Zobrazeno 41 - 50
of 2 160
pro vyhledávání: '"Li, Siyuan"'
Demonstrations are widely used in Deep Reinforcement Learning (DRL) for facilitating solving tasks with sparse rewards. However, the tasks in real-world scenarios can often have varied initial conditions from the demonstration, which would require ad
Externí odkaz:
http://arxiv.org/abs/2307.02889
Autor:
Tan, Cheng, Li, Siyuan, Gao, Zhangyang, Guan, Wenfei, Wang, Zedong, Liu, Zicheng, Wu, Lirong, Li, Stan Z.
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsupervised manner. Despite remarkable progress in recent years, a lack of
Externí odkaz:
http://arxiv.org/abs/2306.11249
In recent years, AI-assisted drug design methods have been proposed to generate molecules given the pockets' structures of target proteins. Most of them are atom-level-based methods, which consider atoms as basic components and generate atom position
Externí odkaz:
http://arxiv.org/abs/2306.13769
Autor:
Yang, Rushuai, Bai, Chenjia, Guo, Hongyi, Li, Siyuan, Zhao, Bin, Wang, Zhen, Liu, Peng, Li, Xuelong
In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI objective tends
Externí odkaz:
http://arxiv.org/abs/2305.04477
Autor:
Li, Siyuan, Wang, Yongpan, Dong, Chaopeng, Yang, Shouguo, Li, Hong, Sun, Hao, Lang, Zhe, Chen, Zuxin, Wang, Weijie, Zhu, Hongsong, Sun, Limin
Third-party libraries (TPLs) are extensively utilized by developers to expedite the software development process and incorporate external functionalities. Nevertheless, insecure TPL reuse can lead to significant security risks. Existing methods are e
Externí odkaz:
http://arxiv.org/abs/2305.04026
The ability to recognize, localize and track dynamic objects in a scene is fundamental to many real-world applications, such as self-driving and robotic systems. Yet, traditional multiple object tracking (MOT) benchmarks rely only on a few object cat
Externí odkaz:
http://arxiv.org/abs/2304.08408
Autor:
Wang, Xiao, Zhou, Weikang, Zu, Can, Xia, Han, Chen, Tianze, Zhang, Yuansen, Zheng, Rui, Ye, Junjie, Zhang, Qi, Gui, Tao, Kang, Jihua, Yang, Jingsheng, Li, Siyuan, Du, Chunsai
Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have difficulty with information extraction tasks. For example, gpt-3.5-turbo ach
Externí odkaz:
http://arxiv.org/abs/2304.08085
In the field of artificial intelligence for science, it is consistently an essential challenge to face a limited amount of labeled data for real-world problems. The prevailing approach is to pretrain a powerful task-agnostic model on a large unlabele
Externí odkaz:
http://arxiv.org/abs/2304.03906
Autor:
Zheng, Jiangbin, Wang, Ge, Huang, Yufei, Hu, Bozhen, Li, Siyuan, Tan, Cheng, Fan, Xinwen, Li, Stan Z.
Pretrained protein structure models without labels are crucial foundations for the majority of protein downstream applications. The conventional structure pretraining methods follow the mature natural language pretraining methods such as denoised rec
Externí odkaz:
http://arxiv.org/abs/2303.11783
Autor:
Zheng, Jiangbin, Wang, Yile, Tan, Cheng, Li, Siyuan, Wang, Ge, Xia, Jun, Chen, Yidong, Li, Stan Z.
Sign language recognition (SLR) is a weakly supervised task that annotates sign videos as textual glosses. Recent studies show that insufficient training caused by the lack of large-scale available sign datasets becomes the main bottleneck for SLR. M
Externí odkaz:
http://arxiv.org/abs/2303.05725