Zobrazeno 1 - 10
of 618
pro vyhledávání: '"Guo, Jiawei"'
Diffusion Transformer, the backbone of Sora for video generation, successfully scales the capacity of diffusion models, pioneering new avenues for high-fidelity sequential data generation. Unlike static data such as images, sequential data consists o
Externí odkaz:
http://arxiv.org/abs/2407.16134
Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough images to work with, leading to pro
Externí odkaz:
http://arxiv.org/abs/2407.05666
Autor:
Guo, Jiawei, Li, Ziming, Liu, Xueling, Ma, Kaijing, Zheng, Tianyu, Yu, Zhouliang, Pan, Ding, LI, Yizhi, Liu, Ruibo, Wang, Yue, Guo, Shuyue, Qu, Xingwei, Yue, Xiang, Zhang, Ge, Chen, Wenhu, Fu, Jie
Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks, includ
Externí odkaz:
http://arxiv.org/abs/2404.03543
Autor:
Ji, Tianying, Liang, Yongyuan, Zeng, Yan, Luo, Yu, Xu, Guowei, Guo, Jiawei, Zheng, Ruijie, Huang, Furong, Sun, Fuchun, Xu, Huazhe
The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rew
Externí odkaz:
http://arxiv.org/abs/2402.14528
Autor:
Zheng, Tianyu, Guo, Shuyue, Qu, Xingwei, Guo, Jiawei, Zhang, Weixu, Du, Xinrun, Jia, Qi, Lin, Chenghua, Huang, Wenhao, Chen, Wenhu, Fu, Jie, Zhang, Ge
In this paper, we introduce Kun, a novel approach for creating high-quality instruction-tuning datasets for large language models (LLMs) without relying on manual annotations. Adapting a self-training algorithm based on instruction back-translation a
Externí odkaz:
http://arxiv.org/abs/2401.06477
For multi-scale problems, the conventional physics-informed neural networks (PINNs) face some challenges in obtaining available predictions. In this paper, based on PINNs, we propose a practical deep learning framework for multi-scale problems by rec
Externí odkaz:
http://arxiv.org/abs/2308.06672
Publikováno v:
Computer Methods in Applied Mechanics and Engineering, 2023
Given the facts of the extensiveness of multi-material diffusion problems and the inability of the standard PINN(Physics-Informed Neural Networks) method for such problems, in this paper we present a novel PINN method that can accurately solve the mu
Externí odkaz:
http://arxiv.org/abs/2305.09125
Publikováno v:
Journal of Computational Physics, 2023
The physics informed neural network (PINN) is a promising method for solving time-evolution partial differential equations (PDEs). However, the standard PINN method may fail to solve the PDEs with strongly nonlinear characteristics or those with high
Externí odkaz:
http://arxiv.org/abs/2212.00798
Autor:
Zhou, Hui1,2 (AUTHOR) zhouh@iwhr.com, Guo, Jiawei3 (AUTHOR) guoguo123123@emails.imau.edu.cn, Liu, Hu1,2 (AUTHOR) liuh@iwhr.com, Wang, Jian1 (AUTHOR) wangjian@iwhr.com, Wang, Yongqiang3 (AUTHOR) wangjian@iwhr.com
Publikováno v:
Agronomy. Jul2024, Vol. 14 Issue 7, p1529. 23p.
Autor:
Li Chengyi, Liu Ran, Xiong Zhenyu, Bao Xue, Liang Sijia, Zeng Haotian, Jin Wei, Gong Quan, Liu Lian, Guo Jiawei
Publikováno v:
Acta Biochimica et Biophysica Sinica, Vol 56, Pp 331-344 (2024)
Atherosclerosis (AS), the main contributor to acute cardiovascular events, such as myocardial infarction and ischemic stroke, is characterized by necrotic core formation and plaque instability induced by cell death. The mechanisms of cell death in AS
Externí odkaz:
https://doaj.org/article/3c169694499e498090840b49ea8f3ab6