Zobrazeno 1 - 10
of 872
pro vyhledávání: '"Wang, Zilin"'
Autor:
Chen, Shengqi, Wang, Zilin, Dai, Jianrong, Qin, Shirui, Cao, Ying, Zhao, Ruiao, Chen, Jiayun, Wu, Guohua, Tang, Yuan
Objective: Ensuring the precision in motion tracking for MRI-guided Radiotherapy (MRIgRT) is crucial for the delivery of effective treatments. This study refined the motion tracking accuracy in MRIgRT through the innovation of an automatic real-time
Externí odkaz:
http://arxiv.org/abs/2411.07503
Autor:
Wang, Mingze, Wang, Jinbo, He, Haotian, Wang, Zilin, Huang, Guanhua, Xiong, Feiyu, Li, Zhiyu, E, Weinan, Wu, Lei
In this work, we propose an Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning, thereby improving generalization and convergence. Specifically, IRE decouples the dynamics of flat and sha
Externí odkaz:
http://arxiv.org/abs/2405.20763
Autor:
Hughes, Lillian B., Meynell, Simon A., Wu, Weijie, Parthasarathy, Shreyas, Chen, Lingjie, Zhang, Zhiran, Wang, Zilin, Davis, Emily J., Mukherjee, Kunal, Yao, Norman Y., Jayich, Ania C. Bleszynski
Systems of spins with strong dipolar interactions and controlled dimensionality enable new explorations in quantum sensing and simulation. In this work, we investigate the creation of strong dipolar interactions in a two-dimensional ensemble of nitro
Externí odkaz:
http://arxiv.org/abs/2404.10075
Autor:
Wang, Zilin, Zhuang, Haolin, Li, Lu, Zhang, Yinmin, Zhong, Junjie, Chen, Jun, Yang, Yu, Tang, Boshi, Wu, Zhiyong
This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models. Current models often generate monotonous and simplistic dance
Externí odkaz:
http://arxiv.org/abs/2312.11442
Inverse reinforcement learning (IRL) aims to explicitly infer an underlying reward function based on collected expert demonstrations. Considering that obtaining expert demonstrations can be costly, the focus of current IRL techniques is on learning a
Externí odkaz:
http://arxiv.org/abs/2310.08823
Autor:
Yang, Sicheng, Wang, Zilin, Wu, Zhiyong, Li, Minglei, Zhang, Zhensong, Huang, Qiaochu, Hao, Lei, Xu, Songcen, Wu, Xiaofei, yang, changpeng, Dai, Zonghong
The automatic co-speech gesture generation draws much attention in computer animation. Previous works designed network structures on individual datasets, which resulted in a lack of data volume and generalizability across different motion capture sta
Externí odkaz:
http://arxiv.org/abs/2309.07051
Autor:
Chen, Jun, Rao, Wei, Wang, Zilin, Lin, Jiuxin, Ju, Yukai, He, Shulin, Wang, Yannan, Wu, Zhiyong
The previous SpEx+ has yielded outstanding performance in speaker extraction and attracted much attention. However, it still encounters inadequate utilization of multi-scale information and speaker embedding. To this end, this paper proposes a new ef
Externí odkaz:
http://arxiv.org/abs/2306.16250
Recent advances in visual reinforcement learning (RL) have led to impressive success in handling complex tasks. However, these methods have demonstrated limited generalization capability to visual disturbances, which poses a significant challenge for
Externí odkaz:
http://arxiv.org/abs/2306.00656
Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
Autor:
Ma, Guozheng, Zhang, Linrui, Wang, Haoyu, Li, Lu, Wang, Zilin, Wang, Zhen, Shen, Li, Wang, Xueqian, Tao, Dacheng
Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra auxiliary
Externí odkaz:
http://arxiv.org/abs/2305.16379
Traditional blockchain design gives miners or validators full control over transaction ordering, i.e., they can freely choose which transactions to include or exclude, as well as in which order. While not an issue initially, the emergence of decentra
Externí odkaz:
http://arxiv.org/abs/2305.05206