Zobrazeno 1 - 10
of 722
pro vyhledávání: '"Wang, Shusen"'
Autor:
Gu, Zhouhong, Zhang, Lin, Zhu, Xiaoxuan, Chen, Jiangjie, Huang, Wenhao, Zhang, Yikai, Wang, Shusen, Ye, Zheyu, Gao, Yan, Feng, Hongwei, Xiao, Yanghua
Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a benchmark called
Externí odkaz:
http://arxiv.org/abs/2406.12641
Autor:
Wang, Shusen
Recommender system (RS) is an established technology with successful applications in social media, e-commerce, entertainment, and more. RSs are indeed key to the success of many popular APPs, such as YouTube, Tik Tok, Xiaohongshu, Bilibili, and other
Externí odkaz:
http://arxiv.org/abs/2308.01204
Autor:
Gu, Zhouhong, Zhu, Xiaoxuan, Ye, Haoning, Zhang, Lin, Wang, Jianchen, Zhu, Yixin, Jiang, Sihang, Xiong, Zhuozhi, Li, Zihan, Wu, Weijie, He, Qianyu, Xu, Rui, Huang, Wenhao, Liu, Jingping, Wang, Zili, Wang, Shusen, Zheng, Weiguo, Feng, Hongwei, Xiao, Yanghua
New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge. Xiezhi com
Externí odkaz:
http://arxiv.org/abs/2306.05783
Large Language Models (LLMs) have attained the impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. However, collecting human-written data of high quality, especially multi-turn dialogues, is expens
Externí odkaz:
http://arxiv.org/abs/2305.14994
Online platforms often incentivize consumers to improve user engagement and platform revenue. Since different consumers might respond differently to incentives, individual-level budget allocation is an essential task in marketing campaigns. Recent ad
Externí odkaz:
http://arxiv.org/abs/2302.04477
We study multi-agent reinforcement learning (MARL) with centralized training and decentralized execution. During the training, new agents may join, and existing agents may unexpectedly leave the training. In such situations, a standard deep MARL mode
Externí odkaz:
http://arxiv.org/abs/2208.02424
Autor:
Bu Hong, Fan Ying, Fan Zhaoqing, Hu Xichun, Li Man, Li Qiao, Liao Ning, Luo Ting, Nie Jianyun, Pan Yueyin, Qi Xiaowei, Shao Zhimin, Song Guohong, Sun Tao, Teng Yue-e, Tong Zhongsheng, Wang Jiayu, Wang Shusen, Wang Xue, Wang Yongsheng, Wang Zhonghua, Xu Binghe, Xu Ling, Xue Yan, Yang Wentao, Yao Herui, Ying Jianming, Yuan Peng, Zhang Jian, Zhang Qingyuan, Zhang Yongqiang, Zhao Jiuda
Publikováno v:
Journal of the National Cancer Center, Vol 3, Iss 4, Pp 266-272 (2023)
Treatment of breast cancer with low expression of human epidermal growth factor receptor 2 (HER2; HER2-low) has drawn much attention in recent years. With the proven therapeutic effect of trastuzumab deruxtecan (T-DXd) in patients with HER2-low (immu
Externí odkaz:
https://doaj.org/article/256852e51361455da409e1403a8b21fa
We study a Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. We stress the constraint of environment hetero
Externí odkaz:
http://arxiv.org/abs/2204.02634
Autor:
Hua, Huijuan, Wang, Yaqi, Wang, Xiaofeng, Wang, Shusen, Zhou, Yunlu, Liu, Yinan, Liang, Zhen, Ren, Huixia, Lu, Sufang, Wu, Shuangshuang, Jiang, Yong, Pu, Yue, Zheng, Xiang, Tang, Chao, Shen, Zhongyang, Li, Cheng, Du, Yuanyuan, Deng, Hongkui
Publikováno v:
In Cell Stem Cell 6 June 2024 31(6):850-865
Autor:
Liu, Kaijing, Li, Ruihao, Wang, Shusen, Fu, Xue, Zhu, Ni, Liang, Xiaoyu, Li, Huiyang, Wang, Xiaoli, Wang, Le, Li, Yongjun, Dai, Jianwu, Yang, Jing
Publikováno v:
In Bioactive Materials June 2024 36:455-473