Zobrazeno 1 - 10
of 456
pro vyhledávání: '"Li, Boyan"'
Large Language Models (LLMs) have demonstrated impressive capabilities across a range of scientific tasks including mathematics, physics, and chemistry. Despite their successes, the effectiveness of LLMs in handling complex statistical tasks remains
Externí odkaz:
http://arxiv.org/abs/2406.07815
Translating users' natural language questions into SQL queries (i.e., NL2SQL) significantly lowers the barriers to accessing relational databases. The emergence of Large Language Models has introduced a novel paradigm in NL2SQL tasks, enhancing capab
Externí odkaz:
http://arxiv.org/abs/2406.01265
Autor:
Hu, Kaiyuan, Chen, Yongting, Han, Kaiying, Liu, Junhua, Yang, Haowen, Jin, Yili, Li, Boyan, Wang, Fangxin
Volumetric video has emerged as a prominent medium within the realm of eXtended Reality (XR) with the advancements in computer graphics and depth capture hardware. Users can fully immersive themselves in volumetric video with the ability to switch th
Externí odkaz:
http://arxiv.org/abs/2310.08205
Autor:
Li, Boyan, Leng, Luziwei, Shen, Shuaijie, Zhang, Kaixuan, Zhang, Jianguo, Liao, Jianxing, Cheng, Ran
Advancements in adapting deep convolution architectures for Spiking Neural Networks (SNNs) have significantly enhanced image classification performance and reduced computational burdens. However, the inability of Multiplication-Free Inference (MFI) t
Externí odkaz:
http://arxiv.org/abs/2306.12465
Autor:
SUN Zilong, FU Jiaolong, WANG Yue, ZHOU Yunfeng, LI Boyan, QIAN Wei, BAI Jing, JU Xin, LI Liangzhi
Publikováno v:
Shipin Kexue, Vol 44, Iss 23, Pp 231-251 (2023)
ε-Poly-L-lysine (ε-PL) is a novel biopolymer consisting of 25–35 L-lysine residues, which is formed by the dehydration condensation of ε-NH2 and α-COOH. ε-PL possesses many excellent characteristics, such as antimicrobial activity, edibility,
Externí odkaz:
https://doaj.org/article/2f22dc491a594b358075ce6f9dab0614
Autor:
Sang, Tong, Tang, Hongyao, Ma, Yi, Hao, Jianye, Zheng, Yan, Meng, Zhaopeng, Li, Boyan, Wang, Zhen
Deep Reinforcement Learning (DRL) has been a promising solution to many complex decision-making problems. Nevertheless, the notorious weakness in generalization among environments prevent widespread application of DRL agents in real-world scenarios.
Externí odkaz:
http://arxiv.org/abs/2204.02877
Autor:
Liu, Lei, Yuan, Jialei, Li, Boyan, Feng, Wei, Wang, Xinyu, Zhao, Ke, Tang, Chengwei, Wang, Ping, Guo, Yongchun, Li, Jianping
Publikováno v:
In Journal of Alloys and Compounds 25 June 2024 989
Publikováno v:
In Environmental Technology & Innovation May 2024 34
Autor:
Li, Boyan, Tang, Hongyao, Zheng, Yan, Hao, Jianye, Li, Pengyi, Wang, Zhen, Meng, Zhaopeng, Wang, Li
Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or c
Externí odkaz:
http://arxiv.org/abs/2109.05490
Publikováno v:
In Expert Systems With Applications 15 October 2024 252 Part B