Zobrazeno 1 - 10
of 11 752
pro vyhledávání: '"ZHANG, XINYU"'
Studying unified model averaging estimation for situations with complicated data structures, we propose a novel model averaging method based on cross-validation (MACV). MACV unifies a large class of new and existing model averaging estimators and cov
Externí odkaz:
http://arxiv.org/abs/2412.09804
Radio-frequency (RF) Radiance Field reconstruction is a challenging problem. The difficulty lies in the interactions between the propagating signal and objects, such as reflections and diffraction, which are hard to model precisely, especially when t
Externí odkaz:
http://arxiv.org/abs/2412.08003
Autor:
Lu, Hannan, Wu, Xiaohe, Wang, Shudong, Qin, Xiameng, Zhang, Xinyu, Han, Junyu, Zuo, Wangmeng, Tao, Ji
Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms for spatial
Externí odkaz:
http://arxiv.org/abs/2412.03520
Autor:
Zhou, Changzhi, Song, Dandan, Tian, Yuhang, Wu, Zhijing, Wang, Hao, Zhang, Xinyu, Yang, Jun, Yang, Ziyi, Zhang, Shuhao
Recently, Large Language Models (LLMs) have garnered increasing attention in the field of natural language processing, revolutionizing numerous downstream tasks with powerful reasoning and generation abilities. For example, In-Context Learning (ICL)
Externí odkaz:
http://arxiv.org/abs/2412.02279
Autor:
Zhang, Xinyu, Zhang, Lingling, Wu, Yanrui, Huang, Muye, Wu, Wenjun, Li, Bo, Wang, Shaowei, Liu, Jun
Visual Question Generation (VQG) has gained significant attention due to its potential in educational applications. However, VQG researches mainly focus on natural images, neglecting diagrams in educational materials used to assess students' conceptu
Externí odkaz:
http://arxiv.org/abs/2411.17771
Removing adverse weather conditions such as rain, raindrop, and snow from images is critical for various real-world applications, including autonomous driving, surveillance, and remote sensing. However, existing multi-task approaches typically rely o
Externí odkaz:
http://arxiv.org/abs/2411.16739
We study the global symmetries of the $\mathbb{Z}_2$-orbifold of N=4 Super-Yang-Mills theory and its marginal deformations. The process of orbifolding to obtain an N=2 theory would appear to break the $\mathrm{SU}(4)$ R-symmetry down to $\mathrm{SU}(
Externí odkaz:
http://arxiv.org/abs/2411.11612
Radio frequency (RF) propagation modeling poses unique electromagnetic simulation challenges. While recent neural representations have shown success in visible spectrum rendering, the fundamentally different scales and physics of RF signals require n
Externí odkaz:
http://arxiv.org/abs/2411.18635
Autor:
Yang, Lei, Zhang, Xinyu, Li, Jun, Wang, Chen, Song, Zhiying, Zhao, Tong, Song, Ziying, Wang, Li, Zhou, Mo, Shen, Yang, Wu, Kai, Lv, Chen
Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, ther
Externí odkaz:
http://arxiv.org/abs/2411.10962
The Structured Dialogue System, referred to as SuDoSys, is an innovative Large Language Model (LLM)-based chatbot designed to provide psychological counseling. SuDoSys leverages the World Health Organization (WHO)'s Problem Management Plus (PM+) guid
Externí odkaz:
http://arxiv.org/abs/2411.10681