Zobrazeno 1 - 10
of 1 303
pro vyhledávání: '"ZHANG Linfeng"'
Autor:
ZHANG Linfeng, LIU Suijun, YANG Linchao, LIU Ying, HU Jiacheng, CAI Jinhui, SHEN Yinchu, LI Shaohua, LI Qing
Publikováno v:
Shipin yu jixie, Vol 39, Iss 8, Pp 84-88 (2023)
Objective: In order to prevent the problem of small range electronic belt scale with inefficient method of traditional intermediate verification, low verification accuracy and security. Methods: A on-line intermediate check device was designed for sm
Externí odkaz:
https://doaj.org/article/874f6b0bab404e928060bc8462bb736e
Autor:
Shi, Yaorui, Li, Sihang, Zhang, Taiyan, Fang, Xi, Wang, Jiankun, Liu, Zhiyuan, Zhao, Guojiang, Zhu, Zhengdan, Gao, Zhifeng, Zhong, Renxin, Zhang, Linfeng, Ke, Guolin, E, Weinan, Cai, Hengxing, Wang, Xiang
Automated drug discovery offers significant potential for accelerating the development of novel therapeutics by substituting labor-intensive human workflows with machine-driven processes. However, a critical bottleneck persists in the inability of cu
Externí odkaz:
http://arxiv.org/abs/2412.07819
Autor:
Zheng, Xu, Xue, Haiwei, Chen, Jialei, Yan, Yibo, Jiang, Lutao, Lyu, Yuanhuiyi, Yang, Kailun, Zhang, Linfeng, Hu, Xuming
Simultaneously using multimodal inputs from multiple sensors to train segmentors is intuitively advantageous but practically challenging. A key challenge is unimodal bias, where multimodal segmentors over rely on certain modalities, causing performan
Externí odkaz:
http://arxiv.org/abs/2411.17141
Autor:
Li, Jungang, Tao, Sicheng, Yan, Yibo, Gu, Xiaojie, Xu, Haodong, Zheng, Xu, Lyu, Yuanhuiyi, Zhang, Linfeng, Hu, Xuming
Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs still face challenges in effectively integrating the rich and diverse
Externí odkaz:
http://arxiv.org/abs/2411.16213
Autor:
Chen, Junzhe, Zhang, Tianshu, Huang, Shiyu, Niu, Yuwei, Zhang, Linfeng, Wen, Lijie, Hu, Xuming
Despite the recent breakthroughs achieved by Large Vision Language Models (LVLMs) in understanding and responding to complex visual-textual contexts, their inherent hallucination tendencies limit their practical application in real-world scenarios th
Externí odkaz:
http://arxiv.org/abs/2411.15268
Autor:
Fang, Xi, Wang, Jiankun, Cai, Xiaochen, Chen, Shangqian, Yang, Shuwen, Yao, Lin, Zhang, Linfeng, Ke, Guolin
In recent decades, chemistry publications and patents have increased rapidly. A significant portion of key information is embedded in molecular structure figures, complicating large-scale literature searches and limiting the application of large lang
Externí odkaz:
http://arxiv.org/abs/2411.11098
The vision tokens in multimodal large language models usually exhibit significant spatial and temporal redundancy and take up most of the input tokens, which harms their inference efficiency. To solve this problem, some recent works were introduced t
Externí odkaz:
http://arxiv.org/abs/2411.10803
Quantum transport calculations are essential for understanding and designing nanoelectronic devices, yet the trade-off between accuracy and computational efficiency has long limited their practical applications. We present a general framework that co
Externí odkaz:
http://arxiv.org/abs/2411.08800
Autor:
Wang, Shaobo, Tang, Hongxuan, Wang, Mingyang, Zhang, Hongrui, Liu, Xuyang, Li, Weiya, Hu, Xuming, Zhang, Linfeng
The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable
Externí odkaz:
http://arxiv.org/abs/2410.21815
Protecting the intellectual property of open-source Large Language Models (LLMs) is very important, because training LLMs costs extensive computational resources and data. Therefore, model owners and third parties need to identify whether a suspect m
Externí odkaz:
http://arxiv.org/abs/2410.14273