Zobrazeno 1 - 10
of 3 979
pro vyhledávání: '"WANG, Haoran"'
Autor:
Wang, Haoran, Dai, Cunxi, Wang, Siyuan, Zhang, Ximan, Zhu, Zheng, Liu, Xiaohan, Zhou, Jianxiang, Liu, Zhengtao, Jia, Zhenzhong
This paper introduces two field transportation robots. Both robots are equipped with transformable wheel-leg modules, which can smoothly switch between operation modes and can work in various challenging terrains. SWhegPro, with six S-shaped legs, en
Externí odkaz:
http://arxiv.org/abs/2410.18507
Goal-conditioned hierarchical reinforcement learning (HRL) decomposes complex reaching tasks into a sequence of simple subgoal-conditioned tasks, showing significant promise for addressing long-horizon planning in large-scale environments. This paper
Externí odkaz:
http://arxiv.org/abs/2410.09505
3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering. However, 3DGS assumes that the scene is in a clear medium environment and struggles to generate satisfactory representations in underwater scenes
Externí odkaz:
http://arxiv.org/abs/2410.01517
Autor:
Huang, Zhehao, Cheng, Xinwen, Zheng, JingHao, Wang, Haoran, He, Zhengbao, Li, Tao, Huang, Xiaolin
Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigation into approximate MU starts with identifying the steepest descent di
Externí odkaz:
http://arxiv.org/abs/2409.19732
Autor:
Wang, Haoran
Dispersive estimate for the fourth order Schr\"odinger operator with a class of scaling-critical magnetic potentials in dimension two was obtained by the construction of the corresponding resolvent kernel and the stationary phase method.
Comment
Comment
Externí odkaz:
http://arxiv.org/abs/2408.16473
Autor:
Wang, Haoran, Mai, Xinji, Tao, Zeng, Wang, Yan, Yu, Jiawen, Zhou, Ziheng, Tong, Xuan, Yan, Shaoqi, Zhao, Qing, Gao, Shuyong, Zhang, Wenqiang
Affective Forecasting, a research direction in psychology that predicts individuals future emotions, is often constrained by numerous external factors like social influence and temporal distance. To address this, we transform Affective Forecasting in
Externí odkaz:
http://arxiv.org/abs/2407.16406
Autor:
Mai, Xinji, Lin, Junxiong, Wang, Haoran, Tao, Zeng, Wang, Yan, Yan, Shaoqi, Tong, Xuan, Yu, Jiawen, Wang, Boyang, Zhou, Ziheng, Zhao, Qing, Gao, Shuyong, Zhang, Wenqiang
In the field of affective computing, fully leveraging information from a variety of sensory modalities is essential for the comprehensive understanding and processing of human emotions. Inspired by the process through which the human brain handles em
Externí odkaz:
http://arxiv.org/abs/2407.15590
Cooperative Adaptive Cruise Control (CACC) often requires human takeover for tasks such as exiting a freeway. Direct human takeover can pose significant risks, especially given the close-following strategy employed by CACC, which might cause drivers
Externí odkaz:
http://arxiv.org/abs/2407.11551
Autor:
Lau, Matthew, Wang, Haoran, Helbling, Alec, Hul, Matthew, Peng, ShengYun, Andreoni, Martin, Lunardi, Willian T., Lee, Wenke
The robustness of machine learning models has been questioned by the existence of adversarial examples. We examine the threat of adversarial examples in practical applications that require lightweight models for one-class classification. Building on
Externí odkaz:
http://arxiv.org/abs/2407.06372
Few-shot unsupervised domain adaptation (FS-UDA) utilizes few-shot labeled source domain data to realize effective classification in unlabeled target domain. However, current FS-UDA methods are still suffer from two issues: 1) the data from different
Externí odkaz:
http://arxiv.org/abs/2407.04066