Zobrazeno 1 - 10
of 59
pro vyhledávání: '"WU Qiyu"'
Publikováno v:
Zhejiang dianli, Vol 43, Iss 5, Pp 10-17 (2024)
In the context of the “dual carbon” goals， photovoltaic energy storage charging stations （PSCSs） are gradually emerging as the mainstream form of electric vehicle （EV） charging stations. To address the uncertainty associated with photov
Externí odkaz:
https://doaj.org/article/67f1ef8dd6fe4201a97b16b8c3d2770a
Publikováno v:
电力工程技术, Vol 43, Iss 3, Pp 99-110 (2024)
With the development of the smart grid, power quality issues have been widespread in the power grid and it threaten the safety and stability of the power grid. The monitoring data of power quality disturbances (PQDs) increase rapidly, and it is of gr
Externí odkaz:
https://doaj.org/article/dd67c0a945eb4d1399e8d9d0e0cadc17
Reinforcement Learning (RL) empowers agents to acquire various skills by learning from reward signals. Unfortunately, designing high-quality instance-level rewards often demands significant effort. An emerging alternative, RL with delayed reward, foc
Externí odkaz:
http://arxiv.org/abs/2410.20176
The problem of hallucination and omission, a long-standing problem in machine translation (MT), is more pronounced when a large language model (LLM) is used in MT because an LLM itself is susceptible to these phenomena. In this work, we mitigate the
Externí odkaz:
http://arxiv.org/abs/2405.09223
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word representati
Externí odkaz:
http://arxiv.org/abs/2404.02490
Autor:
Liu, Guangyi, Wang, Yu, Feng, Zeyu, Wu, Qiyu, Tang, Liping, Gao, Yuan, Li, Zhen, Cui, Shuguang, McAuley, Julian, Yang, Zichao, Xing, Eric P., Hu, Zhiting
The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and
Externí odkaz:
http://arxiv.org/abs/2402.19009
In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world scenarios,
Externí odkaz:
http://arxiv.org/abs/2402.03771
Medical Image Hierarchical Multi-Label Classification (MI-HMC) is of paramount importance in modern healthcare, presenting two significant challenges: data imbalance and \textit{hierarchy constraint}. Existing solutions involve complex model architec
Externí odkaz:
http://arxiv.org/abs/2311.00282
Autor:
Wu, Qiyu, Zhao, Mengjie, He, Yutong, Huang, Lang, Ono, Junya, Wakaki, Hiromi, Mitsufuji, Yuki
Reporting bias arises when people assume that some knowledge is universally understood and hence, do not necessitate explicit elaboration. In this paper, we focus on the wide existence of reporting bias in visual-language datasets, embodied as the ob
Externí odkaz:
http://arxiv.org/abs/2310.01330
Learning multi-lingual sentence embeddings is a fundamental task in natural language processing. Recent trends in learning both mono-lingual and multi-lingual sentence embeddings are mainly based on contrastive learning (CL) among an anchor, one posi
Externí odkaz:
http://arxiv.org/abs/2309.08929