Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Chen, Huancheng"'
Recent text-to-image diffusion models excel at generating high-resolution images from text but struggle with precise control over spatial composition and object counting. To address these challenges, several studies developed layout-to-image (L2I) ap
Externí odkaz:
http://arxiv.org/abs/2411.10495
In the era of foundation models, we revisit continual learning~(CL), which aims to enable vision transformers (ViTs) to learn new tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a persistent challenge
Externí odkaz:
http://arxiv.org/abs/2411.00623
Autor:
Chen, Huancheng, Vikalo, Haris
Gradient inversion (GI) attacks present a threat to the privacy of clients in federated learning (FL) by aiming to enable reconstruction of the clients' data from communicated model updates. A number of such techniques attempts to accelerate data rec
Externí odkaz:
http://arxiv.org/abs/2405.00955
Autor:
Chen, Huancheng, Vikalo, Haris
Statistical heterogeneity of data present at client devices in a federated learning (FL) system renders the training of a global model in such systems difficult. Particularly challenging are the settings where due to communication resource constraint
Externí odkaz:
http://arxiv.org/abs/2310.00198
Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years, personalized federa
Externí odkaz:
http://arxiv.org/abs/2301.08968
Autor:
Chen, Huancheng, Vikalo, Haris
Federated learning (FL) is a privacy-promoting framework that enables potentially large number of clients to collaboratively train machine learning models. In a FL system, a server coordinates the collaboration by collecting and aggregating clients'
Externí odkaz:
http://arxiv.org/abs/2206.00686
Publikováno v:
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2021
Several applications such as autonomous driving, augmented reality and virtual reality require a precise prediction of the 3D human pose. Recently, a new problem was introduced in the field to predict the 3D human poses from observed 2D poses. We pro
Externí odkaz:
http://arxiv.org/abs/2109.10257
Autor:
Chen, Qin, Zhou, Yuxing, Xu, Binjie, Lou, Zhefeng, Chen, Huancheng, Chen, Shuijin, Wu, Chunxiang, Du, Jianhua, Wang, Hangdong, Yang, Jinhu, Fang, Minghu
Publikováno v:
CHIN. PHYS. LETT. Vol. 38, No. 8 (2021) 087501
Compounds with the A15 structure have attracted extensive attention due to their superconductivity and nontrivial topological band structure. We have successfully grown Nb$_3$Sb single crystals with a A15 structure and systematically measured the lon
Externí odkaz:
http://arxiv.org/abs/2107.14689
Autor:
Chen, Qin, Lou, Zhefeng, Zhang, ShengNan, Zhou, Yuxing, Xu, Binjie, Chen, Huancheng, Chen, Shuijin, Du, Jianhua, Wang, Hangdong, Yang, Jinhu, Wu, QuanSheng, Yazyev, Oleg V., Fang, Minghu
Publikováno v:
Phys. Rev. B 104, 115104 (2021)
The extremely large magnetoresistance (XMR) observed in many topologically nontrivial and trivial semimetals has attracted much attention in relation to its underlying physical mechanism. In this paper, by combining the band structure and Fermi surfa
Externí odkaz:
http://arxiv.org/abs/2104.03799
Autor:
Zhou, Yuxing, Li, Bin, Lou, Zhefeng, Chen, Huancheng, Chen, Qin, Xu, Binjie, Wu, Chunxiang, Du, Jianhua, Yang, Jinhu, Wang, Hangdong, Fang, Minghu
Publikováno v:
Sci. China-Phys. Mech. Astron. 64, 247411(2021)
A feasible strategy to realize the Majorana fermions is searching for a simple compound with both bulk superconductivity and Dirac surface states. In this paper, we performed calculations of electronic band structure, the Fermi surface and surface st
Externí odkaz:
http://arxiv.org/abs/2012.03274