Jinchao Xu

most citedExpressivity and Approximation Properties of Deep Neural Networks with ReLU

^{k}

Activation

3 citations · 5 across the 3 of their papers we have counts for

collaborators

3 papers

cs.CL2024

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Juhao Liang, Zhenyang Cai, Jianqing Zhu +9

The alignment of large language models (LLMs) is critical for developing effective and safe language models. Traditional approaches focus on aligning models during the instruction…

cs.LG2024★ 3 cited

Expressivity and Approximation Properties of Deep Neural Networks with ReLU $^{k}$ Activation

Juncai He, Tong Mao, Jinchao Xu

In this paper, we investigate the expressivity and approximation properties of deep neural networks employing the ReLU $^{k}$ activation function for $k \geq 2$ . Although deep ReLU ne…

math.NA2024★ 2 cited

Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions

Juncai He, Jinchao Xu

In this study, we establish that deep neural networks employing ReLU and ReLU $^{2}$ activation functions can effectively represent Lagrange finite element functions of any order on v…

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs

Expressivity and Approximation Properties of Deep Neural Networks with ReLUk Activation

Deep Neural Networks and Finite Elements of Any Order on Arbitrary Dimensions

Expressivity and Approximation Properties of Deep Neural Networks with ReLU $^{k}$ Activation