1 code implementation • 22 Apr 2024 • Zichuan Liu, Zefan Wang, Linjie Xu, Jinyu Wang, Lei Song, Tianchun Wang, Chunlin Chen, Wei Cheng, Jiang Bian
The advent of large language models (LLMs) has revolutionized the field of natural language processing, yet they might be attacked to produce harmful content.
no code implementations • 15 Apr 2024 • Linjie Xu, Zichuan Liu, Alexander Dockhorn, Diego Perez-Liebana, Jinyu Wang, Lei Song, Jiang Bian
One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency.
1 code implementation • The Journal of Supercomputing 2023 • Wangxing Chen, Haifeng Sang, Jinyu Wang, Zishan Zhao
STIGCN considers the correlation between social interaction and pedestrian movement factors to achieve more accurate interaction modeling.
1 code implementation • 6 Jun 2023 • Linjie Xu, Zhengyao Jiang, Jinyu Wang, Lei Song, Jiang Bian
Offline reinforcement learning (RL) methodologies enforce constraints on the policy to adhere closely to the behavior policy, thereby stabilizing value learning and mitigating the selection of out-of-distribution (OOD) actions during test time.
no code implementations • 23 Apr 2023 • Xin Jin, Wu Zhou, Jinyu Wang, Duo Xu, Yiqing Rong, Jialin Sun
In order to guide the generation task of AI music performance, and to improve the performance effect of human performers, this paper uses Birkhoff's aesthetic measure to propose a method of objective measurement of beauty.
no code implementations • 14 Jan 2023 • Xin Jin, Wu Zhou, Jinyu Wang, Duo Xu, Yiqing Rong, Shuai Cui
Computational aesthetics evaluation has made great achievements in the field of visual arts, but the research work on music still needs to be explored.