Zobrazeno 1 - 10
of 12 168
pro vyhledávání: '"ZHANG, MIAO"'
Autor:
Zhang, Yue, Che, Xinyang, Wei, Yuanbang, Tian, Rui, Li, Yi-an, Zhang, Miao, Li, Shuai, Liu, Bo
Uncertainty principle is one of the fundamental principles of quantum mechanics. Exploring such uncertainty relations in pre- and postselected (PPS) systems, where weak measurements on post-selected states have been used as a powerful tool for explor
Externí odkaz:
http://arxiv.org/abs/2412.13399
Autor:
Wu, Xinle, Wu, Xingjian, Zhang, Dalin, Zhang, Miao, Guo, Chenjuan, Yang, Bin, Jensen, Christian S.
Societal and industrial infrastructures and systems increasingly leverage sensors that emit correlated time series. Forecasting of future values of such time series based on recorded historical values has important benefits. Automatically designed mo
Externí odkaz:
http://arxiv.org/abs/2411.05833
Decentralized Federated Learning has emerged as an alternative to centralized architectures due to its faster training, privacy preservation, and reduced communication overhead. In decentralized communication, the server aggregation phase in Centrali
Externí odkaz:
http://arxiv.org/abs/2410.07272
Decentralized Federated Learning (DFL) surpasses Centralized Federated Learning (CFL) in terms of faster training, privacy preservation, and light communication, making it a promising alternative in the field of federated learning. However, DFL still
Externí odkaz:
http://arxiv.org/abs/2410.06482
Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to the field of vision, achieving significant accomplishments on the expe
Externí odkaz:
http://arxiv.org/abs/2409.19345
Label-free single-molecule detection is essential for studying biomolecules in their native state, yet having materials with intrinsic molecular specificity to identify a broad range of molecules without complex functionalization remains challenging.
Externí odkaz:
http://arxiv.org/abs/2409.18702
Diffusion models (DMs) have demonstrated exceptional generative capabilities across various areas, while they are hindered by slow inference speeds and high computational demands during deployment. The most common way to accelerate DMs involves reduc
Externí odkaz:
http://arxiv.org/abs/2409.03550
Autor:
Jiang, Junpeng, Hong, Gangyi, Zhou, Lijun, Ma, Enhui, Hu, Hengtong, Zhou, Xia, Xiang, Jie, Liu, Fan, Yu, Kaicheng, Sun, Haiyang, Zhan, Kun, Jia, Peng, Zhang, Miao
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned problem, i.e
Externí odkaz:
http://arxiv.org/abs/2409.01595
Automatic and precise medical image segmentation (MIS) is of vital importance for clinical diagnosis and analysis. Current MIS methods mainly rely on the convolutional neural network (CNN) or self-attention mechanism (Transformer) for feature modelin
Externí odkaz:
http://arxiv.org/abs/2408.13698
Autor:
Liu, Zixuan, Xu, Hanwen, Woicik, Addie, Shapiro, Linda G., Blazes, Marian, Wu, Yue, Steffen, Verena, Cukras, Catherine, Lee, Cecilia S., Zhang, Miao, Lee, Aaron Y., Wang, Sheng
We present OCTCube-M, a 3D OCT-based multi-modal foundation model for jointly analyzing OCT and en face images. OCTCube-M first developed OCTCube, a 3D foundation model pre-trained on 26,685 3D OCT volumes encompassing 1.62 million 2D OCT images. It
Externí odkaz:
http://arxiv.org/abs/2408.11227