Zobrazeno 1 - 10
of 743
pro vyhledávání: '"Hu, Junhao"'
Autor:
Hu, Junhao, Huang, Wenrui, Wang, Haoyi, Wang, Weidong, Hu, Tiancheng, Zhang, Qin, Feng, Hao, Chen, Xusheng, Shan, Yizhou, Xie, Tao
Large Language Models (LLMs) are critical for a wide range of applications, but serving them efficiently becomes increasingly challenging as inputs become more complex. Context caching improves serving performance by exploiting inter-request dependen
Externí odkaz:
http://arxiv.org/abs/2410.15332
Autor:
Hu, Cunchen, Huang, Heyang, Hu, Junhao, Xu, Jiang, Chen, Xusheng, Xie, Tao, Wang, Chenxi, Wang, Sa, Bao, Yungang, Sun, Ninghui, Shan, Yizhou
Large language model (LLM) serving has transformed from stateless to stateful systems, utilizing techniques like context caching and disaggregated inference. These optimizations extend the lifespan and domain of the KV cache, necessitating a new arch
Externí odkaz:
http://arxiv.org/abs/2406.17565
This paper focuses on the randomized Milstein scheme for approximating solutions to stochastic Volterra integral equations with weakly singular kernels, where the drift coefficients are non-differentiable. An essential component of the error analysis
Externí odkaz:
http://arxiv.org/abs/2312.03474
Deformable image registration (DIR) is an active research topic in biomedical imaging. There is a growing interest in developing DIR methods based on deep learning (DL). A traditional DL approach to DIR is based on training a convolutional neural net
Externí odkaz:
http://arxiv.org/abs/2310.04297
By using the It\^{o}-Tanaka trick, we prove the unique strong solvability as well as the gradient estimates for stochastic differential equations with irregular drifts in low regularity Lebesgue-H\"{o}lder space $L^q(0,T;{\mathcal C}_b^\alpha({\mathb
Externí odkaz:
http://arxiv.org/abs/2310.00421
Recently, deep learning-based techniques have shown promising performance on various tasks related to software engineering. For these learning-based approaches to perform well, obtaining high-quality data is one fundamental and crucial issue. The com
Externí odkaz:
http://arxiv.org/abs/2308.06898
In this article, we consider slow-fast McKean-Vlasov stochastic differential equations driven by Brownian motions and fractional Brownian motions. We give a definition of the large deviation principle (LDP) on the product space related to Brownian mo
Externí odkaz:
http://arxiv.org/abs/2306.00289
This paper focuses on the numerical scheme of highly nonlinear neutral multiple-delay stohchastic McKean-Vlasov equation (NMSMVE) by virtue of the stochastic particle method. First, under general assumptions, the results about propagation of chaos in
Externí odkaz:
http://arxiv.org/abs/2302.09724
Autor:
Wang, Chaozheng, Hu, Junhao, Gao, Cuiyun, Jin, Yu, Xie, Tao, Huang, Hailiang, Lei, Zhenyu, Deng, Yuetang
Code completion has become a common practice for programmers during their daily programming activities. It aims at automatically predicting the next tokens or lines that the programmers tend to use. A good code completion tool can substantially save
Externí odkaz:
http://arxiv.org/abs/2301.03846
Autor:
Xue, Hailong1 (AUTHOR), Hu, Junhao1,2 (AUTHOR), Chen, Yingge1 (AUTHOR), Huang, Wenbin1 (AUTHOR), Liu, Haoling1 (AUTHOR), Xu, Hongli1 (AUTHOR), Shi, Ming2 (AUTHOR) biomidas@163.com
Publikováno v:
BMC Neurology. 10/7/2024, Vol. 24 Issue 1, p1-8. 8p.
