Zobrazeno 1 - 10
of 227
pro vyhledávání: '"Zhang, Shufei"'
With the increasing prevalence of graph-structured data, multi-view graph clustering has been widely used in various downstream applications. Existing approaches primarily rely on a unified message passing mechanism, which significantly enhances clus
Externí odkaz:
http://arxiv.org/abs/2410.03596
Autor:
Zhang, Di, Wu, Jianbo, Lei, Jingdi, Che, Tong, Li, Jiatong, Xie, Tong, Huang, Xiaoshui, Zhang, Shufei, Pavone, Marco, Li, Yuqiang, Ouyang, Wanli, Zhou, Dongzhan
This paper presents an advanced mathematical problem-solving framework, LLaMA-Berry, for enhancing the mathematical reasoning ability of Large Language Models (LLMs). The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to
Externí odkaz:
http://arxiv.org/abs/2410.02884
Autor:
Li, Junxian, Zhang, Di, Wang, Xunzhi, Hao, Zeying, Lei, Jingdi, Tan, Qian, Zhou, Cai, Liu, Wei, Yang, Yaotian, Xiong, Xinrui, Wang, Weiyun, Chen, Zhe, Wang, Wenhai, Li, Wei, Zhang, Shufei, Su, Mao, Ouyang, Wanli, Li, Yuqiang, Zhou, Dongzhan
Large Language Models (LLMs) have achieved remarkable success and have been applied across various scientific fields, including chemistry. However, many chemical tasks require the processing of visual information, which cannot be successfully handled
Externí odkaz:
http://arxiv.org/abs/2408.07246
Autor:
Xu, Han, Cui, Taoyong, Tang, Chenyu, Zhou, Dongzhan, Li, Yuqiang, Gao, Xiang, Gong, Xingao, Ouyang, Wanli, Zhang, Shufei, Su, Mao
Machine learning interatomic potentials (MLIPs) have been widely used to facilitate large scale molecular simulations with ab initio level accuracy. However, MLIP-based molecular simulations frequently encounter the issue of collapse due to decreased
Externí odkaz:
http://arxiv.org/abs/2407.13994
Autor:
Cui, Taoyong, Tang, Chenyu, Zhou, Dongzhan, Li, Yuqiang, Gong, Xingao, Ouyang, Wanli, Su, Mao, Zhang, Shufei
Machine learning interatomic potentials (MLIPs) enable more efficient molecular dynamics (MD) simulations with ab initio accuracy, which have been used in various domains of physical science. However, distribution shift between training and test data
Externí odkaz:
http://arxiv.org/abs/2405.08308
Autor:
Li, Ruifeng, Zhou, Dongzhan, Shen, Ancheng, Zhang, Ao, Su, Mao, Li, Mingqian, Chen, Hongyang, Chen, Gang, Zhang, Yin, Zhang, Shufei, Li, Yuqiang, Ouyang, Wanli
Artificial intelligence (AI) technology has demonstrated remarkable potential in drug dis-covery, where pharmacokinetics plays a crucial role in determining the dosage, safety, and efficacy of new drugs. A major challenge for AI-driven drug discovery
Externí odkaz:
http://arxiv.org/abs/2404.10354
Autor:
Zhang, Di, Liu, Wei, Tan, Qian, Chen, Jingdan, Yan, Hang, Yan, Yuliang, Li, Jiatong, Huang, Weiran, Yue, Xiangyu, Ouyang, Wanli, Zhou, Dongzhan, Zhang, Shufei, Su, Mao, Zhong, Han-Sen, Li, Yuqiang
Large language models (LLMs) have made impressive progress in chemistry applications. However, the community lacks an LLM specifically designed for chemistry. The main challenges are two-fold: firstly, most chemical data and scientific knowledge are
Externí odkaz:
http://arxiv.org/abs/2402.06852
Autor:
Cui, Taoyong, Tang, Chenyu, Su, Mao, Zhang, Shufei, Li, Yuqiang, Bai, Lei, Dong, Yuhan, Gong, Xingao, Ouyang, Wanli
Publikováno v:
Published in Nature Machine Intelligence 2024
Machine learning interatomic potentials (MLIPs) enables molecular dynamics (MD) simulations with ab initio accuracy and has been applied to various fields of physical science. However, the performance and transferability of MLIPs are limited by insuf
Externí odkaz:
http://arxiv.org/abs/2309.15718
In this paper, we focus on tackling the precise keypoint coordinates regression task. Most existing approaches adopt complicated networks with a large number of parameters, leading to a heavy model with poor cost-effectiveness in practice. To overcom
Externí odkaz:
http://arxiv.org/abs/2202.09115
In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial training method through robust
Externí odkaz:
http://arxiv.org/abs/2107.04401