Zobrazeno 1 - 10
of 14 443
pro vyhledávání: '"Wu, Chao"'
Generative artificial intelligence (GenAI) has made significant progress in understanding world knowledge and generating content from human languages across various modalities, like text-to-text large language models, text-to-image stable diffusion,
Externí odkaz:
http://arxiv.org/abs/2405.14132
We study several types of self-similar solutions for the electron magnetohydrodynamics (MHD) without resistivity, including locally self-similar solutions and pseudo-self-similar solutions. We show that under certain conditions, these types of self-s
Externí odkaz:
http://arxiv.org/abs/2405.00324
Data trading is increasingly gaining attention. However, the inherent replicability and privacy concerns of data make it challenging to directly apply traditional trading theories to data markets. This paper compares data trading markets with traditi
Externí odkaz:
http://arxiv.org/abs/2404.05272
We present PointInfinity, an efficient family of point cloud diffusion models. Our core idea is to use a transformer-based architecture with a fixed-size, resolution-invariant latent representation. This enables efficient training with low-resolution
Externí odkaz:
http://arxiv.org/abs/2404.03566
We study a class of active scalar equations with even non-local operator in the drift term. Non-trivial stationary weak solutions in the space $C^{0-}$ are constructed using the iterative convex integration approach.
Externí odkaz:
http://arxiv.org/abs/2403.16800
Autor:
Liu, Jun, Wu, Chao, Yang, Changdi, Tang, Hao, Kong, Zhenglun, Yuan, Geng, Niu, Wei, Huang, Dong, Wang, Yanzhi
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices. Structured pruning is a widely used method to
Externí odkaz:
http://arxiv.org/abs/2403.10799
With the development of astronomical facilities, large-scale time series data observed by these facilities is being collected. Analyzing anomalies in these astronomical observations is crucial for uncovering potential celestial events and physical ph
Externí odkaz:
http://arxiv.org/abs/2403.10220
Autor:
Zhang, Fengda, He, Qianpei, Kuang, Kun, Liu, Jiashuo, Chen, Long, Wu, Chao, Xiao, Jun, Zhang, Hanwang
Facial Attribute Classification (FAC) holds substantial promise in widespread applications. However, FAC models trained by traditional methodologies can be unfair by exhibiting accuracy inconsistencies across varied data subpopulations. This unfairne
Externí odkaz:
http://arxiv.org/abs/2403.06606
The two-dimensional (2D) multiferroic materials have widespread of application prospects in facilitating the integration and miniaturization of nanodevices. However, it is rarely coupling between the magnetic, ferroelectric, and ferrovalley in one 2D
Externí odkaz:
http://arxiv.org/abs/2403.01070
Federated learning (FL) involves multiple heterogeneous clients collaboratively training a global model via iterative local updates and model fusion. The generalization of FL's global model has a large gap compared with centralized training, which is
Externí odkaz:
http://arxiv.org/abs/2402.18949