语言模型分离,提升灵活性和可扩展性,并在多种任务上优于基线模型。

Comments Accepted by NeurIPS 2025, 28 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15134 2025-12-16 cs.CV

Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation

实例自适应关键点学习与局部到全局几何聚合用于类别级物体姿态估计

Xiao Zhang, Lu Zou, Tao Lu, Yuan Yao, Zhangjin Huang, Guoping Wang

机构 * Wuhan Institute of Technology(武汉理工大学) University of Science and Technology of China(中国科学技术大学) Peking University(北京大学)

AI总结 INKL-Pose通过实例自适应关键点学习与局部到全局几何聚合,实现类别级物体姿态估计的高精度与高效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.17827 2025-12-16 eess.SP cs.LG

A Physics-Embedded Dual-Learning Imaging Framework for Electrical Impedance Tomography

一种嵌入物理的双学习成像框架用于电阻抗断层成像

Xuanxuan Yang, Yangming Zhang, Haofeng Chen, Gang Ma, Xiaojie Wang

机构 * Hefei Institutes of Physical Science, Chinese Academy of Sciences(合肥物理研究所,中国科学院) Department of Precision Instruments and Precision Machinery, University of Science and Technology of China(中国科学技术大学精密仪器与机械系) Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague(布拉格技术大学电子工程学院控制系)

AI总结 本文提出了一种嵌入物理的双学习框架,用于解决电阻抗断层成像中的逆问题,通过结合监督CNN和无监督PINN提高重建的鲁棒性和效率。

Comments 14 pages,11 figures

Journal ref Neural Networks, p. 108464, 2025/12/11/ 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11849 2025-12-16 cs.CL cs.AI cs.CV

KH-FUNSD: A Hierarchical and Fine-Grained Layout Analysis Dataset for Low-Resource Khmer Business Document

KH-FUNSD:一种面向低资源柬埔寨商业文档的分层和细粒度布局分析数据集

Nimol Thuon, Jun Du

机构 * National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP) University of Science and Technology of China(国家语信息处理语音工程研究中心(NERC-SLIP)大学科学技术大学)

AI总结 KH-FUNSD是首个面向克默语商业文档的分层细粒度布局分析数据集,通过三级注释框架提升低资源语言文档处理能力。

Journal ref 2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)

详情

展开后加载摘要…

URL PDF HTML 收藏