Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Duan, Yawen"'
Autor:
Ji, Jiaming, Qiu, Tianyi, Chen, Boyuan, Zhang, Borong, Lou, Hantao, Wang, Kaile, Duan, Yawen, He, Zhonghao, Zhou, Jiayi, Zhang, Zhaowei, Zeng, Fanzhi, Ng, Kwan Yee, Dai, Juntao, Pan, Xuehai, O'Gara, Aidan, Lei, Yingshan, Xu, Hua, Tse, Brian, Fu, Jie, McAleer, Stephen, Yang, Yaodong, Wang, Yizhou, Zhu, Song-Chun, Guo, Yike, Gao, Wen
AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve
Externí odkaz:
http://arxiv.org/abs/2310.19852
Autor:
Chan, Alan, Salganik, Rebecca, Markelius, Alva, Pang, Chris, Rajkumar, Nitarshan, Krasheninnikov, Dmitrii, Langosco, Lauro, He, Zhonghao, Duan, Yawen, Carroll, Micah, Lin, Michelle, Mayhew, Alex, Collins, Katherine, Molamohammadi, Maryam, Burden, John, Zhao, Wanru, Rismani, Shalaleh, Voudouris, Konstantinos, Bhatt, Umang, Weller, Adrian, Krueger, David, Maharaj, Tegan
Research in Fairness, Accountability, Transparency, and Ethics (FATE) has established many sources and forms of algorithmic harm, in domains as diverse as health care, finance, policing, and recommendations. Much work remains to be done to mitigate t
Externí odkaz:
http://arxiv.org/abs/2302.10329
Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly focused on th
Externí odkaz:
http://arxiv.org/abs/2301.03652
Autor:
Wang, Tony T., Gleave, Adam, Tseng, Tom, Pelrine, Kellin, Belrose, Nora, Miller, Joseph, Dennis, Michael D., Duan, Yawen, Pogrebniak, Viktor, Levine, Sergey, Russell, Stuart
We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our adversaries do not win by playing Go well. Instead, they trick KataGo
Externí odkaz:
http://arxiv.org/abs/2211.00241
Recent breakthroughs of Neural Architecture Search (NAS) extend the field's research scope towards a broader range of vision tasks and more diversified search spaces. While existing NAS methods mostly design architectures on a single task, algorithms
Externí odkaz:
http://arxiv.org/abs/2105.11871
Autor:
Chen, Xin, Duan, Yawen, Chen, Zewei, Xu, Hang, Chen, Zihao, Liang, Xiaodan, Zhang, Tong, Li, Zhenguo
Neural Architecture Search (NAS) achieved many breakthroughs in recent years. In spite of its remarkable progress, many algorithms are restricted to particular search spaces. They also lack efficient mechanisms to reuse knowledge when confronting mul
Externí odkaz:
http://arxiv.org/abs/2007.09380
Autor:
Chen, Qing, Ding, Lijun, Duan, Yawen, Shi, Chunlei, Li, ke, Guo, Chunfeng, Gao, Zhenpeng, Liu, Bin
Publikováno v:
In Food Bioscience December 2023 56
Autor:
Zhang, Xia, Duan, Yawen, Duan, Jianping, Chen, Liang, Jian, Dongnan, Lv, Meixia, Yang, Qing, Ma, Zhuguo
Publikováno v:
In Atmospheric Research 1 August 2022 273
Publikováno v:
In Journal of Hydrology April 2022 607
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.