Zobrazeno 1 - 10
of 311
pro vyhledávání: '"Xu Shusheng"'
Autor:
Xu, Shusheng, Fu, Wei, Gao, Jiaxuan, Ye, Wenjie, Liu, Weilin, Mei, Zhiyu, Wang, Guangju, Yu, Chao, Wu, Yi
Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free. Novel app
Externí odkaz:
http://arxiv.org/abs/2404.10719
Publikováno v:
2024 IEEE International Conference on Robotics and Automation (ICRA 2024)
We aim to control a robot to physically behave in the real world following any high-level language command like "cartwheel" or "kick". Although human motion datasets exist, this task remains particularly challenging since generative models can produc
Externí odkaz:
http://arxiv.org/abs/2306.10518
Autor:
Liu, Xuanrui, Le, Kai, Wang, Jiandong, Lin, Hao, Liu, Yuzhen, Jiang, Fengchun, Yang, Zhenlin, Li, Haixin, Xu, Shusheng, Liu, Weimin
Publikováno v:
In Applied Surface Science 30 September 2024 668
Autor:
Ning, Wenwen, Xu, Shusheng, Wang, Peiqingfeng, Ma, Hui, Yang, Xiujin, Sun, Xuecheng, Yang, Chao, Shi, Xue-Rong
Publikováno v:
In Journal of Energy Storage 15 August 2024 96
Autor:
Ma, Hui, Xu, Shusheng, Wang, Peiqingfeng, Zhu, Jiaqing, Yang, Chao, Zhang, Shengming, Shi, Xue-Rong, Yao, Lu
Publikováno v:
In Applied Surface Science 1 August 2024 663
Autor:
Lin, Hao, Liang, Wenping, Miao, Qiang, Qi, Yan, Zhou, Shaoyun, Jia, Feilong, Lan, Hao, Xu, Shusheng
Publikováno v:
In Surface & Coatings Technology 15 July 2024 487
We present Native Chinese Reader (NCR), a new machine reading comprehension (MRC) dataset with particularly long articles in both modern and classical Chinese. NCR is collected from the exam questions for the Chinese course in China's high schools, w
Externí odkaz:
http://arxiv.org/abs/2112.06494
A ubiquitous requirement in many practical reinforcement learning (RL) applications, including medical treatment, recommendation system, education and robotics, is that the deployed policy that actually interacts with the environment cannot change fr
Externí odkaz:
http://arxiv.org/abs/2112.06424
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused an ongoing pandemic infecting 219 million people as of 10/19/21, with a 3.6% mortality rate. Natural selection can generate favorable mutations with improved fitness advantages;
Externí odkaz:
http://arxiv.org/abs/2111.01969
Publikováno v:
Journal of Applied Physics; 4/14/2024, Vol. 135 Issue 14, p1-8, 8p