Zobrazeno 1 - 10
of 1 194
pro vyhledávání: '"XU Yifeng"'
Recently, large-scale diffusion models have made impressive progress in text-to-image (T2I) generation. To further equip these T2I models with fine-grained spatial control, approaches like ControlNet introduce an extra network that learns to follow a
Externí odkaz:
http://arxiv.org/abs/2410.09400
A nonlinear Helmholtz (NLH) equation with high frequencies and corner singularities is discretized by the linear finite element method (FEM). After deriving some wave-number-explicit stability estimates and the singularity decomposition for the NLH p
Externí odkaz:
http://arxiv.org/abs/2405.15344
In this paper, we discuss adaptive approximations of an elliptic eigenvalue optimization problem in a phase-field setting by a conforming finite element method. An adaptive algorithm is proposed and implemented in several two dimensional numerical ex
Externí odkaz:
http://arxiv.org/abs/2310.03970
Effective image restoration with large-size corruptions, such as blind image inpainting, entails precise detection of corruption region masks which remains extremely challenging due to diverse shapes and patterns of corruptions. In this work, we pres
Externí odkaz:
http://arxiv.org/abs/2308.14061
Publikováno v:
Journal of Computational Physics, 2024
In this work, we develop an adaptive algorithm for the efficient numerical solution of the minimum compliance problem in topology optimization. The algorithm employs the phase field approximation and continuous density field. The adaptive procedure i
Externí odkaz:
http://arxiv.org/abs/2308.06756
Publikováno v:
Clinical Proteomics. 10/16/2024, Vol. 21 Issue 1, p1-11. 11p.
Autor:
XU Yifeng1, KE Shiwen2, LI Keke1, YAN Zhaoqi1, XU Yueqi1, XU Xiaogang1, WANG Yu1, LIU Liangji2 llj6505@163.com
Publikováno v:
Chinese Journal of Immunology. Oct2024, Vol. 40 Issue 10, p2108-2115. 8p.
Non-independent and identically distributed (non-IID) data is a key challenge in federated learning (FL), which usually hampers the optimization convergence and the performance of FL. Existing data augmentation methods based on federated generative m
Externí odkaz:
http://arxiv.org/abs/2211.13116
Publikováno v:
In Colloids and Surfaces A: Physicochemical and Engineering Aspects 20 November 2024 701
Autor:
Xin, Xipeng, Xu, Yifeng, Liu, Qingdong, Zhu, Yiqiu, Chen, Hu, Chen, Wei, Gao, Lian, Song, Xuefeng
Publikováno v:
In Chemical Engineering Journal 1 November 2024 499