Zobrazeno 1 - 10
of 834
pro vyhledávání: '"Du, Quan"'
Autor:
Wang, Chenglong, Gan, Yang, Huo, Yifu, Mu, Yongyu, Yang, Murun, He, Qiaozhi, Xiao, Tong, Zhang, Chunliang, Liu, Tongran, Du, Quan, Yang, Di, Zhu, Jingbo
Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using human-pre
Externí odkaz:
http://arxiv.org/abs/2408.12109
Autor:
Wang, Chenglong, Zhou, Hang, Chang, Kaiyan, Liu, Tongran, Zhang, Chunliang, Du, Quan, Xiao, Tong, Zhu, Jingbo
Large language models achieve state-of-the-art performance on sequence generation evaluation, but typically have a large number of parameters. This is a computational challenge as presented by applying their evaluation capability at scale. To overcom
Externí odkaz:
http://arxiv.org/abs/2308.04386
Publikováno v:
Acta Biochimica et Biophysica Sinica, Vol 56, Pp 645-656 (2024)
Spontaneous subarachnoid hemorrhage (SAH) is a kind of hemorrhagic stroke which causes neurological deficits in survivors. Huperzine A has a neuroprotective effect, but its role in SAH is unclear. Therefore, we explore the effect of Huperzine A on ne
Externí odkaz:
https://doaj.org/article/6e4fb1a67fd54a888a2f53208b3f923d
Autor:
Li, Bei, Du, Quan, Zhou, Tao, Jing, Yi, Zhou, Shuhan, Zeng, Xin, Xiao, Tong, Zhu, JingBo, Liu, Xuebo, Zhang, Min
Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE). This paper explores a deeper relationship between Transformer and numerical ODE methods. We first show that a residual block of layers in Transformer
Externí odkaz:
http://arxiv.org/abs/2203.09176
Publikováno v:
In Translational Oncology June 2024 44
It has been found that residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODEs). In this paper, we explore a deeper relationship between Transformer and numerical methods of ODEs. We show that a residual bl
Externí odkaz:
http://arxiv.org/abs/2104.02308
Recently, deep models have shown tremendous improvements in neural machine translation (NMT). However, systems of this kind are computationally expensive and memory intensive. In this paper, we take a natural step towards learning strong but light-we
Externí odkaz:
http://arxiv.org/abs/2012.13866
Autor:
Li, Yanyang, Luo, Yingfeng, Lin, Ye, Du, Quan, Wang, Huizhen, Huang, Shujian, Xiao, Tong, Zhu, Jingbo
Unsupervised Bilingual Dictionary Induction methods based on the initialization and the self-learning have achieved great success in similar language pairs, e.g., English-Spanish. But they still fail and have an accuracy of 0% in many distant languag
Externí odkaz:
http://arxiv.org/abs/2011.14874
Autor:
Li, Bei, Wang, Ziyang, Liu, Hui, Jiang, Yufan, Du, Quan, Xiao, Tong, Wang, Huizhen, Zhu, Jingbo
Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but training an extremely deep encoder is time consuming. Moreover, why deep models help NMT is an open question. In this paper, we investigate the
Externí odkaz:
http://arxiv.org/abs/2010.03737
Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest the effectiveness of transferr
Externí odkaz:
http://arxiv.org/abs/2009.09152