Zobrazeno 1 - 10
of 10 155
pro vyhledávání: '"Gao,Chao"'
The advent of foundation models have revolutionized various fields, enabling unprecedented task accuracy and flexibility in computational linguistics, computer vision and other domains. Attention mechanism has become an essential component of foundat
Externí odkaz:
http://arxiv.org/abs/2411.17720
Autor:
Luo, Yuetian, Gao, Chao
This paper studies the construction of adaptive confidence intervals under Huber's contamination model when the contamination proportion is unknown. For the robust confidence interval of a Gaussian mean, we show that the optimal length of an adaptive
Externí odkaz:
http://arxiv.org/abs/2410.22647
This paper explores the problem of class-generalizable anomaly detection, where the objective is to train one unified AD model that can generalize to detect anomalies in diverse classes from different domains without any retraining or fine-tuning on
Externí odkaz:
http://arxiv.org/abs/2410.20047
We consider deep deterministic policy gradient (DDPG) in the context of reinforcement learning with sparse rewards. To enhance exploration, we introduce a search procedure, \emph{${\epsilon}{t}$-greedy}, which generates exploratory options for explor
Externí odkaz:
http://arxiv.org/abs/2410.05225
We consider testing the goodness-of-fit of a distribution against alternatives separated in sup norm. We study the twin settings of Poisson-generated count data with a large number of categories and high-dimensional multinomials. In previous studies
Externí odkaz:
http://arxiv.org/abs/2409.08871
In this paper, we consider partially observable timed automata endowed with a single clock. A time interval is associated with each transition specifying at which clock values it may occur. In addition, a resetting condition associated to a transitio
Externí odkaz:
http://arxiv.org/abs/2409.05810
We investigate the ground-state properties and quantum phase transitions of an ensemble consisting of $N$ four-level atoms within an optical cavity coupled to the single cavity mode and external laser fields. The system is described by an extended im
Externí odkaz:
http://arxiv.org/abs/2408.10121
This study evaluates the performance of Recurrent Neural Network (RNN) and Transformer models in replicating cross-language structural priming, a key indicator of abstract grammatical representations in human language processing. Focusing on Chinese-
Externí odkaz:
http://arxiv.org/abs/2405.09508
Publikováno v:
Phys. Rev. Lett. 133, 163401 (2024)
The work intends to extend the moir\'e physics to three dimensions. Three-dimensional moir\'e patterns can be realized in ultracold atomic gases by coupling two spin states in spin-dependent optical lattices with a relative twist, a structure current
Externí odkaz:
http://arxiv.org/abs/2404.19608
The translation symmetry of a lattice is greatly modified when subjected to a perpendicular magnetic field [Zak, Phys. Rev. \textbf{134}, A1602 (1964)]. This change in symmetry can lead to magnetic unit cells that are substantially larger than the or
Externí odkaz:
http://arxiv.org/abs/2404.08211