Zobrazeno 1 - 10
of 791
pro vyhledávání: '"Li Jianxiong"'
Publikováno v:
Shanghai yufang yixue, Vol 34, Iss 12, Pp 1188-1191 (2022)
Anaphylactic shock is a serious and rare adverse reaction， which can be life-threatening if not treated in time. COVID-19 vaccine is a newly marketed vaccine， and people pay high attention to its adverse reactions. This report summarized the inve
Externí odkaz:
https://doaj.org/article/011352fbdb744d608e89dc8cd40ac424
Autor:
Li, Jianxiong, Li, Boyang, Guo, Zhuoqiang, Li, Mingzhen, Li, Enji, Liu, Lijun, Yuan, Guojun, Wang, Zhan, Tan, Guangming, Jia, Weile
Physical phenomena such as chemical reactions, bond breaking, and phase transition require molecular dynamics (MD) simulation with ab initio accuracy ranging from milliseconds to microseconds. However, previous state-of-the-art neural network based M
Externí odkaz:
http://arxiv.org/abs/2410.22867
The network is becoming Domain-Specific, which requires on-demand design of the network protocols, as well as the microarchitecture of the NIC. However, to develop such a NIC is not that easy. Since the scissor gap between network speed and the growt
Externí odkaz:
http://arxiv.org/abs/2410.08476
Autor:
Li, Jianxiong, Wang, Zhihao, Zheng, Jinliang, Zhou, Xiaoai, Wang, Guanming, Song, Guanglu, Liu, Yu, Liu, Jingjing, Zhang, Ya-Qin, Yu, Junzhi, Zhan, Xianyuan
Multimodal task specification is essential for enhanced robotic performance, where \textit{Cross-modality Alignment} enables the robot to holistically understand complex task instructions. Directly annotating multimodal instructions for model trainin
Externí odkaz:
http://arxiv.org/abs/2410.01529
Autor:
Niu, Haoyi, Chen, Qimao, Liu, Tenglong, Li, Jianxiong, Zhou, Guyue, Zhang, Yi, Hu, Jianming, Zhan, Xianyuan
Reusing pre-collected data from different domains is an appealing solution for decision-making tasks that have insufficient data in the target domain but are relatively abundant in other related domains. Existing cross-domain policy transfer methods
Externí odkaz:
http://arxiv.org/abs/2409.08687
Publikováno v:
Jixie qiangdu, Vol 42, Pp 966-970 (2020)
The main drive system of rolling mill is a complicated electromechanical system,as the main device of transmitting motion and torque. The factor of electromechanical coupling is one of the important reasons for the abnormal variation of torsional vib
Externí odkaz:
https://doaj.org/article/bfbd282adee4427d876e4572ad53899a
Autor:
Zheng, Jinliang, Li, Jianxiong, Cheng, Sijie, Zheng, Yinan, Li, Jiaming, Liu, Jihao, Liu, Yu, Liu, Jingjing, Zhan, Xianyuan
Instruction following is crucial in contemporary LLM. However, when extended to multimodal setting, it often suffers from misalignment between specific textual instruction and targeted local region of an image. To achieve more accurate and nuanced mu
Externí odkaz:
http://arxiv.org/abs/2405.19783
Autor:
Li, Jianxiong, Zheng, Jinliang, Zheng, Yinan, Mao, Liyuan, Hu, Xiao, Cheng, Sijie, Niu, Haoyi, Liu, Jihao, Liu, Yu, Liu, Jingjing, Zhang, Ya-Qin, Zhan, Xianyuan
Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing
Externí odkaz:
http://arxiv.org/abs/2402.18137
Autor:
Zheng, Yinan, Li, Jianxiong, Yu, Dongjie, Yang, Yujie, Li, Shengbo Eben, Zhan, Xianyuan, Liu, Jingjing
Safe offline RL is a promising way to bypass risky online interactions towards safe policy learning. Most existing methods only enforce soft constraints, i.e., constraining safety violations in expectation below thresholds predetermined. This can lea
Externí odkaz:
http://arxiv.org/abs/2401.10700
Preference-based reinforcement learning (PbRL) provides a natural way to align RL agents' behavior with human desired outcomes, but is often restrained by costly human feedback. To improve feedback efficiency, most existing PbRL methods focus on sele
Externí odkaz:
http://arxiv.org/abs/2305.17400